论文周报[0624-0630] | 推荐系统领域最新研究进展(16篇)

本文精选了上周（0624-0630）最新发布的16篇推荐系统相关论文，主要研究方向包括高效课程推荐、图推荐、多模态食物推荐、个性化多场景多任务联邦推荐、语言理解增强推荐、序列推荐、跨域推荐、去偏推荐、大模型可解释推荐、轻量化嵌入推荐基准、点击率预估等。

1. Efficient Course Recommendations with T5-based Ranking and Summarization

2. Amplify Graph Learning for Recommendation via Sparsity Completion

3. Multi-modal Food Recommendation using Clustering and Self-supervised Learning

4. Towards Personalized Federated Multi-scenario Multi-task Recommendation

5. ELCoRec: Enhance Language Understanding with Co-Propagation of Numerical and Categorical Features for Recommendation

6. UniRec: A Dual Enhancement of Uniformity and Frequency in Sequential Recommendations

7. Hyperbolic Knowledge Transfer in Cross-Domain Recommendation System

8. Debiased Recommendation with Noisy Feedback

9. Guardrails for Avoiding Harmful Medical Product Recommendations and Off-label Promotion in Generative AI Models

10. LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning

11. SimCE: Simplifying Cross-Entropy Loss for Collaborative Filtering

12. Effects of Using Synthetic Data on Deep Recommender Models' Performance

13. Performative Debias with Fair-exposure Optimization Driven by Strategic Agents in Recommender Systems

14. A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems

15. A Survey on Intent-aware Recommender Systems

16. Light-weight End-to-End Graph Interest Network for CTR Prediction in E-commerce Search

1. Efficient Course Recommendations with T5-based Ranking and Summarization

Thijmen Bijl, Niels van Weeren, Suzan Verberne

https://arxiv.org/abs/2406.19018

In this paper, we implement and evaluate a two-stage retrieval pipeline for a course recommender system that ranks courses for skill-occupation pairs. The in-production recommender system BrightFit provides course recommendations from multiple sources. Some of the course descriptions are long and noisy, while retrieval and ranking in an online system have to be highly efficient. We developed a two-step retrieval pipeline with RankT5 finetuned on MSMARCO as re-ranker. We compare two summarizers for course descriptions: a LongT5 model that we finetuned for the task, and a generative LLM (Vicuna) with in-context learning. We experiment with quantization to reduce the size of the ranking model and increase inference speed. We evaluate our rankers on two newly labelled datasets, with an A/B test, and with a user questionnaire. On the two labelled datasets, our proposed two-stage ranking with automatic summarization achieves a substantial improvement over the in-production (BM25) ranker: nDCG@10 scores improve from 0.482 to 0.684 and from 0.447 to 0.844 on the two datasets. We also achieve a 40% speed-up by using a quantized version of RankT5. The improved quality of the ranking was confirmed by the questionnaire completed by 29 respondents, but not by the A/B test. In the A/B test, a higher clickthrough rate was observed for the BM25-ranking than for the proposed two-stage retrieval. We conclude that T5-based re-ranking and summarization for online course recommendation can obtain much better effectiveness than single-step lexical retrieval, and that quantization has a large effect on RankT5. In the online evaluation, however, other factors than relevance play a role (such as speed and interpretability of the retrieval results), as well as individual preferences. https://github.com/tbijl/course_ranking_data

2. Amplify Graph Learning for Recommendation via Sparsity Completion

Peng Yuan, Haojie Li, Minying Fang, Xu Yu, Yongjing Hao, Junwei Du

https://arxiv.org/abs/2406.18984

Graph learning models have been widely deployed in collaborative filtering (CF) based recommendation systems. Due to the issue of data sparsity, the graph structure of the original input lacks potential positive preference edges, which significantly reduces the performance of recommendations. In this paper, we study how to enhance the graph structure for CF more effectively, thereby optimizing the representation of graph nodes. Previous works introduced matrix completion techniques into CF, proposing the use of either stochastic completion methods or superficial structure completion to address this issue. However, most of these approaches employ random numerical filling that lack control over noise perturbations and limit the in-depth exploration of higher-order interaction features of nodes, resulting in biased graph representations.

In this paper, we propose an Amplify Graph Learning framework based on Sparsity Completion (called AGL-SC). First, we utilize graph neural network to mine direct interaction features between user and item nodes, which are used as the inputs of the encoder. Second, we design a factorization-based method to mine higher-order interaction features. These features serve as perturbation factors in the latent space of the hidden layer to facilitate generative enhancement. Finally, by employing the variational inference, the above multi-order features are integrated to implement the completion and enhancement of missing graph structures. We conducted benchmark and strategy experiments on four real-world datasets related to recommendation tasks. The experimental results demonstrate that AGL-SC significantly outperforms the state-of-the-art methods.https://github.com/yp8976/AGL_SC

3. Multi-modal Food Recommendation using Clustering and Self-supervised Learning

Yixin Zhang, Xin Zhou, Qianwen Meng, Fanglin Zhu, Yonghui Xu, Zhiqi Shen, Lizhen Cui

https://arxiv.org/abs/2406.18962

Food recommendation systems serve as pivotal components in the realm of digital lifestyle services, designed to assist users in discovering recipes and food items that resonate with their unique dietary predilections. Typically, multi-modal descriptions offer an exhaustive profile for each recipe, thereby ensuring recommendations that are both personalized and accurate. Our preliminary investigation of two datasets indicates that pre-trained multi-modal dense representations might precipitate a deterioration in performance compared to ID features when encapsulating interactive relationships. This observation implies that ID features possess a relative superiority in modeling interactive collaborative signals. Consequently, contemporary cutting-edge methodologies augment ID features with multi-modal information as supplementary features, overlooking the latent semantic relations between recipes.

To rectify this, we present CLUSSL, a novel food recommendation framework that employs clustering and self-supervised learning. Specifically, CLUSSL formulates a modality-specific graph tailored to each modality with discrete/continuous features, thereby transforming semantic features into structural representation. Furthermore, CLUSSL procures recipe representations pertinent to different modalities via graph convolutional operations. A self-supervised learning objective is proposed to foster independence between recipe representations derived from different unimodal graphs. Comprehensive experiments on real-world datasets substantiate that CLUSSL consistently surpasses state-of-the-art recommendation benchmarks in performance.

4. Towards Personalized Federated Multi-scenario Multi-task Recommendation

Yue Ding, Yanbiao Ji, Xun Cai, Xin Xin, Xiaofeng Gao, Hongtao Lu

https://arxiv.org/abs/2406.18938

In modern recommender system applications, such as e-commerce, predicting multiple targets like click-through rate (CTR) and post-view click-through & conversion rate (CTCVR) is common. Multi-task recommender systems are gaining traction in research and practical use. Existing multi-task recommender systems tackle diverse business scenarios, merging and modeling these scenarios unlocks shared knowledge to boost overall performance. As new and more complex real-world recommendation scenarios have emerged, data privacy issues make it difficult to train a single global multi-task recommendation model that processes multiple separate scenarios.

In this paper, we propose a novel framework for personalized federated multi-scenario multi-task recommendation, called PF-MSMTrec. We assign each scenario to a dedicated client, with each client utilizing the Mixture-of-Experts (MMoE) structure. Our proposed method aims to tackle the unique challenge posed by multiple optimization conflicts in this setting. We introduce a bottom-up joint learning mechanism. Firstly, we design a parameter template to decouple the parameters of the expert network. Thus, scenario parameters are shared knowledge for federated parameter aggregation, while task-specific parameters are personalized local parameters. Secondly, we conduct personalized federated learning for the parameters of each expert network through a federated communication round, utilizing three modules: federated batch normalization, conflict coordination, and personalized aggregation. Finally, we perform another round of personalized federated parameter aggregation on the task tower network to obtain the prediction results for multiple tasks. We conduct extensive experiments on two public datasets, and the results demonstrate that our proposed method surpasses state-of-the-art methods.

5. ELCoRec: Enhance Language Understanding with Co-Propagation of Numerical and Categorical Features for Recommendation

Jizheng Chen, Kounianhua Du, Jianghao Lin, Bo Chen, Ruiming Tang, Weinan Zhang

https://arxiv.org/abs/2406.18825

Large language models have been flourishing in the natural language processing (NLP) domain, and their potential for recommendation has been paid much attention to. Despite the intelligence shown by the recommendation-oriented finetuned models, LLMs struggle to fully understand the user behavior patterns due to their innate weakness in interpreting numerical features and the overhead for long context, where the temporal relations among user behaviors, subtle quantitative signals among different ratings, and various side features of items are not well explored. Existing works only fine-tune a sole LLM on given text data without introducing that important information to it, leaving these problems unsolved. In this paper, we propose ELCoRec to Enhance Language understanding with CoPropagation of numerical and categorical features for Recommendation. Concretely, we propose to inject the preference understanding capability into LLM via a GAT expert model where the user preference is better encoded by parallelly propagating the temporal relations, and rating signals as well as various side information of historical items. The parallel propagation mechanism could stabilize heterogeneous features and offer an informative user preference encoding, which is then injected into the language models via soft prompting at the cost of a single token embedding. To further obtain the user's recent interests, we proposed a novel Recent interaction Augmented Prompt (RAP) template. Experiment results over three datasets against strong baselines validate the effectiveness of ELCoRec. The code is available at https://anonymous.4open.science/r/CIKM_Code_Repo-E6F5/README.md.

6. UniRec: A Dual Enhancement of Uniformity and Frequency in Sequential Recommendations

Yang Liu, Yitong Wang, Chenyue Feng

https://arxiv.org/abs/2406.18470

Representation learning in sequential recommendation is critical for accurately modeling user interaction patterns and improving recommendation precision. However, existing approaches predominantly emphasize item-to-item transitions, often neglecting the time intervals between interactions, which are closely related to behavior pattern changes. Additionally, broader interaction attributes, such as item frequency, are frequently overlooked. We found that both sequences with more uniform time intervals and items with higher frequency yield better prediction performance. Conversely, non-uniform sequences exacerbate user interest drift and less-frequent items are difficult to model due to sparse sampling, presenting unique challenges inadequately addressed by current methods. In this paper, we propose UniRec, a novel bidirectional enhancement sequential recommendation method. UniRec leverages sequence uniformity and item frequency to enhance performance, particularly improving the representation of non-uniform sequences and less-frequent items. These two branches mutually reinforce each other, driving comprehensive performance optimization in complex sequential recommendation scenarios. Additionally, we present a multidimensional time module to further enhance adaptability. To the best of our knowledge, UniRec is the first method to utilize the characteristics of uniformity and frequency for feature augmentation. Comparing with eleven advanced models across four datasets, we demonstrate that UniRec outperforms SOTA models significantly. The code is available at https://github.com/Linxi000/UniRec

7. Hyperbolic Knowledge Transfer in Cross-Domain Recommendation System

Xin Yang, Heng Chang, Zhijian La, Jinze Yang, Xingrun Li, Yu Lu, Shuaiqiang Wang, Dawei Yin, Erxue Min

https://arxiv.org/abs/2406.17289

Cross-Domain Recommendation (CDR) seeks to utilize knowledge from different domains to alleviate the problem of data sparsity in the target recommendation domain, and it has been gaining more attention in recent years. Although there have been notable advancements in this area, most current methods represent users and items in Euclidean space, which is not ideal for handling long-tail distributed data in recommendation systems. Additionally, adding data from other domains can worsen the long-tail characteristics of the entire dataset, making it harder to train CDR models effectively. Recent studies have shown that hyperbolic methods are particularly suitable for modeling long-tail distributions, which has led us to explore hyperbolic representations for users and items in CDR scenarios. However, due to the distinct characteristics of the different domains, applying hyperbolic representation learning to CDR tasks is quite challenging. In this paper, we introduce a new framework called Hyperbolic Contrastive Learning (HCTS), designed to capture the unique features of each domain while enabling efficient knowledge transfer between domains. We achieve this by embedding users and items from each domain separately and mapping them onto distinct hyperbolic manifolds with adjustable curvatures for prediction. To improve the representations of users and items in the target domain, we develop a hyperbolic contrastive learning module for knowledge transfer. Extensive experiments on real-world datasets demonstrate that hyperbolic manifolds are a promising alternative to Euclidean space for CDR tasks.

8. Debiased Recommendation with Noisy Feedback

Haoxuan Li, Chunyuan Zheng, Wenjie Wang, Hao Wang, Fuli Feng, Xiao-Hua Zhou

https://arxiv.org/abs/2406.17182

Ratings of a user to most items in recommender systems are usually missing not at random (MNAR), largely because users are free to choose which items to rate. To achieve unbiased learning of the prediction model under MNAR data, three typical solutions have been proposed, including error-imputation-based (EIB), inverse-propensity-scoring (IPS), and doubly robust (DR) methods. However, these methods ignore an alternative form of bias caused by the inconsistency between the observed ratings and the users' true preferences, also known as noisy feedback or outcome measurement errors (OME), e.g., due to public opinion or low-quality data collection process. In this work, we study intersectional threats to the unbiased learning of the prediction model from data MNAR and OME in the collected data. First, we design OME-EIB, OME-IPS, and OME-DR estimators, which largely extend the existing estimators to combat OME in real-world recommendation scenarios. Next, we theoretically prove the unbiasedness and generalization bound of the proposed estimators. We further propose an alternate denoising training approach to achieve unbiased learning of the prediction model under MNAR data with OME. Extensive experiments are conducted on three real-world datasets and one semi-synthetic dataset to show the effectiveness of our proposed approaches. The code is available at https://github.com/haoxuanli-pku/KDD24-OME-DR

9. Guardrails for Avoiding Harmful Medical Product Recommendations and Off-label Promotion in Generative AI Models

Daniel Lopez-Martinez

https://arxiv.org/abs/2406.16455

Generative AI (GenAI) models have demonstrated remarkable capabilities in a wide variety of medical tasks. However, as these models are trained using generalist datasets with very limited human oversight, they can learn uses of medical products that have not been adequately evaluated for safety and efficacy, nor approved by regulatory agencies. Given the scale at which GenAI may reach users, unvetted recommendations pose a public health risk. In this work, we propose an approach to identify potentially harmful product recommendations, and demonstrate it using a recent multimodal large language model.

10. LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning

Guangsi Shi, Xiaofeng Deng, Linhao Luo, Lijuan Xia, Lei Bao, Bei Ye, Fei Du, Shirui Pan, Yuxiao Li

https://arxiv.org/abs/2406.15859

Recommender systems are pivotal in enhancing user experiences across various web applications by analyzing the complicated relationships between users and items. Knowledge graphs(KGs) have been widely used to enhance the performance of recommender systems. However, KGs are known to be noisy and incomplete, which are hard to provide reliable explanations for recommendation results. An explainable recommender system is crucial for the product development and subsequent decision-making. To address these challenges, we introduce a novel recommender that synergies Large Language Models (LLMs) and KGs to enhance the recommendation and provide interpretable results. Specifically, we first harness the power of LLMs to augment KG reconstruction. LLMs comprehend and decompose user reviews into new triples that are added into KG. In this way, we can enrich KGs with explainable paths that express user preferences.

To enhance the recommendation on augmented KGs, we introduce a novel subgraph reasoning module that effectively measures the importance of nodes and discovers reasoning for recommendation. Finally, these reasoning paths are fed into the LLMs to generate interpretable explanations of the recommendation results. Our approach significantly enhances both the effectiveness and interpretability of recommender systems, especially in cross-selling scenarios where traditional methods falter. The effectiveness of our approach has been rigorously tested on four open real-world datasets, with our methods demonstrating a superior performance over contemporary state-of-the-art techniques by an average improvement of 12%. The application of our model in a multinational engineering and technology company cross-selling recommendation system further underscores its practical utility and potential to redefine recommendation practices through improved accuracy and user trust.

11. SimCE: Simplifying Cross-Entropy Loss for Collaborative Filtering

Xiaodong Yang, Huiyuan Chen, Yuchen Yan, Yuxin Tang, Yuying Zhao, Eric Xu, Yiwei Cai, Hanghang Tong

https://arxiv.org/abs/2406.16170

The learning objective is integral to collaborative filtering systems, where the Bayesian Personalized Ranking (BPR) loss is widely used for learning informative backbones. However, BPR often experiences slow convergence and suboptimal local optima, partially because it only considers one negative item for each positive item, neglecting the potential impacts of other unobserved items. To address this issue, the recently proposed Sampled Softmax Cross-Entropy (SSM) compares one positive sample with multiple negative samples, leading to better performance. Our comprehensive experiments confirm that recommender systems consistently benefit from multiple negative samples during training. Furthermore, we introduce a Simplified Sampled Softmax Cross-Entropy Loss (SimCE), which simplifies the SSM using its upper bound. Our validation on 12 benchmark datasets, using both MF and LightGCN backbones, shows that SimCE significantly outperforms both BPR and SSM.

12. Effects of Using Synthetic Data on Deep Recommender Models' Performance

Fatih Cihan Taskin, Ilknur Akcay, Muhammed Pesen, Said Aldemir, Ipek Iraz Esin, Furkan Durmus

https://arxiv.org/abs/2406.18286

Recommender systems are essential for enhancing user experiences by suggesting items based on individual preferences. However, these systems frequently face the challenge of data imbalance, characterized by a predominance of negative interactions over positive ones. This imbalance can result in biased recommendations favoring popular items. This study investigates the effectiveness of synthetic data generation in addressing data imbalances within recommender systems. Six different methods were used to generate synthetic data. Our experimental approach involved generating synthetic data using these methods and integrating the generated samples into the original dataset. Our results show that the inclusion of generated negative samples consistently improves the Area Under the Curve (AUC) scores. The significant impact of synthetic negative samples highlights the potential of data augmentation strategies to address issues of data sparsity and imbalance, ultimately leading to improved performance of recommender systems.

13. Performative Debias with Fair-exposure Optimization Driven by Strategic Agents in Recommender Systems

Zhichen Xiang, Hongke Zhao, Chuang Zhao, Ming He, Jianping Fan

https://arxiv.org/abs/2406.17475

Data bias, e.g., popularity impairs the dynamics of two-sided markets within recommender systems. This overshadows the less visible but potentially intriguing long-tail items that could capture user interest. Despite the abundance of research surrounding this issue, it still poses challenges and remains a hot topic in academic circles. Along this line, in this paper, we developed a re-ranking approach in dynamic settings with fair-exposure optimization driven by strategic agents. Designed for the producer side, the execution of agents assumes content creators can modify item features based on strategic incentives to maximize their exposure. This iterative process entails an end-to-end optimization, employing differentiable ranking operators that simultaneously target accuracy and fairness. Joint objectives ensure the performance of recommendations while enhancing the visibility of tail items. We also leveraged the performativity nature of predictions to illustrate how strategic learning influences content creators to shift towards fairness efficiently, thereby incentivizing features of tail items. Through comprehensive experiments on both public and industrial datasets, we have substantiated the effectiveness and dominance of the proposed method especially on unveiling the potential of tail items.

14. A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems

Hung Vinh Tran, Tong Chen, Quoc Viet Hung Nguyen, Zi Huang, Lizhen Cui, Hongzhi Yin

https://arxiv.org/abs/2406.17335

Since the creation of the Web, recommender systems (RSs) have been an indispensable mechanism in information filtering. State-of-the-art RSs primarily depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables. To prevent over-parameterized embedding tables from harming scalability, both academia and industry have seen increasing efforts in compressing RS embeddings. However, despite the prosperity of lightweight embedding-based RSs (LERSs), a wide diversity is seen in evaluation protocols, resulting in obstacles when relating LERS performance to real-world usability. Moreover, despite the common goal of lightweight embeddings, LERSs are evaluated with a single choice between the two main recommendation tasks -- collaborative filtering and content-based recommendation. This lack of discussions on cross-task transferability hinders the development of unified, more scalable solutions. Motivated by these issues, this study investigates various LERSs' performance, efficiency, and cross-task transferability via a thorough benchmarking process. Additionally, we propose an efficient embedding compression method using magnitude pruning, which is an easy-to-deploy yet highly competitive baseline that outperforms various complex LERSs. Our study reveals the distinct performance of LERSs across the two tasks, shedding light on their effectiveness and generalizability. To support edge-based recommendations, we tested all LERSs on a Raspberry Pi 4, where the efficiency bottleneck is exposed. Finally, we conclude this paper with critical summaries of LERS performance, model selection suggestions, and underexplored challenges around LERSs for future research. To encourage future research, we publish source codes and artifacts at https://github.com/chenxing1999/recsys-benchmark

15. A Survey on Intent-aware Recommender Systems

Dietmar Jannach, Markus Zanker

https://arxiv.org/abs/2406.16350

Many modern online services feature personalized recommendations. A central challenge when providing such recommendations is that the reason why an individual user accesses the service may change from visit to visit or even during an ongoing usage session. To be effective, a recommender system should therefore aim to take the users' probable intent of using the service at a certain point in time into account. In recent years, researchers have thus started to address this challenge by incorporating intent-awareness into recommender systems. Correspondingly, a number of technical approaches were put forward, including diversification techniques, intent prediction models or latent intent modeling approaches. In this paper, we survey and categorize existing approaches to building the next generation of Intent-Aware Recommender Systems (IARS). Based on an analysis of current evaluation practices, we outline open gaps and possible future directions in this area, which in particular include the consideration of additional interaction signals and contextual information to further improve the effectiveness of such systems.

16. Light-weight End-to-End Graph Interest Network for CTR Prediction in E-commerce Search

Pai Peng, Quanxiang Jia, Ziqiang Zhou, Shuang Hong, Zichong Xiao

https://arxiv.org/abs/2406.17745

Click-through-rate (CTR) prediction has an essential impact on improving user experience and revenue in e-commerce search. With the development of deep learning, graph-based methods are well exploited to utilize graph structure extracted from user behaviors and other information to help embedding learning. However, most of the previous graph-based methods mainly focus on recommendation scenarios, and therefore their graph structures highly depend on item's sequential information from user behaviors, ignoring query's sequential signal and query-item correlation. In this paper, we propose a new approach named Light-weight End-to-End Graph Interest Network (EGIN) to effectively mine users' search interests and tackle previous challenges. (i) EGIN utilizes query and item's correlation and sequential information from the search system to build a heterogeneous graph for better CTR prediction in e-commerce search. (ii) EGIN's graph embedding learning shares the same training input and is jointly trained with CTR prediction, making the end-to-end framework effortless to deploy in large-scale search systems. The proposed EGIN is composed of three parts: query-item heterogeneous graph, light-weight graph sampling, and multi-interest network. The query-item heterogeneous graph captures correlation and sequential information of query and item efficiently by the proposed light-weight graph sampling. The multi-interest network is well designed to utilize graph embedding to capture various similarity relationships between query and item to enhance the final CTR prediction. We conduct extensive experiments on both public and industrial datasets to demonstrate the effectiveness of the proposed EGIN. At the same time, the training cost of graph learning is relatively low compared with the main CTR prediction task, ensuring efficiency in practical applications.