论文周报 | 推荐系统领域最新研究进展，含多篇最新发布的SIGIR等顶会论文

本文精选了上周（0410-0416）最新发布的22篇推荐系统相关论文，其中包含多篇基于扩散模型的序列推荐、基于提示学习的序列推荐、跨域推荐、图推荐等文章。

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. GNNUERS: Fairness Explanation in GNNs for Recommendation via Counterfactual Reasoning

2. Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation

3. Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Training

4. Prompt Learning for News Recommendation, SIGIR 2023

5. Triple Sequence Learning for Cross-domain Recommendation

6. Neural Multi-network Diffusion towards Social Recommendation

7. AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations

8. Sequential Recommendation with Diffusion Models

9. FAN: Fatigue-Aware Network for Click-Through Rate Prediction in E-commerce Recommendation

10. COOOL: A Learning-To-Rank Approach for SQL Hint Recommendations

11. Editable User Profiles for Controllable Text Recommendation, SIGIR 2023

12. Automated Prompting for Non-overlapping Cross-domain Sequential Recommendation

13. Timestamps as Prompts for Geography-Aware Location Recommendation

14. Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation

15. Contrastive Cross-Domain Sequential Recommendation, CIKM 2022

16. GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation

17. Generative Recommendation: Towards Next-generation Recommender Paradigm

18. Graph Collaborative Signals Denoising and Augmentation for Recommendation, SIGIR 2023

19. Unbiased Pairwise Learning from Implicit Feedback for Recommender Systems without Biased Variance Control, SIGIR 2023

20. Diffusion Recommender Model, SIGIR 2023

21. A Recommender System Approach for Very Large-scale Multi-objective Optimization

22. Continuous Input Embedding Size Search For Recommender Systems, SIGIR 2023

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/0410-0416/

1. GNNUERS: Fairness Explanation in GNNs for Recommendation via Counterfactual Reasoning

Giacomo Medda, Francesco Fabbri, Mirko Marras, Ludovico Boratto, Mihnea Tufis, Gianni Fenu

https://arxiv.org/abs/2304.06182

In recent years, personalization research has been delving into issues of explainability and fairness. While some techniques have emerged to provide post-hoc and self-explanatory individual recommendations, there is still a lack of methods aimed at uncovering unfairness in recommendation systems beyond identifying biased user and item features. This paper proposes a new algorithm, GNNUERS, which uses counterfactuals to pinpoint user unfairness explanations in terms of user-item interactions within a bi-partite graph. By perturbing the graph topology, GNNUERS reduces differences in utility between protected and unprotected demographic groups. The paper evaluates the approach using four real-world graphs from different domains and demonstrates its ability to systematically explain user unfairness in three state-of-the-art GNN-based recommendation models. This perturbed network analysis reveals insightful patterns that confirm the nature of the unfairness underlying the explanations. The source code and preprocessed datasets are available at: https://github.com/jackmedda/RS-BGExplainer

2. Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation

Qiang Liu, Zhaocheng Liu, Zhenxi Zhu, Shu Wu, Liang Wang

https://arxiv.org/abs/2304.05615

Recently, multi-interest models, which extract interests of a user as multiple representation vectors, have shown promising performances for sequential recommendation. However, none of existing multi-interest recommendation models consider the Out-Of-Distribution (OOD) generalization problem, in which interest distribution may change. Considering multiple interests of a user are usually highly correlated, the model has chance to learn spurious correlations between noisy interests and target items. Once the data distribution changes, the correlations among interests may also change, and the spurious correlations will mislead the model to make wrong predictions. To tackle with above OOD generalization problem, we propose a novel multi-interest network, named DEep Stable Multi-Interest Learning (DESMIL), which attempts to de-correlate the extracted interests in the model, and thus spurious correlations can be eliminated. DESMIL applies an attentive module to extract multiple interests, and then selects the most important one for making final predictions. Meanwhile, DESMIL incorporates a weighted correlation estimation loss based on Hilbert-Schmidt Independence Criterion (HSIC), with which training samples are weighted, to minimize the correlations among extracted interests. Extensive experiments have been conducted under both OOD and random settings, and up to 36.8% and 21.7% relative improvements are achieved respectively.

3. Towards More Robust and Accurate Sequential Recommendation with Cascade-guided Adversarial Training

Juntao Tan, Shelby Heinecke, Zhiwei Liu, Yongjun Chen, Yongfeng Zhang, Huan Wang

https://arxiv.org/abs/2304.05492

Sequential recommendation models, models that learn from chronological user-item interactions, outperform traditional recommendation models in many settings. Despite the success of sequential recommendation models, their robustness has recently come into question. Two properties unique to the nature of sequential recommendation models may impair their robustness - the cascade effects induced during training and the model's tendency to rely too heavily on temporal information. To address these vulnerabilities, we propose Cascade-guided Adversarial training, a new adversarial training procedure that is specifically designed for sequential recommendation models. Our approach harnesses the intrinsic cascade effects present in sequential modeling to produce strategic adversarial perturbations to item embeddings during training. Experiments on training state-of-the-art sequential models on four public datasets from different domains show that our training approach produces superior model ranking accuracy and superior model robustness to real item replacement perturbations when compared to both standard model training and generic adversarial training.

4. Prompt Learning for News Recommendation, SIGIR 2023

Zizhuo Zhang, Bang Wang

https://arxiv.org/abs/2304.05263

Some recent news recommendation (NR) methods introduce a Pre-trained Language Model (PLM) to encode news representation by following the vanilla pre-train and fine-tune paradigm with carefully-designed recommendation-specific neural networks and objective functions. Due to the inconsistent task objective with that of PLM, we argue that their modeling paradigm has not well exploited the abundant semantic information and linguistic knowledge embedded in the pre-training process. Recently, the pre-train, prompt, and predict paradigm, called prompt learning, has achieved many successes in natural language processing domain. In this paper, we make the first trial of this new paradigm to develop a Prompt Learning for News Recommendation (Prompt4NR) framework, which transforms the task of predicting whether a user would click a candidate news as a cloze-style mask-prediction task. Specifically, we design a series of prompt templates, including discrete, continuous, and hybrid templates, and construct their corresponding answer spaces to examine the proposed Prompt4NR framework. Furthermore, we use the prompt ensembling to integrate predictions from multiple prompt templates. Extensive experiments on the MIND dataset validate the effectiveness of our Prompt4NR with a set of new benchmark results.

5. Triple Sequence Learning for Cross-domain Recommendation

Haokai Ma, Ruobing Xie, Lei Meng, Xin Chen, Xu Zhang, Leyu Lin, Jie Zhou

https://arxiv.org/abs/2304.05027

Cross-domain recommendation (CDR) aims to leverage the users' behaviors in both source and target domains to improve the target domain's performance. Conventional CDR methods typically explore the dual relations between the source and target domains' behavior sequences. However, they ignore modeling the third sequence of mixed behaviors that naturally reflects the user's global preference. To address this issue, we present a novel and model-agnostic Triple sequence learning for cross-domain recommendation (Tri-CDR) framework to jointly model the source, target, and mixed behavior sequences in CDR. Specifically, Tri-CDR independently models the hidden user representations for the source, target, and mixed behavior sequences, and proposes a triple cross-domain attention (TCA) to emphasize the informative knowledge related to both user's target-domain preference and global interests in three sequences. To comprehensively learn the triple correlations, we design a novel triple contrastive learning (TCL) that jointly considers coarse-grained similarities and fine-grained distinctions among three sequences, ensuring the alignment while preserving the information diversity in multi-domain. We conduct extensive experiments and analyses on two real-world datasets with four domains. The significant improvements of Tri-CDR with different sequential encoders on all datasets verify the effectiveness and universality. The source code will be released in the future.

6. Neural Multi-network Diffusion towards Social Recommendation

Boxin Du, Lihui Liu, Jiejun Xu, Fei Wang, Hanghang Tong

https://arxiv.org/abs/2304.04994

Graph Neural Networks (GNNs) have been widely applied on a variety of real-world applications, such as social recommendation. However, existing GNN-based models on social recommendation suffer from serious problems of generalization and oversmoothness, because of the underexplored negative sampling method and the direct implanting of the off-the-shelf GNN models. In this paper, we propose a succinct multi-network GNN-based neural model (NeMo) for social recommendation. Compared with the existing methods, the proposed model explores a generative negative sampling strategy, and leverages both the positive and negative user-item interactions for users' interest propagation. The experiments show that NeMo outperforms the state-of-the-art baselines on various real-world benchmark datasets (e.g., by up to 38.8% in terms of NDCG@15).

7. AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations

Danwei Li, Zhengyu Zhang, Siyang Yuan, Mingze Gao, Weilin Zhang, Chaofei Yang, Xi Liu, Jiyan Yang

https://arxiv.org/abs/2304.04959

Multi-task learning (MTL) aims at enhancing the performance and efficiency of machine learning models by training them on multiple tasks simultaneously. However, MTL research faces two challenges: 1) modeling the relationships between tasks to effectively share knowledge between them, and 2) jointly learning task-specific and shared knowledge. In this paper, we present a novel model Adaptive Task-to-Task Fusion Network (AdaTT) to address both challenges. AdaTT is a deep fusion network built with task specific and optional shared fusion units at multiple levels. By leveraging a residual mechanism and gating mechanism for task-to-task fusion, these units adaptively learn shared knowledge and task specific knowledge. To evaluate the performance of AdaTT, we conduct experiments on a public benchmark and an industrial recommendation dataset using various task groups. Results demonstrate AdaTT can significantly outperform existing state-of-the-art baselines.

8. Sequential Recommendation with Diffusion Models

Hanwen Du, Huanhuan Yuan, Zhen Huang, Pengpeng Zhao, Xiaofang Zhou

https://arxiv.org/abs/2304.04541

Generative models, such as Variational Auto-Encoder (VAE) and Generative Adversarial Network (GAN), have been successfully applied in sequential recommendation. These methods require sampling from probability distributions and adopt auxiliary loss functions to optimize the model, which can capture the uncertainty of user behaviors and alleviate exposure bias. However, existing generative models still suffer from the posterior collapse problem or the model collapse problem, thus limiting their applications in sequential recommendation. To tackle the challenges mentioned above, we leverage a new paradigm of the generative models, i.e., diffusion models, and present sequential recommendation with diffusion models (DiffRec), which can avoid the issues of VAE- and GAN-based models and show better performance. While diffusion models are originally proposed to process continuous image data, we design an additional transition in the forward process together with a transition in the reverse process to enable the processing of the discrete recommendation data. We also design a different noising strategy that only noises the target item instead of the whole sequence, which is more suitable for sequential recommendation. Based on the modified diffusion process, we derive the objective function of our framework using a simplification technique and design a denoise sequential recommender to fulfill the objective function. As the lengthened diffusion steps substantially increase the time complexity, we propose an efficient training strategy and an efficient inference strategy to reduce training and inference cost and improve recommendation diversity. Extensive experiment results on three public benchmark datasets verify the effectiveness of our approach and show that DiffRec outperforms the state-of-the-art sequential recommendation models.

9. FAN: Fatigue-Aware Network for Click-Through Rate Prediction in E-commerce Recommendation

Ming Li, Naiyin Liu, Xiaofeng Pan, Yang Huang, Ningning Li, Yingmin Su, Chengjun Mao, Bo Cao

https://arxiv.org/abs/2304.04529

Since clicks usually contain heavy noise, increasing research efforts have been devoted to modeling implicit negative user behaviors (i.e., non-clicks). However, they either rely on explicit negative user behaviors (e.g., dislikes) or simply treat non-clicks as negative feedback, failing to learn negative user interests comprehensively. In such situations, users may experience fatigue because of seeing too many similar recommendations. In this paper, we propose Fatigue-Aware Network (FAN), a novel CTR model that directly perceives user fatigue from non-clicks. Specifically, we first apply Fourier Transformation to the time series generated from non-clicks, obtaining its frequency spectrum which contains comprehensive information about user fatigue. Then the frequency spectrum is modulated by category information of the target item to model the bias that both the upper bound of fatigue and users' patience is different for different categories. Moreover, a gating network is adopted to model the confidence of user fatigue and an auxiliary task is designed to guide the learning of user fatigue, so we can obtain a well-learned fatigue representation and combine it with user interests for the final CTR prediction. Experimental results on real-world datasets validate the superiority of FAN and online A/B tests also show FAN outperforms representative CTR models significantly.

10. COOOL: A Learning-To-Rank Approach for SQL Hint Recommendations

Xianghong Xu, Zhibing Zhao, Tieying Zhang, Rong Kang, Luming Sun, Jianjun Chen,

https://arxiv.org/abs/2304.04407

Query optimization is a pivotal part of every database management system (DBMS) since it determines the efficiency of query execution. Numerous works have introduced Machine Learning (ML) techniques to cost modeling, cardinality estimation, and end-to-end learned optimizer, but few of them are proven practical due to long training time, lack of interpretability, and integration cost. A recent study provides a practical method to optimize queries by recommending per-query hints but it suffers from two inherited problems. First, it follows the regression framework to predict the absolute latency of each query plan, which is very challenging because the latencies of query plans for a certain query may span multiple orders of magnitude. Second, it requires training a model for each dataset, which restricts the application of the trained models in practice. In this paper, we propose COOOL to predict Cost Orders of query plans to cOOperate with DBMS by Learning-To-Rank. Instead of estimating absolute costs, COOOL uses ranking-based approaches to compute relative ranking scores of the costs of query plans. We show that COOOL is theoretically valid to distinguish query plans with different latencies. We implement COOOL on PostgreSQL, and extensive experiments on join-order-benchmark and TPC-H data demonstrate that COOOL outperforms PostgreSQL and state-of-the-art methods on single-dataset tasks as well as a unified model for multiple-dataset tasks. Our experiments also shed some light on why COOOL outperforms regression approaches from the representation learning perspective, which may guide future research.

11. Editable User Profiles for Controllable Text Recommendation, SIGIR 2023

Sheshera Mysore, Mahmood Jasim, Andrew McCallum, Hamed Zamani

https://arxiv.org/abs/2304.04250

Methods for making high-quality recommendations often rely on learning latent representations from interaction data. These methods, while performant, do not provide ready mechanisms for users to control the recommendation they receive. Our work tackles this problem by proposing LACE, a novel concept value bottleneck model for controllable text recommendations. LACE represents each user with a succinct set of human-readable concepts through retrieval given user-interacted documents and learns personalized representations of the concepts based on user documents. This concept based user profile is then leveraged to make recommendations. The design of our model affords control over the recommendations through a number of intuitive interactions with a transparent user profile. We first establish the quality of recommendations obtained from LACE in an offline evaluation on three recommendation tasks spanning six datasets in warm-start, cold-start, and zero-shot setups. Next, we validate the controllability of LACE under simulated user interactions. Finally, we implement LACE in an interactive controllable recommender system and conduct a user study to demonstrate that users are able to improve the quality of recommendations they receive through interactions with an editable user profile.

12. Automated Prompting for Non-overlapping Cross-domain Sequential Recommendation

Lei Guo, Chunxiao Wang, Xinhua Wang, Lei Zhu, Hongzhi Yin

https://arxiv.org/abs/2304.04218

Cross-domain Recommendation (CR) has been extensively studied in recent years to alleviate the data sparsity issue in recommender systems by utilizing different domain information. In this work, we focus on the more general Non-overlapping Cross-domain Sequential Recommendation (NCSR) scenario. NCSR is challenging because there are no overlapped entities (e.g., users and items) between domains, and there is only users' implicit feedback and no content information. Previous CR methods cannot solve NCSR well, since (1) they either need extra content to align domains or need explicit domain alignment constraints to reduce the domain discrepancy from domain-invariant features, (2) they pay more attention to users' explicit feedback (i.e., users' rating data) and cannot well capture their sequential interaction patterns, (3) they usually do a single-target cross-domain recommendation task and seldom investigate the dual-target ones. Considering the above challenges, we propose Prompt Learning-based Cross-domain Recommender (PLCR), an automated prompting-based recommendation framework for the NCSR task. Specifically, to address the challenge (1), PLCR resorts to learning domain-invariant and domain-specific representations via its prompt learning component, where the domain alignment constraint is discarded. For challenges (2) and (3), PLCR introduces a pre-trained sequence encoder to learn users' sequential interaction patterns, and conducts a dual-learning target with a separation constraint to enhance recommendations in both domains. Our empirical study on two sub-collections of Amazon demonstrates the advance of PLCR compared with some related SOTA methods.

13. Timestamps as Prompts for Geography-Aware Location Recommendation

Yan Luo, Haoyi Duan, Ye Liu, Fu-lai Chung

https://arxiv.org/abs/2304.04151

Location recommendation plays a vital role in improving users' travel experience. The timestamp of the POI to be predicted is of great significance, since a user will go to different places at different times. However, most existing methods either do not use this kind of temporal information, or just implicitly fuse it with other contextual information. In this paper, we revisit the problem of location recommendation and point out that explicitly modeling temporal information is a great help when the model needs to predict not only the next location but also further locations. In addition, state-of-the-art methods do not make effective use of geographic information and suffer from the hard boundary problem when encoding geographic information by gridding. To this end, a Temporal Prompt-based and Geography-aware (TPG) framework is proposed. The temporal prompt is firstly designed to incorporate temporal information of any further check-in. A shifted window mechanism is then devised to augment geographic data for addressing the hard boundary problem. Via extensive comparisons with existing methods and ablation studies on five real-world datasets, we demonstrate the effectiveness and superiority of the proposed method under various settings. Most importantly, our proposed model has the superior ability of interval prediction. In particular, the model can predict the location that a user wants to go to at a certain time while the most recent check-in behavioral data is masked, or it can predict specific future check-in (not just the next one) at a given timestamp.

14. Model-Agnostic Decentralized Collaborative Learning for On-Device POI Recommendation

Jing Long, Tong Chen, Nguyen Quoc Viet Hung, Guandong Xu, Kai Zheng, Hongzhi Yin

https://arxiv.org/abs/2304.03947

As an indispensable personalized service in Location-based Social Networks (LBSNs), the next Point-of-Interest (POI) recommendation aims to help people discover attractive and interesting places. Currently, most POI recommenders are based on the conventional centralized paradigm that heavily relies on the cloud to train the recommendation models with large volumes of collected users' sensitive check-in data. Although a few recent works have explored on-device frameworks for resilient and privacy-preserving POI recommendations, they invariably hold the assumption of model homogeneity for parameters/gradients aggregation and collaboration. However, users' mobile devices in the real world have various hardware configurations (e.g., compute resources), leading to heterogeneous on-device models with different architectures and sizes. In light of this, We propose a novel on-device POI recommendation framework, namely Model-Agnostic Collaborative learning for on-device POI recommendation (MAC), allowing users to customize their own model structures (e.g., dimension & number of hidden layers). To counteract the sparsity of on-device user data, we propose to pre-select neighbors for collaboration based on physical distances, category-level preferences, and social networks. To assimilate knowledge from the above-selected neighbors in an efficient and secure way, we adopt the knowledge distillation framework with mutual information maximization. Instead of sharing sensitive models/gradients, clients in MAC only share their soft decisions on a preloaded reference dataset. To filter out low-quality neighbors, we propose two sampling strategies, performance-triggered sampling and similarity-based sampling, to speed up the training process and obtain optimal recommenders. In addition, we design two novel approaches to generate more effective reference datasets while protecting users' privacy.

15. Contrastive Cross-Domain Sequential Recommendation, CIKM 2022

Jiangxia Cao, Xin Cong, Jiawei Sheng, Tingwen Liu, Bin Wang

https://arxiv.org/abs/2304.03891

Cross-Domain Sequential Recommendation (CDSR) aims to predict future interactions based on user's historical sequential interactions from multiple domains. Generally, a key challenge of CDSR is how to mine precise cross-domain user preference based on the intra-sequence and inter-sequence item interactions. Existing works first learn single-domain user preference only with intra-sequence item interactions, and then build a transferring module to obtain cross-domain user preference. However, such a pipeline and implicit solution can be severely limited by the bottleneck of the designed transferring module, and ignores to consider inter-sequence item relationships. In this paper, we propose C^2DSR to tackle the above problems to capture precise user preferences. The main idea is to simultaneously leverage the intra- and inter- sequence item relationships, and jointly learn the single- and cross- domain user preferences. Specifically, we first utilize a graph neural network to mine inter-sequence item collaborative relationship, and then exploit sequential attentive encoder to capture intra-sequence item sequential relationship. Based on them, we devise two different sequential training objectives to obtain user single-domain and cross-domain representations. Furthermore, we present a novel contrastive cross-domain infomax objective to enhance the correlation between single- and cross- domain user representations by maximizing their mutual information. To validate the effectiveness of C^2DSR, we first re-split four e-comerce datasets, and then conduct extensive experiments to demonstrate the effectiveness of our approach C^2DSR.

16. GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation

Jinming Li, Wentao Zhang, Tian Wang, Guanglei Xiong, Alan Lu, Gerard Medioni

https://arxiv.org/abs/2304.03879

Recent advancements in Natural Language Processing (NLP) have led to the development of NLP-based recommender systems that have shown superior performance. However, current models commonly treat items as mere IDs and adopt discriminative modeling, resulting in limitations of (1) fully leveraging the content information of items and the language modeling capabilities of NLP models; (2) interpreting user interests to improve relevance and diversity; and (3) adapting practical circumstances such as growing item inventories. To address these limitations, we present GPT4Rec, a novel and flexible generative framework inspired by search engines. It first generates hypothetical "search queries" given item titles in a user's history, and then retrieves items for recommendation by searching these queries. The framework overcomes previous limitations by learning both user and item embeddings in the language space. To well-capture user interests with different aspects and granularity for improving relevance and diversity, we propose a multi-query generation technique with beam search. The generated queries naturally serve as interpretable representations of user interests and can be searched to recommend cold-start items. With GPT-2 language model and BM25 search engine, our framework outperforms state-of-the-art methods by and in Recall@K on two public datasets. Experiments further revealed that multi-query generation with beam search improves both the diversity of retrieved items and the coverage of a user's multi-interests. The adaptiveness and interpretability of generated queries are discussed with qualitative case studies.

17. Generative Recommendation: Towards Next-generation Recommender Paradigm

Wenjie Wang, Xinyu Lin, Fuli Feng, Xiangnan He, Tat-Seng Chua

https://arxiv.org/abs/2304.03516

Recommender systems typically retrieve items from an item corpus for personalized recommendations. However, such a retrieval-based recommender paradigm faces two limitations: 1) the human-generated items in the corpus might fail to satisfy the users' diverse information needs, and 2) users usually adjust the recommendations via passive and inefficient feedback such as clicks. Nowadays, AI-Generated Content (AIGC) has revealed significant success across various domains, offering the potential to overcome these limitations: 1) generative AI can produce personalized items to meet users' specific information needs, and 2) the newly emerged ChatGPT significantly facilitates users to express information needs more precisely via natural language instructions. In this light, the boom of AIGC points the way towards the next-generation recommender paradigm with two new objectives: 1) generating personalized content through generative AI, and 2) integrating user instructions to guide content generation.

To this end, we propose a novel Generative Recommender paradigm named GeneRec, which adopts an AI generator to personalize content generation and leverages user instructions to acquire users' information needs. Specifically, we pre-process users' instructions and traditional feedback (e.g., clicks) via an instructor to output the generation guidance. Given the guidance, we instantiate the AI generator through an AI editor and an AI creator to repurpose existing items and create new items, respectively. Eventually, GeneRec can perform content retrieval, repurposing, and creation to meet users' information needs. Besides, to ensure the trustworthiness of the generated items, we emphasize various fidelity checks such as authenticity and legality checks. Lastly, we study the feasibility of implementing the AI editor and AI creator on micro-video generation, showing promising results.

中文解读：生成式推荐: 迈向下一代推荐系统新范式

18. Graph Collaborative Signals Denoising and Augmentation for Recommendation, SIGIR 2023

Ziwei Fan, Ke Xu, Zhang Dong, Hao Peng, Jiawei Zhang, Philip S. Yu

https://arxiv.org/abs/2304.03344

Graph collaborative filtering (GCF) is a popular technique for capturing high-order collaborative signals in recommendation systems. However, GCF's bipartite adjacency matrix, which defines the neighbors being aggregated based on user-item interactions, can be noisy for users/items with abundant interactions and insufficient for users/items with scarce interactions. Additionally, the adjacency matrix ignores user-user and item-item correlations, which can limit the scope of beneficial neighbors being aggregated.

In this work, we propose a new graph adjacency matrix that incorporates user-user and item-item correlations, as well as a properly designed user-item interaction matrix that balances the number of interactions across all users. To achieve this, we pre-train a graph-based recommendation method to obtain users/items embeddings, and then enhance the user-item interaction matrix via top-K sampling. We also augment the symmetric user-user and item-item correlation components to the adjacency matrix. Our experiments demonstrate that the enhanced user-item interaction matrix with improved neighbors and lower density leads to significant benefits in graph-based recommendation. Moreover, we show that the inclusion of user-user and item-item correlations can improve recommendations for users with both abundant and insufficient interactions. The code is in https://github.com/zfan20/GraphDA.

19. Unbiased Pairwise Learning from Implicit Feedback for Recommender Systems without Biased Variance Control, SIGIR 2023

Yi Ren, Hongyan Tang, Jiangpeng Rong, Siwen Zhu

https://arxiv.org/abs/2304.05066

Generally speaking, the model training for recommender systems can be based on two types of data, namely explicit feedback and implicit feedback. Moreover, because of its general availability, we see wide adoption of implicit feedback data, such as click signal. There are mainly two challenges for the application of implicit feedback. First, implicit data just includes positive feedback. Therefore, we are not sure whether the non-interacted items are really negative or positive but not displayed to the corresponding user. Moreover, the relevance of rare items is usually underestimated since much fewer positive feedback of rare items is collected compared with popular ones. To tackle such difficulties, both pointwise and pairwise solutions are proposed before for unbiased relevance learning. As pairwise learning suits well for the ranking tasks, the previously proposed unbiased pairwise learning algorithm already achieves state-of-the-art performance. Nonetheless, the existing unbiased pairwise learning method suffers from high variance. To get satisfactory performance, non-negative estimator is utilized for practical variance control but introduces additional bias. In this work, we propose an unbiased pairwise learning method, named UPL, with much lower variance to learn a truly unbiased recommender model. Extensive offline experiments on real world datasets and online A/B testing demonstrate the superior performance of our proposed method.

20. Diffusion Recommender Model, SIGIR 2023

Wenjie Wang, Yiyan Xu, Fuli Feng, Xinyu Lin, Xiangnan He, Tat-Seng Chua

https://arxiv.org/abs/2304.04971

Generative models such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) are widely utilized to model the generative process of user interactions. However, these generative models suffer from intrinsic limitations such as the instability of GANs and the restricted representation ability of VAEs. Such limitations hinder the accurate modeling of the complex user interaction generation procedure, such as noisy interactions caused by various interference factors. In light of the impressive advantages of Diffusion Models (DMs) over traditional generative models in image synthesis, we propose a novel Diffusion Recommender Model (named DiffRec) to learn the generative process in a denoising manner. To retain personalized information in user interactions, DiffRec reduces the added noises and avoids corrupting users' interactions into pure noises like in image synthesis. In addition, we extend traditional DMs to tackle the unique challenges in practical recommender systems: high resource costs for large-scale item prediction and temporal shifts of user preference. To this end, we propose two extensions of DiffRec: L-DiffRec clusters items for dimension compression and conducts the diffusion processes in the latent space; and T-DiffRec reweights user interactions based on the interaction timestamps to encode temporal information. We conduct extensive experiments on three datasets under multiple settings (e.g. clean training, noisy training, and temporal training). The empirical results and in-depth analysis validate the superiority of DiffRec with two extensions over competitive baselines.

21. A Recommender System Approach for Very Large-scale Multi-objective Optimization

Haokai Hong, Min Jiang, Jonathan M. Garibaldi, Qiuzhen Lin, Kay Chen Tan

https://arxiv.org/abs/2304.04067

We define very large multi-objective optimization problems to be multiobjective optimization problems in which the number of decision variables is greater than 100,000 dimensions. This is an important class of problems as many real-world problems require optimizing hundreds of thousands of variables. Existing evolutionary optimization methods fall short of such requirements when dealing with problems at this very large scale. Inspired by the success of existing recommender systems to handle very large-scale items with limited historical interactions, in this paper we propose a method termed Very large-scale Multiobjective Optimization through Recommender Systems (VMORS). The idea of the proposed method is to transform the defined such very large-scale problems into a problem that can be tackled by a recommender system. In the framework, the solutions are regarded as users, and the different evolution directions are items waiting for the recommendation. We use Thompson sampling to recommend the most suitable items (evolutionary directions) for different users (solutions), in order to locate the optimal solution to a multiobjective optimization problem in a very large search space within acceptable time. We test our proposed method on different problems from 100,000 to 500,000 dimensions, and experimental results show that our method not only shows good performance but also significant improvement over existing methods.

22. Continuous Input Embedding Size Search For Recommender Systems, SIGIR 2023

Yunke Qu, Tong Chen, Xiangyu Zhao, Lizhen Cui, Kai Zheng, Hongzhi Yin

https://arxiv.org/abs/2304.03501

Latent factor models are the most popular backbones for today's recommender systems owing to their prominent performance. Latent factor models represent users and items as real-valued embedding vectors for pairwise similarity computation, and all embeddings are traditionally restricted to a uniform size that is relatively large (e.g., 256-dimensional). With the exponentially expanding user base and item catalog in contemporary e-commerce, this design is admittedly becoming memory-inefficient. To facilitate lightweight recommendation, reinforcement learning (RL) has recently opened up opportunities for identifying varying embedding sizes for different users/items. However, challenged by search efficiency and learning an optimal RL policy, existing RL-based methods are restricted to highly discrete, predefined embedding size choices. This leads to a largely overlooked potential of introducing finer granularity into embedding sizes to obtain better recommendation effectiveness under a given memory budget. In this paper, we propose continuous input embedding size search (CIESS), a novel RL-based method that operates on a continuous search space with arbitrary embedding sizes to choose from. In CIESS, we further present an innovative random walk-based exploration strategy to allow the RL policy to efficiently explore more candidate embedding sizes and converge to a better decision. CIESS is also model-agnostic and hence generalizable to a variety of latent factor RSs, whilst experiments on two real-world datasets have shown state-of-the-art performance of CIESS under different memory budgets when paired with three popular recommendation models.