论文周报 | 推荐系统领域最新研究进展，含SIGIR、WWW、CHI等顶会论文

本文精选了上周（0417-0423）最新发布的30篇推荐系统相关论文，主要的研究领域为会话推荐和序列推荐，所利用的技术包括遗忘学习、注意力机制、提示学习、去偏学习、长尾学习、图神经网络、对比学习、扩散模型、多任务学习、ChatGPT、ODE等。

以下整理了论文标题以及摘要，如感兴趣可移步原文精读。

1. Selective and Collaborative Influence Function for Efficient Recommendation Unlearning

2. Frequency Enhanced Hybrid Attention Network for Sequential Recommendation, SIGIR2023

3. Privacy-Preserving Matrix Factorization for Recommendation Systems using Gaussian Mechanism

4. Improving Items and Contexts Understanding with Descriptive Graph for Conversational Recommendation

5. A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits, CHI2023

6. Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations, WWW2023

7. Discreetly Exploiting Inter-session Information for Session-based Recommendation

8. Dual-Ganularity Contrastive Learning for Session-based Recommendation

9. PEGA: Personality-Guided Preference Aggregator for Ephemeral Group Recommendation

10. CAViaR: Context Aware Video Recommendations, WWW2023

11. MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation, SIGIR2023

12. Attention Mixtures for Time-Aware Sequential Recommendation, SIGIR2023

13. PerCoNet: News Recommendation with Explicit Persona and Contrastive Learning

14. Causal Disentangled Variational Auto-Encoder for Preference Understanding in Recommendation

15. M2GNN: Metapath and Multi-interest Aggregated Graph Neural Network for Tag-based Cross-domain Recommendation, SIGIR2023

16. Meta-optimized Contrastive Learning for Sequential Recommendation

17. Hierarchical and Contrastive Representation Learning for Knowledge-aware Recommendation, ICME2023

18. Intent-aware Ranking Ensemble for Personalized Recommendation, SIGIR2023

19. HEAT: A Highly Efficient and Affordable Training System for Collaborative Filtering Based Recommendation on CPUs, ICS2023

20. Learning Graph ODE for Continuous-Time Sequential Recommendation

21. A Diffusion model for POI recommendation

22. Is ChatGPT a Good Recommender? A Preliminary Study

23. Sheaf Neural Networks for Graph-based Recommender Systems

24. CAM2: Conformity-Aware Multi-Task Ranking Model for Large-Scale Recommender Systems, WWW2023

25. Causal Decision Transformer for Recommender Systems via Offline Reinforcement Learning

26. PBNR: Prompt-based News Recommender System

27. More Is Less: When Do Recommenders Underperform for Data-rich Users?

28. FairRec: Fairness Testing for Deep Recommender Systems

29. PIE: Personalized Interest Exploration for Large-Scale Recommender Systems, WWW2023

30. Always Strengthen Your Strengths: A Drift-Aware Incremental Learning Framework for CTR Prediction, SIGIR2023

以上论文pdf版本可在以下链接打包获取：

https://github.com/hongleizhang/RSPapers/tree/master/00-Latest_Papers/RS_Weekly/0417-0423/

1. Selective and Collaborative Influence Function for Efficient Recommendation Unlearning

Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Yizhao Zhang, Biao Gong, Jun Wang

https://arxiv.org/abs/2304.10199

Recent regulations on the Right to be Forgotten have greatly influenced the way of running a recommender system, because users now have the right to withdraw their private data. Besides simply deleting the target data in the database, unlearning the associated data lineage e.g., the learned personal features and preferences in the model, is also necessary for data withdrawal. Existing unlearning methods are mainly devised for generalized machine learning models in classification tasks. In this paper, we first identify two main disadvantages of directly applying existing unlearning methods in the context of recommendation, i.e., (i) unsatisfactory efficiency for large-scale recommendation models and (ii) destruction of collaboration across users and items. To tackle the above issues, we propose an extra-efficient recommendation unlearning method based on Selective and Collaborative Influence Function (SCIF). Our proposed method can (i) avoid any kind of retraining which is computationally prohibitive for large-scale systems, (ii) further enhance efficiency by selectively updating user embedding and (iii) preserve the collaboration across the remaining users and items. Furthermore, in order to evaluate the unlearning completeness, we define a Membership Inference Oracle (MIO), which can justify whether the unlearned data points were in the training set of the model, i.e., whether a data point was completely unlearned. Extensive experiments on two benchmark datasets demonstrate that our proposed method can not only greatly enhance unlearning efficiency, but also achieve adequate unlearning completeness. More importantly, our proposed method outperforms the state-of-the-art unlearning method regarding comprehensive recommendation metrics.

2. Frequency Enhanced Hybrid Attention Network for Sequential Recommendation, SIGIR2023

Xinyu Du, Huanhuan Yuan, Pengpeng Zhao, Fuzhen Zhuang, Guanfeng Liu, Yanchi Liu

https://arxiv.org/abs/2304.09184

The self-attention mechanism, which equips with a strong capability of modeling long-range dependencies, is one of the extensively used techniques in the sequential recommendation field. However, many recent studies represent that current self-attention based models are low-pass filters and are inadequate to capture high-frequency information. Furthermore, since the items in the user behaviors are intertwined with each other, these models are incomplete to distinguish the inherent periodicity obscured in the time domain. In this work, we shift the perspective to the frequency domain, and propose a novel Frequency Enhanced Hybrid Attention Network for Sequential Recommendation, namely FEARec. In this model, we firstly improve the original time domain self-attention in the frequency domain with a ramp structure to make both low-frequency and high-frequency information could be explicitly learned in our approach. Moreover, we additionally design a similar attention mechanism via auto-correlation in the frequency domain to capture the periodic characteristics and fuse the time and frequency level attention in a union model. Finally, both contrastive learning and frequency regularization are utilized to ensure that multiple views are aligned in both the time domain and frequency domain. Extensive experiments conducted on four widely used benchmark datasets demonstrate that the proposed model performs significantly better than the state-of-the-art approaches.

3. Privacy-Preserving Matrix Factorization for Recommendation Systems using Gaussian Mechanism

Sohan Salahuddin Mugdho, Hafiz Imtiaz

https://arxiv.org/abs/2304.09096

Building a recommendation system involves analyzing user data, which can potentially leak sensitive information about users. Anonymizing user data is often not sufficient for preserving user privacy. Motivated by this, we propose a privacy-preserving recommendation system based on the differential privacy framework and matrix factorization, which is one of the most popular algorithms for recommendation systems. As differential privacy is a powerful and robust mathematical framework for designing privacy-preserving machine learning algorithms, it is possible to prevent adversaries from extracting sensitive user information even if the adversary possesses their publicly available (auxiliary) information. We implement differential privacy via the Gaussian mechanism in the form of output perturbation and release user profiles that satisfy privacy definitions. We employ Rényi Differential Privacy for a tight characterization of the overall privacy loss. We perform extensive experiments on real data to demonstrate that our proposed algorithm can offer excellent utility for some parameter choices, while guaranteeing strict privacy.

4. Improving Items and Contexts Understanding with Descriptive Graph for Conversational Recommendation

Huy Dao, Dung D. Le, Cuong Chu

https://arxiv.org/abs/2304.09093

State-of-the-art methods on conversational recommender systems (CRS) leverage external knowledge to enhance both items' and contextual words' representations to achieve high quality recommendations and responses generation. However, the representations of the items and words are usually modeled in two separated semantic spaces, which leads to misalignment issue between them. Consequently, this will cause the CRS to only achieve a sub-optimal ranking performance, especially when there is a lack of sufficient information from the user's input. To address limitations of previous works, we propose a new CRS framework KLEVER, which jointly models items and their associated contextual words in the same semantic space. Particularly, we construct an item descriptive graph from the rich items' textual features, such as item description and categories. Based on the constructed descriptive graph, KLEVER jointly learns the embeddings of the words and items, towards enhancing both recommender and dialog generation modules. Extensive experiments on benchmarking CRS dataset demonstrate that KLEVER achieves superior performance, especially when the information from the users' responses is lacking.

5. A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits, CHI2023

Liu Leqi, Giulio Zhou, Fatma Kılınç-Karzan, Zachary C. Lipton, Alan L. Montgomery

https://arxiv.org/abs/2304.09088

Personalized recommender systems suffuse modern life, shaping what media we read and what products we consume. Algorithms powering such systems tend to consist of supervised learning-based heuristics, such as latent factor models with a variety of heuristically chosen prediction targets. Meanwhile, theoretical treatments of recommendation frequently address the decision-theoretic nature of the problem, including the need to balance exploration and exploitation, via the multi-armed bandits (MABs) framework. However, MAB-based approaches rely heavily on assumptions about human preferences. These preference assumptions are seldom tested using human subject studies, partly due to the lack of publicly available toolkits to conduct such studies. In this work, we conduct a study with crowdworkers in a comics recommendation MABs setting. Each arm represents a comic category, and users provide feedback after each recommendation. We check the validity of core MABs assumptions-that human preferences (reward distributions) are fixed over time-and find that they do not hold. This finding suggests that any MAB algorithm used for recommender systems should account for human preference dynamics. While answering these questions, we provide a flexible experimental framework for understanding human preference dynamics and testing MABs algorithms with human users. The code for our experimental framework and the collected data can be found at

6. Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations, WWW2023

Haoxuan Li, Yanghao Xiao, Chunyuan Zheng, Peng Wu

https://arxiv.org/abs/2304.09085

Recommender systems are seen as an effective tool to address information overload, but it is widely known that the presence of various biases makes direct training on large-scale observational data result in sub-optimal prediction performance. In contrast, unbiased ratings obtained from randomized controlled trials or A/B tests are considered to be the golden standard, but are costly and small in scale in reality. To exploit both types of data, recent works proposed to use unbiased ratings to correct the parameters of the propensity or imputation models trained on the biased dataset. However, the existing methods fail to obtain accurate predictions in the presence of unobserved confounding or model misspecification. In this paper, we propose a theoretically guaranteed model-agnostic balancing approach that can be applied to any existing debiasing method with the aim of combating unobserved confounding and model misspecification. The proposed approach makes full use of unbiased data by alternatively correcting model parameters learned with biased data, and adaptively learning balance coefficients of biased samples for further debiasing. Extensive real-world experiments are conducted along with the deployment of our proposal on four representative debiasing methods to demonstrate the effectiveness.

7. Discreetly Exploiting Inter-session Information for Session-based Recommendation

Zihan Wang, Gang wu, Haotong Wang

https://arxiv.org/abs/2304.08894

Limited intra-session information is the performance bottleneck of the early GNN based SBR models. Therefore, some GNN based SBR models have evolved to introduce additional inter-session information to facilitate the next-item prediction. However, we found that the introduction of inter-session information may bring interference to these models. The possible reasons are twofold. First, inter-session dependencies are not differentiated at the factor-level. Second, measuring inter-session weight by similarity is not enough. In this paper, we propose DEISI to solve the problems. For the first problem, DEISI differentiates the types of inter-session dependencies at the factor-level with the help of DRL technology. For the second problem, DEISI introduces stability as a new metric for weighting inter-session dependencies together with the similarity. Moreover, CL is used to improve the robustness of the model. Extensive experiments on three datasets show the superior performance of the DEISI model compared with the state-of-the-art models.

8. Dual-Ganularity Contrastive Learning for Session-based Recommendation

Zihan Wang, Gang Wu, Haotong Wang

https://arxiv.org/abs/2304.08873

Session-based recommendation systems(SBRS) are more suitable for the current e-commerce and streaming media recommendation scenarios and thus have become a hot topic. The data encountered by SBRS is typically highly sparse, which also serves as one of the bottlenecks limiting the accuracy of recommendations. So Contrastive Learning(CL) is applied in SBRS owing to its capability of improving embedding learning under the condition of sparse data. However, existing CL strategies are limited in their ability to enforce finer-grained (e.g., factor-level) comparisons and, as a result, are unable to capture subtle differences between instances. More than that, these strategies usually use item or segment dropout as a means of data augmentation which may result in sparser data and thus ineffective self-supervised signals. By addressing the two aforementioned limitations, we introduce a novel multi-granularity CL framework. Specifically, two extra augmented embedding convolution channels with different granularities are constructed and the embeddings learned by them are compared with those learned from original view to complete the CL tasks. At factor-level, we employ Disentangled Representation Learning to obtain finer-grained data(e.g. factor-level embeddings), with which we can construct factor-level convolution channels. At item-level, the star graph is deployed as the augmented data and graph convolution on it can ensure the effectiveness of self-supervised signals. Compare the learned embeddings of these two views with the learned embeddings of the basic view to achieve CL at two granularities. Finally, the more precise item-level and factor-level embeddings obtained are referenced to generate personalized recommendations for the user. The proposed model is validated through extensive experiments on two benchmark datasets, showcasing superior performance compared to existing methods.

9. PEGA: Personality-Guided Preference Aggregator for Ephemeral Group Recommendation

Guangze Ye, Wen Wu, Liye Shi, Wenxin Hu, Xin Chen, Liang He

https://arxiv.org/abs/2304.08851

Recently, making recommendations for ephemeral groups which contain dynamic users and few historic interactions have received an increasing number of attention. The main challenge of ephemeral group recommender is how to aggregate individual preferences to represent the group's overall preference. Score aggregation and preference aggregation are two commonly-used methods that adopt hand-craft predefined strategies and data-driven strategies, respectively. However, they neglect to take into account the importance of the individual inherent factors such as personality in the group. In addition, they fail to work well due to a small number of interactive records. To address these issues, we propose a Personality-Guided Preference Aggregator (PEGA) for ephemeral group recommendation. Concretely, we first adopt hyper-rectangle to define the concept of Group Personality. We then use the personality attention mechanism to aggregate group preferences. The role of personality in our approach is twofold: (1) To estimate individual users' importance in a group and provide explainability; (2) to alleviate the data sparsity issue that occurred in ephemeral groups. The experimental results demonstrate that our model significantly outperforms the state-of-the-art methods w.r.t. the score of both Recall and NDCG on Amazon and Yelp datasets.

10. CAViaR: Context Aware Video Recommendations, WWW2023

Khushhall Chandra Mahajan, Aditya Palnitkar, Ameya Raul, Brad Schumitsch

https://arxiv.org/abs/2304.08435

Many recommendation systems rely on point-wise models, which score items individually. However, point-wise models generating scores for a video are unable to account for other videos being recommended in a query. Due to this, diversity has to be introduced through the application of heuristic-based rules, which are not able to capture user preferences, or make balanced trade-offs in terms of diversity and item relevance. In this paper, we propose a novel method which introduces diversity by modeling the impact of low diversity on user's engagement on individual items, thus being able to account for both diversity and relevance to adjust item scores. The proposed method is designed to be easily pluggable into existing large-scale recommender systems, while introducing minimal changes in the recommendations stack. Our models show significant improvements in offline metrics based on the normalized cross entropy loss compared to production point-wise models. Our approach also shows a substantial increase of 1.7% in topline engagements coupled with a 1.5% increase in daily active users in an A/B test with live traffic on Facebook Watch, which translates into an increase of millions in the number of daily active users for the product.

11. MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation, SIGIR2023

Kibum Kim, Dongmin Hyun, Sukwon Yun, Chanyoung Park

https://arxiv.org/abs/2304.08382

The long-tailed problem is a long-standing challenge in Sequential Recommender Systems (SRS) in which the problem exists in terms of both users and items. While many existing studies address the long-tailed problem in SRS, they only focus on either the user or item perspective. However, we discover that the long-tailed user and item problems exist at the same time, and considering only either one of them leads to sub-optimal performance of the other one. In this paper, we propose a novel framework for SRS, called Mutual Enhancement of Long-Tailed user and item (MELT), that jointly alleviates the long-tailed problem in the perspectives of both users and items. MELT consists of bilateral branches each of which is responsible for long-tailed users and items, respectively, and the branches are trained to mutually enhance each other, which is trained effectively by a curriculum learning-based training. MELT is model-agnostic in that it can be seamlessly integrated with existing SRS models. Extensive experiments on eight datasets demonstrate the benefit of alleviating the long-tailed problems in terms of both users and items even without sacrificing the performance of head users and items, which has not been achieved by existing methods. To the best of our knowledge, MELT is the first work that jointly alleviates the long-tailed user and item problems in SRS.

12. Attention Mixtures for Time-Aware Sequential Recommendation, SIGIR2023

Viet-Anh Tran, Guillaume Salha-Galvan, Bruno Sguerra, Romain Hennequin

https://arxiv.org/abs/2304.08158

Transformers emerged as powerful methods for sequential recommendation. However, existing architectures often overlook the complex dependencies between user preferences and the temporal context. In this short paper, we introduce MOJITO, an improved Transformer sequential recommender system that addresses this limitation. MOJITO leverages Gaussian mixtures of attention-based temporal context and item embedding representations for sequential modeling. Such an approach permits to accurately predict which items should be recommended next to users depending on past actions and the temporal context. We demonstrate the relevance of our approach, by empirically outperforming existing Transformers for sequential recommendation on several real-world datasets.

13. PerCoNet: News Recommendation with Explicit Persona and Contrastive Learning

Rui Liu, Bin Yin, Ziyi Cao, Qianchen Xia, Yong Chen, Dell Zhang

https://arxiv.org/abs/2304.07923

Personalized news recommender systems help users quickly find content of their interests from the sea of information. Today, the mainstream technology for personalized news recommendation is based on deep neural networks that can accurately model the semantic match between news items and users' interests. In this paper, we present PerCoNet, a novel deep learning approach to personalized news recommendation which features two new findings: (i) representing users through explicit persona analysis based on the prominent entities in their recent news reading history could be more effective than latent persona analysis employed by most existing work, with a side benefit of enhanced explainability; (ii) utilizing the title and abstract of each news item via cross-view contrastive learning would work better than just combining them directly. Extensive experiments on two real-world news datasets clearly show the superior performance of our proposed approach in comparison with current state-of-the-art techniques.

14. Causal Disentangled Variational Auto-Encoder for Preference Understanding in Recommendation

Siyu Wang, Xiaocong Chen, Quan Z. Sheng, Yihong Zhang, Lina Yao

https://arxiv.org/abs/2304.07922

Recommendation models are typically trained on observational user interaction data, but the interactions between latent factors in users' decision-making processes lead to complex and entangled data. Disentangling these latent factors to uncover their underlying representation can improve the robustness, interpretability, and controllability of recommendation models. This paper introduces the Causal Disentangled Variational Auto-Encoder (CaD-VAE), a novel approach for learning causal disentangled representations from interaction data in recommender systems. The CaD-VAE method considers the causal relationships between semantically related factors in real-world recommendation scenarios, rather than enforcing independence as in existing disentanglement methods. The approach utilizes structural causal models to generate causal representations that describe the causal relationship between latent factors. The results demonstrate that CaD-VAE outperforms existing methods, offering a promising solution for disentangling complex user behavior data in recommendation systems.

15. M2GNN: Metapath and Multi-interest Aggregated Graph Neural Network for Tag-based Cross-domain Recommendation, SIGIR2023

Zepeng Huai, Yuji Yang, Mengdi Zhang, Zhongyi Zhang, Yichun Li, Wei Wu

https://arxiv.org/abs/2304.07911

Cross-domain recommendation (CDR) is an effective way to alleviate the data sparsity problem. Content-based CDR is one of the most promising branches since most kinds of products can be described by a piece of text, especially when cold-start users or items have few interactions. However, two vital issues are still under-explored: (1) From the content modeling perspective, sufficient long-text descriptions are usually scarce in a real recommender system, more often the light-weight textual features, such as a few keywords or tags, are more accessible, which is improperly modeled by existing methods. (2) From the CDR perspective, not all inter-domain interests are helpful to infer intra-domain interests. Caused by domain-specific features, there are part of signals benefiting for recommendation in the source domain but harmful for that in the target domain. Therefore, how to distill useful interests is crucial. To tackle the above two problems, we propose a metapath and multi-interest aggregated graph neural network (M2GNN). Specifically, to model the tag-based contents, we construct a heterogeneous information network to hold the semantic relatedness between users, items, and tags in all domains. The metapath schema is predefined according to domain-specific knowledge, with one metapath for one domain. User representations are learned by GNN with a hierarchical aggregation framework, where the intra-metapath aggregation firstly filters out trivial tags and the inter-metapath aggregation further filters out useless interests. Offline experiments and online A/B tests demonstrate that M2GNN achieves significant improvements over the state-of-the-art methods and current industrial recommender system in Dianping, respectively. Further analysis shows that M2GNN offers an interpretable recommendation.

16. Meta-optimized Contrastive Learning for Sequential Recommendation

Xiuyuan Qin, Huanhuan Yuan, Pengpeng Zhao, Junhua Fang, Fuzhen Zhuang, Guanfeng Liu, Yanchi Liu, Victor Sheng

https://arxiv.org/abs/2304.07763

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or model augmentation for generating contrastive pairs to find a proper augmentation operation for different datasets, which makes the model hard to generalize. Additionally, since insufficient input data may lead the encoder to learn collapsed embeddings, these CL methods expect a relatively large number of training data (e.g., large batch size or memory bank) to contrast. However, not all contrastive pairs are always informative and discriminative enough for the training processing. Therefore, a more general CL-based recommendation model called Meta-optimized Contrastive Learning for sequential Recommendation (MCLRec) is proposed in this work. By applying both data augmentation and learnable model augmentation operations, this work innovates the standard CL framework by contrasting data and model augmented views for adaptively capturing the informative features hidden in stochastic data augmentation. Moreover, MCLRec utilizes a meta-learning manner to guide the updating of the model augmenters, which helps to improve the quality of contrastive pairs without enlarging the amount of input data. Finally, a contrastive regularization term is considered to encourage the augmentation model to generate more informative augmented views and avoid too similar contrastive pairs within the meta updating. The experimental results on commonly used datasets validate the effectiveness of MCLRec.

17. Hierarchical and Contrastive Representation Learning for Knowledge-aware Recommendation, ICME2023

Bingchao Wu, Yangyuxuan Kang, Daoguang Zan, Bei Guan, Yongji Wang

https://arxiv.org/abs/2304.07506

Incorporating knowledge graph into recommendation is an effective way to alleviate data sparsity. Most existing knowledge-aware methods usually perform recursive embedding propagation by enumerating graph neighbors. However, the number of nodes' neighbors grows exponentially as the hop number increases, forcing the nodes to be aware of vast neighbors under this recursive propagation for distilling the high-order semantic relatedness. This may induce more harmful noise than useful information into recommendation, leading the learned node representations to be indistinguishable from each other, that is, the well-known over-smoothing issue. To relieve this issue, we propose a Hierarchical and CONtrastive representation learning framework for knowledge-aware recommendation named HiCON. Specifically, for avoiding the exponential expansion of neighbors, we propose a hierarchical message aggregation mechanism to interact separately with low-order neighbors and meta-path-constrained high-order neighbors. Moreover, we also perform cross-order contrastive learning to enforce the representations to be more discriminative. Extensive experiments on three datasets show the remarkable superiority of HiCON over state-of-the-art approaches.

18. Intent-aware Ranking Ensemble for Personalized Recommendation, SIGIR2023

Jiayu Li, Peijie Sun, Zhefan Wang, Weizhi Ma, Yangkun Li, Min Zhang, Zhoutian Feng, Daiyue Xue

https://arxiv.org/abs/2304.07450

Ranking ensemble is a critical component in real recommender systems. When a user visits a platform, the system will prepare several item lists, each of which is generally from a single behavior objective recommendation model. As multiple behavior intents, e.g., both clicking and buying some specific item category, are commonly concurrent in a user visit, it is necessary to integrate multiple single-objective ranking lists into one. However, previous work on rank aggregation mainly focused on fusing homogeneous item lists with the same objective while ignoring ensemble of heterogeneous lists ranked with different objectives with various user intents.

In this paper, we treat a user's possible behaviors and the potential interacting item categories as the user's intent. And we aim to study how to fuse candidate item lists generated from different objectives aware of user intents. To address such a task, we propose an Intent-aware ranking Ensemble Learning~(IntEL) model to fuse multiple single-objective item lists with various user intents, in which item-level personalized weights are learned. Furthermore, we theoretically prove the effectiveness of IntEL with point-wise, pair-wise, and list-wise loss functions via error-ambiguity decomposition. Experiments on two large-scale real-world datasets also show significant improvements of IntEL on multiple behavior objectives simultaneously compared to previous ranking ensemble models.

19. HEAT: A Highly Efficient and Affordable Training System for Collaborative Filtering Based Recommendation on CPUs, ICS2023

Chengming Zhang, Shaden Smith, Baixi Sun, Jiannan Tian, Jonathan Soifer, Xiaodong Yu, Shuaiwen Leon Song, Yuxiong He, Dingwen Tao

https://arxiv.org/abs/2304.07334

Collaborative filtering (CF) has been proven to be one of the most effective techniques for recommendation. Among all CF approaches, SimpleX is the state-of-the-art method that adopts a novel loss function and a proper number of negative samples. However, there is no work that optimizes SimpleX on multi-core CPUs, leading to limited performance. To this end, we perform an in-depth profiling and analysis of existing SimpleX implementations and identify their performance bottlenecks including (1) irregular memory accesses, (2) unnecessary memory copies, and (3) redundant computations. To address these issues, we propose an efficient CF training system (called HEAT) that fully enables the multi-level caching and multi-threading capabilities of modern CPUs. Specifically, the optimization of HEAT is threefold: (1) It tiles the embedding matrix to increase data locality and reduce cache misses (thus reduce read latency); (2) It optimizes stochastic gradient descent (SGD) with sampling by parallelizing vector products instead of matrix-matrix multiplications, in particular the similarity computation therein, to avoid memory copies for matrix data preparation; and (3) It aggressively reuses intermediate results from the forward phase in the backward phase to alleviate redundant computation. Evaluation on five widely used datasets with both x86- and ARM-architecture processors shows that HEAT achieves up to 65.3X speedup over existing CPU solution and 4.8X speedup and 7.9X cost reduction in Cloud over existing GPU solution with NVIDIA V100 GPU.

20. Learning Graph ODE for Continuous-Time Sequential Recommendation

Yifang Qin, Wei Ju, Hongjun Wu, Xiao Luo, Ming Zhang

https://arxiv.org/abs/2304.07042

Sequential recommendation aims at understanding user preference by capturing successive behavior correlations, which are usually represented as the item purchasing sequences based on their past interactions. Existing efforts generally predict the next item via modeling the sequential patterns. Despite effectiveness, there exist two natural deficiencies: (i) user preference is dynamic in nature, and the evolution of collaborative signals is often ignored; and (ii) the observed interactions are often irregularly-sampled, while existing methods model item transitions assuming uniform intervals. Thus, how to effectively model and predict the underlying dynamics for user preference becomes a critical research problem. To tackle the above challenges, in this paper, we focus on continuous-time sequential recommendation and propose a principled graph ordinary differential equation framework named GDERec. Technically, GDERec is characterized by an autoregressive graph ordinary differential equation consisting of two components, which are parameterized by two tailored graph neural networks (GNNs) respectively to capture user preference from the perspective of hybrid dynamical systems. The two customized GNNs are trained alternately in an autoregressive manner to track the evolution of the underlying system from irregular observations, and thus learn effective representations of users and items beneficial to the sequential recommendation. Extensive experiments on five benchmark datasets demonstrate the superiority of our model over various state-of-the-art recommendation methods.

21. A Diffusion model for POI recommendation

Yifang Qin, Hongjun Wu, Wei Ju, Xiao Luo, Ming Zhang

https://arxiv.org/abs/2304.07041

Next Point-of-Interest (POI) recommendation is a critical task in location-based services that aim to provide personalized suggestions for the user's next destination. Previous works on POI recommendation have laid focused on modeling the user's spatial preference. However, existing works that leverage spatial information are only based on the aggregation of users' previous visited positions, which discourages the model from recommending POIs in novel areas. This trait of position-based methods will harm the model's performance in many situations. Additionally, incorporating sequential information into the user's spatial preference remains a challenge. In this paper, we propose Diff-POI: a Diffusion-based model that samples the user's spatial preference for the next POI recommendation. Inspired by the wide application of diffusion algorithm in sampling from distributions, Diff-POI encodes the user's visiting sequence and spatial character with two tailor-designed graph encoding modules, followed by a diffusion-based sampling strategy to explore the user's spatial visiting trends. We leverage the diffusion process and its reversed form to sample from the posterior distribution and optimized the corresponding score function. We design a joint training and inference framework to optimize and evaluate the proposed Diff-POI. Extensive experiments on four real-world POI recommendation datasets demonstrate the superiority of our Diff-POI over state-of-the-art baseline methods. Further ablation and parameter studies on Diff-POI reveal the functionality and effectiveness of the proposed diffusion-based sampling strategy for addressing the limitations of existing methods.

22. Is ChatGPT a Good Recommender? A Preliminary Study

Junling Liu, Chao Liu, Renjie Lv, Kang Zhou, Yan Zhang

https://arxiv.org/abs/2304.10149

Recommendation systems have witnessed significant advancements and have been widely used over the past decades. However, most traditional recommendation methods are task-specific and therefore lack efficient generalization ability. Recently, the emergence of ChatGPT has significantly advanced NLP tasks by enhancing the capabilities of conversational models. Nonetheless, the application of ChatGPT in the recommendation domain has not been thoroughly investigated. In this paper, we employ ChatGPT as a general-purpose recommendation model to explore its potential for transferring extensive linguistic and world knowledge acquired from large-scale corpora to recommendation scenarios. Specifically, we design a set of prompts and evaluate ChatGPT's performance on five recommendation scenarios. Unlike traditional recommendation methods, we do not fine-tune ChatGPT during the entire evaluation process, relying only on the prompts themselves to convert recommendation tasks into natural language tasks. Further, we explore the use of few-shot prompting to inject interaction information that contains user potential interest to help ChatGPT better understand user needs and interests. Comprehensive experimental results on Amazon Beauty dataset show that ChatGPT has achieved promising results in certain tasks and is capable of reaching the baseline level in others. We conduct human evaluations on two explainability-oriented tasks to more accurately evaluate the quality of contents generated by different models. And the human evaluations show ChatGPT can truly understand the provided information and generate clearer and more reasonable results. We hope that our study can inspire researchers to further explore the potential of language models like ChatGPT to improve recommendation performance and contribute to the advancement of the recommendation systems field.

23. Sheaf Neural Networks for Graph-based Recommender Systems

Antonio Purificato, Giulia Cassarà, Pietro Liò, Fabrizio Silvestri

https://arxiv.org/abs/2304.09097

Recent progress in Graph Neural Networks has resulted in wide adoption by many applications, including recommendation systems. The reason for Graph Neural Networks' superiority over other approaches is that many problems in recommendation systems can be naturally modeled as graphs, where nodes can be either users or items and edges represent preference relationships. In current Graph Neural Network approaches, nodes are represented with a static vector learned at training time. This static vector might only be suitable to capture some of the nuances of users or items they define. To overcome this limitation, we propose using a recently proposed model inspired by category theory: Sheaf Neural Networks. Sheaf Neural Networks, and its connected Laplacian, can address the previous problem by associating every node (and edge) with a vector space instead than a single vector. The vector space representation is richer and allows picking the proper representation at inference time. This approach can be generalized for different related tasks on graphs and achieves state-of-the-art performance in terms of F1-Score@N in collaborative filtering and Hits@20 in link prediction. For collaborative filtering, the approach is evaluated on the MovieLens 100K with a 5.1% improvement, on MovieLens 1M with a 5.4% improvement and on Book-Crossing with a 2.8% improvement, while for link prediction on the ogbl-ddi dataset with a 1.6% refinement with respect to the respective baselines.

24. CAM2: Conformity-Aware Multi-Task Ranking Model for Large-Scale Recommender Systems, WWW2023

Ameya Raul, Amey Porobo Dharwadker, Brad Schumitsch

https://arxiv.org/abs/2304.08562

Learning large-scale industrial recommender system models by fitting them to historical user interaction data makes them vulnerable to conformity bias. This may be due to a number of factors, including the fact that user interests may be difficult to determine and that many items are often interacted with based on ecosystem factors other than their relevance to the individual user. In this work, we introduce CAM2, a conformity-aware multi-task ranking model to serve relevant items to users on one of the largest industrial recommendation platforms. CAM2 addresses these challenges systematically by leveraging causal modeling to disentangle users' conformity to popular items from their true interests. This framework is generalizable and can be scaled to support multiple representations of conformity and user relevance in any large-scale recommender system. We provide deeper practical insights and demonstrate the effectiveness of the proposed model through improvements in offline evaluation metrics compared to our production multi-task ranking model. We also show through online experiments that the CAM2 model results in a significant 0.50% increase in aggregated user engagement, coupled with a 0.21% increase in daily active users on Facebook Watch, a popular video discovery and sharing platform serving billions of users.

25. Causal Decision Transformer for Recommender Systems via Offline Reinforcement Learning

Siyu Wang, Xiaocong Chen, Dietmar Jannach, Lina Yao

https://arxiv.org/abs/2304.07920

Reinforcement learning-based recommender systems have recently gained popularity. However, the design of the reward function, on which the agent relies to optimize its recommendation policy, is often not straightforward. Exploring the causality underlying users' behavior can take the place of the reward function in guiding the agent to capture the dynamic interests of users. Moreover, due to the typical limitations of simulation environments (e.g., data inefficiency), most of the work cannot be broadly applied in large-scale situations. Although some works attempt to convert the offline dataset into a simulator, data inefficiency makes the learning process even slower. Because of the nature of reinforcement learning (i.e., learning by interaction), it cannot collect enough data to train during a single interaction. Furthermore, traditional reinforcement learning algorithms do not have a solid capability like supervised learning methods to learn from offline datasets directly. In this paper, we propose a new model named the causal decision transformer for recommender systems (CDT4Rec). CDT4Rec is an offline reinforcement learning system that can learn from a dataset rather than from online interaction. Moreover, CDT4Rec employs the transformer architecture, which is capable of processing large offline datasets and capturing both short-term and long-term dependencies within the data to estimate the causal relationship between action, state, and reward. To demonstrate the feasibility and superiority of our model, we have conducted experiments on six real-world offline datasets and one online simulator.

26. PBNR: Prompt-based News Recommender System

Xinyi Li, Yongfeng Zhang, Edward C. Malthouse

https://arxiv.org/abs/2304.07862

Online news platforms often use personalized news recommendation methods to help users discover articles that align with their interests. These methods typically predict a matching score between a user and a candidate article to reflect the user's preference for the article. Some previous works have used language model techniques, such as the attention mechanism, to capture users' interests based on their past behaviors, and to understand the content of articles. However, these existing model architectures require adjustments if additional information is taken into account. Pre-trained large language models, which can better capture word relationships and comprehend contexts, have seen a significant development in recent years, and these pre-trained models have the advantages of transfer learning and reducing the training time for downstream tasks. Meanwhile, prompt learning is a newly developed technique that leverages pre-trained language models by building task-specific guidance for output generations. To leverage textual information in news articles, this paper introduces the pre-trained large language model and prompt-learning to the community of news recommendation. The proposed model "prompt-based news recommendation" (PBNR) treats the personalized news recommendation as a text-to-text language task and designs personalized prompts to adapt to the pre-trained language model -- text-to-text transfer transformer (T5). Experimental studies using the Microsoft News dataset show that PBNR is capable of making accurate recommendations by taking into account various lengths of past behaviors of different users. PBNR can also easily adapt to new information without changing the model architecture and the training objective. Additionally, PBNR can make recommendations based on users' specific requirements, allowing human-computer interaction in the news recommendation field.

27. More Is Less: When Do Recommenders Underperform for Data-rich Users?

Yueqing Xuan, Kacper Sokol, Jeffrey Chan, Mark Sanderson

https://arxiv.org/abs/2304.07487

Users of recommender systems tend to differ in their level of interaction with these algorithms, which may affect the quality of recommendations they receive and lead to undesirable performance disparity. In this paper we investigate under what conditions the performance for data-rich and data-poor users diverges for a collection of popular evaluation metrics applied to ten benchmark datasets. We find that Precision is consistently higher for data-rich users across all the datasets; Mean Average Precision is comparable across user groups but its variance is large; Recall yields a counter-intuitive result where the algorithm performs better for data-poor than for data-rich users, which bias is further exacerbated when negative item sampling is employed during evaluation. The final observation suggests that as users interact more with recommender systems, the quality of recommendations they receive degrades (when measured by Recall). Our insights clearly show the importance of an evaluation protocol and its influence on the reported results when studying recommender systems.

28. FairRec: Fairness Testing for Deep Recommender Systems

Huizhong Guo, Jinfeng Li, Jingyi Wang, Xiangyu Liu, Dongxia Wang, Zehong Hu, Rong Zhang, Hui Xue

https://arxiv.org/abs/2304.07030

Deep learning-based recommender systems (DRSs) are increasingly and widely deployed in the industry, which brings significant convenience to people's daily life in different ways. However, recommender systems are also shown to suffer from multiple issues,e.g., the echo chamber and the Matthew effect, of which the notation of "fairness" plays a core role.While many fairness notations and corresponding fairness testing approaches have been developed for traditional deep classification models, they are essentially hardly applicable to DRSs. One major difficulty is that there still lacks a systematic understanding and mapping between the existing fairness notations and the diverse testing requirements for deep recommender systems, not to mention further testing or debugging activities. To address the gap, we propose FairRec, a unified framework that supports fairness testing of DRSs from multiple customized perspectives, e.g., model utility, item diversity, item popularity, etc. We also propose a novel, efficient search-based testing approach to tackle the new challenge, i.e., double-ended discrete particle swarm optimization (DPSO) algorithm, to effectively search for hidden fairness issues in the form of certain disadvantaged groups from a vast number of candidate groups. Given the testing report, by adopting a simple re-ranking mitigation strategy on these identified disadvantaged groups, we show that the fairness of DRSs can be significantly improved. We conducted extensive experiments on multiple industry-level DRSs adopted by leading companies. The results confirm that FairRec is effective and efficient in identifying the deeply hidden fairness issues, e.g., achieving 95% testing accuracy with half to 1/8 time.

29. PIE: Personalized Interest Exploration for Large-Scale Recommender Systems, WWW2023

Khushhall Chandra Mahajan, Amey Porobo Dharwadker, Romil Shah, Simeng Qu, Gaurav Bang, Brad Schumitsch

https://arxiv.org/abs/2304.06844

Recommender systems are increasingly successful in recommending personalized content to users. However, these systems often capitalize on popular content. There is also a continuous evolution of user interests that need to be captured, but there is no direct way to systematically explore users' interests. This also tends to affect the overall quality of the recommendation pipeline as training data is generated from the candidates presented to the user. In this paper, we present a framework for exploration in large-scale recommender systems to address these challenges. It consists of three parts, first the user-creator exploration which focuses on identifying the best creators that users are interested in, second the online exploration framework and third a feed composition mechanism that balances explore and exploit to ensure optimal prevalence of exploratory videos. Our methodology can be easily integrated into an existing large-scale recommender system with minimal modifications. We also analyze the value of exploration by defining relevant metrics around user-creator connections and understanding how this helps the overall recommendation pipeline with strong online gains in creator and ecosystem value. In contrast to the regression on user engagement metrics generally seen while exploring, our method is able to achieve significant improvements of 3.50% in strong creator connections and 0.85% increase in novel creator connections. Moreover, our work has been deployed in production on Facebook Watch, a popular video discovery and sharing platform serving billions of users.

30. Always Strengthen Your Strengths: A Drift-Aware Incremental Learning Framework for CTR Prediction, SIGIR2023

Congcong Liu, Fei Teng, Xiwei Zhao, Zhangang Lin, Jinghe Hu, Jingping Shao

https://arxiv.org/abs/2304.09062

Click-through rate (CTR) prediction is of great importance in recommendation systems and online advertising platforms. When served in industrial scenarios, the user-generated data observed by the CTR model typically arrives as a stream. Streaming data has the characteristic that the underlying distribution drifts over time and may recur. This can lead to catastrophic forgetting if the model simply adapts to new data distribution all the time. Also, it's inefficient to relearn distribution that has been occurred. Due to memory constraints and diversity of data distributions in large-scale industrial applications, conventional strategies for catastrophic forgetting such as replay, parameter isolation, and knowledge distillation are difficult to be deployed. In this work, we design a novel drift-aware incremental learning framework based on ensemble learning to address catastrophic forgetting in CTR prediction. With explicit error-based drift detection on streaming data, the framework further strengthens well-adapted ensembles and freezes ensembles that do not match the input distribution avoiding catastrophic interference. Both evaluations on offline experiments and A/B test shows that our method outperforms all baselines considered.