论文周报 | 推荐系统领域最新研究进展
嘿，记得给“机器学习与推荐算法”添加星标
本次论文集合的方向主要包括基于Transformer的引用推荐评估[1]、推荐系统中语言解释的公平性[2]、工业级广告推荐的机器学习工程[3]、基于强化学习的推荐与推理[4]、多行为推荐中的因果干预公平性[5]、可信医疗诊断推荐系统[8]、基于循环神经切线核的序列推荐[9]、极简图对比学习推荐算法[13]、在线小说推荐中的可重复购买建模[14]、基于解耦图对比学习的评论推荐[19]、可解释指导的对比学习序列推荐[20]、推荐系统模型发展简史[25]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. Large-scale Evaluation of Transformer-based Article Encoders on the Task of Citation Recommendation, Workshop on COLING2022 2. On Faithfulness and Coherence of Language Explanations for Recommendation Systems 3. On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models, Workshop on RecSys2022 4. Reinforcement Recommendation Reasoning through Knowledge Graphs for Explanation Path Quality 5. Causal Intervention for Fairness in Multi-behavior Recommendation 6. Simple and Powerful Architecture for Inductive Recommendation Using Knowledge Graph Convolutions 7. SUPER-Rec: SUrrounding Position-Enhanced Representation for Recommendation 8. Towards Responsible Medical Diagnostics Recommendation Systems 9. Beyond Double Ascent via Recurrent Neural Tangent Kernel in Sequential Recommendation 10. Tag-Aware Document Representation for Research Paper Recommendation 11. INFACT: An Online Human Evaluation Framework for Conversational Recommendation 12. A Systematical Evaluation for Next-Basket Recommendation Algorithms 13. XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation, submitted to TKDE2022 14. Modeling User Repeat Consumption Behavior for Online Novel Recommendation, RecSys2022 15. The Best Decisions Are Not the Best Advice: Making Adherence-Aware Recommendations 16. Exposure-Aware Recommendation using Contextual Bandits 17. DMiner: Dashboard Design Mining and Recommendation 18. Hierarchical Transformer with Spatio-Temporal Context Aggregation for Next Point-of-Interest Recommendation 19. Disentangled Graph Contrastive Learning for Review-based Recommendation 20. Explanation Guided Contrastive Learning for Sequential Recommendation, CIKM2022 21. Ordinal Graph Gamma Belief Network for Social Recommender Systems 22. Random Isn't Always Fair: Candidate Set Imbalance and Exposure Inequality in Recommender Systems 23. Fair Matrix Factorisation for Large-Scale Recommender Systems 24. Recommender Systems and Algorithmic Hate, RecSys2022 25. A Brief History of Recommender Systems, DLP-KDD2022
1. Large-scale Evaluation of Transformer-based Article Encoders on the Task of Citation Recommendation, Workshop on COLING2022
Zoran Medić, Jan Šnajder
https://arxiv.org/abs/2209.05452
Recently introduced transformer-based article encoders (TAEs) designed to produce similar vector representations for mutually related scientific articles have demonstrated strong performance on benchmark datasets for scientific article recommendation. However, the existing benchmark datasets are predominantly focused on single domains and, in some cases, contain easy negatives in small candidate pools. Evaluating representations on such benchmarks might obscure the realistic performance of TAEs in setups with thousands of articles in candidate pools. In this work, we evaluate TAEs on large benchmarks with more challenging candidate pools. We compare the performance of TAEs with a lexical retrieval baseline model BM25 on the task of citation recommendation, where the model produces a list of recommendations for citing in a given input article. We find out that BM25 is still very competitive with the state-of-the-art neural retrievers, a finding which is surprising given the strong performance of TAEs on small benchmarks. As a remedy for the limitations of the existing benchmarks, we propose a new benchmark dataset for evaluating scientific article representations: Multi-Domain Citation Recommendation dataset (MDCR), which covers different scientific fields and contains challenging candidate pools.
2. On Faithfulness and Coherence of Language Explanations for Recommendation Systems
Zhouhang Xie, Julian McAuley, Bodhisattwa Prasad Majumder
https://arxiv.org/abs/2209.05409
Reviews contain rich information about product characteristics and user interests and thus are commonly used to boost recommender system performance. Specifically, previous work show that jointly learning to perform review generation improves rating prediction performance. Meanwhile, these model-produced reviews serve as recommendation explanations, providing the user with insights on predicted ratings. However, while existing models could generate fluent, human-like reviews, it is unclear to what degree the reviews fully uncover the rationale behind the jointly predicted rating. In this work, we perform a series of evaluations that probes state-of-the-art models and their review generation component. We show that the generated explanations are brittle and need further evaluation before being taken as literal rationales for the estimated ratings.
3. On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models, Workshop on RecSys2022
Rohan Anil, Sandra Gadanho, Da Huang, Nijith Jacob, Zhuoshu Li, Dong Lin, Todd Phillips, Cristina Pop, Kevin Regan, Gil I. Shamir, Rakesh Shivanna, Qiqi Yan
https://arxiv.org/abs/2209.05310
For industrial-scale advertising systems, prediction of ad click-through rate (CTR) is a central problem. Ad clicks constitute a significant class of user engagements and are often used as the primary signal for the usefulness of ads to users. Additionally, in cost-per-click advertising systems where advertisers are charged per click, click rate expectations feed directly into value estimation. Accordingly, CTR model development is a significant investment for most Internet advertising companies. Engineering for such problems requires many machine learning (ML) techniques suited to online learning that go well beyond traditional accuracy improvements, especially concerning efficiency, reproducibility, calibration, credit attribution. We present a case study of practical techniques deployed in Google's search ads CTR model. This paper provides an industry case study highlighting important areas of current ML research and illustrating how impactful new ML methods are evaluated and made useful in a large-scale industrial setting.
4. Reinforcement Recommendation Reasoning through Knowledge Graphs for Explanation Path Quality
Giacomo Balloccu, Ludovico Boratto, Gianni Fenu, Mirko Marras
https://arxiv.org/abs/2209.04954
Numerous Knowledge Graphs (KGs) are being created to make recommender systems not only intelligent but also knowledgeable. Reinforcement recommendation reasoning is a recent approach able to model high-order user-product relations, according to the KG. This type of approach makes it possible to extract reasoning paths between the recommended product and already experienced products. These paths can be in turn translated into textual explanations to be provided to the user for a given recommendation. However, none of the existing approaches has investigated user-level properties of a single or a group of reasoning paths. In this paper, we propose a series of quantitative properties that monitor the quality of the reasoning paths, based on recency, popularity, and diversity. We then combine in- and post-processing approaches to optimize for both recommendation quality and reasoning path quality. Experiments on three public data sets show that our approaches significantly increase reasoning path quality according to the proposed properties, while preserving recommendation quality. Source code, data sets, and KGs are available at: https://tinyurl.com/bdbfzr4n
5. Causal Intervention for Fairness in Multi-behavior Recommendation
Xi Wang, Wenjie Wang, Fuli Feng, Wenge Rong, Chuantao Yin
https://arxiv.org/abs/2209.04589
Recommender systems usually learn user interests from various user behaviors, including clicks and post-click behaviors (e.g., like and favorite). However, these behaviors inevitably exhibit popularity bias, leading to some unfairness issues: 1) for items with similar quality, more popular ones get more exposure; and 2) even worse the popular items with lower popularity might receive more exposure. Existing work on mitigating popularity bias blindly eliminates the bias and usually ignores the effect of item quality. We argue that the relationships between different user behaviors (e.g., conversion rate) actually reflect the item quality. Therefore, to handle the unfairness issues, we propose to mitigate the popularity bias by considering multiple user behaviors.
6. Simple and Powerful Architecture for Inductive Recommendation Using Knowledge Graph Convolutions
Theis E. Jendal, Matteo Lissandrini, Peter Dolog, Katja Hose
https://arxiv.org/abs/2209.04185
Using graph models with relational information in recommender systems has shown promising results. Yet, most methods are transductive, i.e., they are based on dimensionality reduction architectures. Hence, they require heavy retraining every time new items or users are added. Conversely, inductive methods promise to solve these issues. Nonetheless, all inductive methods rely only on interactions, making recommendations for users with few interactions sub-optimal and even impossible for new items. Therefore, we focus on inductive methods able to also exploit knowledge graphs (KGs). In this work, we propose SimpleRec, a strong baseline that uses a graph neural network and a KG to provide better recommendations than related inductive methods for new users and items. We show that it is unnecessary to create complex model architectures for user representations, but it is enough to allow users to be represented by the few ratings they provide and the indirect connections among them without any user metadata. As a result, we re-evaluate state-of-the-art methods, identify better evaluation protocols, highlight unwarranted conclusions from previous proposals, and showcase a novel, stronger baseline for this task.
7. SUPER-Rec: SUrrounding Position-Enhanced Representation for Recommendation
Taejun Lim, Siqu Long, Josiah Poon, Soyeon Caren Han
https://arxiv.org/abs/2209.04154
Collaborative filtering problems are commonly solved based on matrix completion techniques which recover the missing values of user-item interaction matrices. In a matrix, the rating position specifically represents the user given and the item rated. Previous matrix completion techniques tend to neglect the position of each element (user, item and ratings) in the matrix but mainly focus on semantic similarity between users and items to predict the missing value in a matrix. This paper proposes a novel position-enhanced user/item representation training model for recommendation, SUPER-Rec. We first capture the rating position in the matrix using the relative positional rating encoding and store the position-enhanced rating information and its user-item relationship to the fixed dimension of embedding that is not affected by the matrix size. Then, we apply the trained position-enhanced user and item representations to the simplest traditional machine learning models to highlight the pure novelty of our representation learning model. We contribute the first formal introduction and quantitative analysis of position-enhanced item representation in the recommendation domain and produce a principled discussion about our SUPER-Rec to the outperformed performance of typical collaborative filtering recommendation tasks with both explicit and implicit feedback.
8. Towards Responsible Medical Diagnostics Recommendation Systems
Daniel Schlör, Andreas Hotho
https://arxiv.org/abs/2209.03760
The early development and deployment of hospital and healthcare information systems have encouraged the ongoing digitization of processes in hospitals. Many of these processes, which previously required paperwork and telephone arrangements, are now integrated into IT solutions and require physicians and medical staff to interact with appropriate interfaces and tools. Although this shift to digital data management and process support has benefited patient care in many ways, it requires physicians to accurately capture all relevant information digitally for billing and documentation purposes, which takes a lot of time away from actual patient care work. However, systematic collection of healthcare data over a long period of time offers opportunities to improve this process and support medical staff by introducing recommender systems. Based on a practical working example, in this position paper, we will outline the design of a responsible recommender system in the medical context from a technical, application driven perspective and discuss potential design choices and criteria with a specific focus on accountability, safety, and fairness.
9. Beyond Double Ascent via Recurrent Neural Tangent Kernel in Sequential Recommendation
Ruihong Qiu, Zi Huang, Hongzhi Yin
https://arxiv.org/abs/2209.03735
Overfitting has long been considered a common issue to large neural network models in sequential recommendation. In our study, an interesting phenomenon is observed that overfitting is temporary. When the model scale is increased, the trend of the performance firstly ascends, then descends (i.e., overfitting) and finally ascends again, which is named as double ascent in this paper. We therefore raise an assumption that a considerably larger model will generalise better with a higher performance. In an extreme case to infinite-width, performance is expected to reach the limit of this specific structure. Unfortunately, it is impractical to directly build a huge model due to the limit of resources. In this paper, we propose the Overparameterised Recommender (OverRec), which utilises a recurrent neural tangent kernel (RNTK) as a similarity measurement for user sequences to successfully bypass the restriction of hardware for huge models. We further prove that the RNTK for the tied input-output embeddings in recommendation is the same as the RNTK for general untied input-output embeddings, which makes RNTK theoretically suitable for recommendation. Since the RNTK is analytically derived, OverRec does not require any training, avoiding physically building the huge model. Extensive experiments are conducted on four datasets, which verifies the state-of-the-art performance of OverRec.
10. Tag-Aware Document Representation for Research Paper Recommendation
Hebatallah A. Mohamed, Giuseppe Sansonetti, Alessandro Micarelli
https://arxiv.org/abs/2209.03660
Finding online research papers relevant to one's interests is very challenging due to the increasing number of publications. Therefore, personalized research paper recommendation has become a significant and timely research topic. Collaborative filtering is a successful recommendation approach, which exploits the ratings given to items by users as a source of information for learning to make accurate recommendations. However, the ratings are often very sparse as in the research paper domain, due to the huge number of publications growing every year. Therefore, more attention has been drawn to hybrid methods that consider both ratings and content information. Nevertheless, most of the hybrid recommendation approaches that are based on text embedding have utilized bag-of-words techniques, which ignore word order and semantic meaning. In this paper, we propose a hybrid approach that leverages deep semantic representation of research papers based on social tags assigned by users. The experimental evaluation is performed on CiteULike, a real and publicly available dataset. The obtained findings show that the proposed model is effective in recommending research papers even when the rating data is very sparse.
11. INFACT: An Online Human Evaluation Framework for Conversational Recommendation
Ahtsham Manzoor, Dietmar jannach
https://arxiv.org/abs/2209.03213
Conversational recommender systems (CRS) are interactive agents that support their users in recommendation-related goals through multi-turn conversations. Generally, a CRS can be evaluated in various dimensions. Today's CRS mainly rely on offline(computational) measures to assess the performance of their algorithms in comparison to different baselines. However, offline measures can have limitations, for example, when the metrics for comparing a newly generated response with a ground truth do not correlate with human perceptions, because various alternative generated responses might be suitable too in a given dialog situation. Current research on machine learning-based CRS models therefore acknowledges the importance of humans in the evaluation process, knowing that pure offline measures may not be sufficient in evaluating a highly interactive system like a CRS.
12. A Systematical Evaluation for Next-Basket Recommendation Algorithms
Zhufeng Shao, Shoujin Wang, Qian Zhang, Wenpeng Lu, Zhao Li, Xueping Peng
https://arxiv.org/abs/2209.02892
Next basket recommender systems (NBRs) aim to recommend a user's next (shopping) basket of items via modeling the user's preferences towards items based on the user's purchase history, usually a sequence of historical baskets. Due to its wide applicability in the real-world E-commerce industry, the studies NBR have attracted increasing attention in recent years. NBRs have been widely studied and much progress has been achieved in this area with a variety of NBR approaches having been proposed. However, an important issue is that there is a lack of a systematic and unified evaluation over the various NBR approaches. Different studies often evaluate NBR approaches on different datasets, under different experimental settings, making it hard to fairly and effectively compare the performance of different NBR approaches. To bridge this gap, in this work, we conduct a systematical empirical study in NBR area. Specifically, we review the representative work in NBR and analyze their cons and pros. Then, we run the selected NBR algorithms on the same datasets, under the same experimental setting and evaluate their performances using the same measurements. This provides a unified framework to fairly compare different NBR approaches. We hope this study can provide a valuable reference for the future research in this vibrant area.
13. XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation, submitted to TKDE2022
Junliang Yu, Xin Xia, Tong Chen, Lizhen Cui, Nguyen Quoc Viet Hung, Hongzhi Yin
https://arxiv.org/abs/2209.02544
Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance. The fundamental idea of CL-based recommendation models is to maximize the consistency between representations learned from different graph augmentations of the user-item bipartite graph. In such a self-supervised manner, CL-based recommendation models are expected to extract general features from the raw data to tackle the data sparsity issue. Despite the effectiveness of this paradigm, we still have no clue what underlies the performance gains. In this paper, we first reveal that CL enhances recommendation through endowing the model with the ability to learn more evenly distributed user/item representations, which can implicitly alleviate the pervasive popularity bias and promote long-tail items. Meanwhile, we find that the graph augmentations, which were considered a necessity in prior studies, are relatively unreliable and less significant in CL-based recommendation. On top of these findings, we put forward an eXtremely Simple Graph Contrastive Learning method (XSimGCL) for recommendation, which discards the ineffective graph augmentations and instead employs a simple yet effective noise-based embedding augmentation to create views for CL. A comprehensive experimental study on three large and highly sparse benchmark datasets demonstrates that, though the proposed method is extremely simple, it can smoothly adjust the uniformity of learned representations and outperforms its graph augmentation-based counterparts by a large margin in both recommendation accuracy and training efficiency. The code is released at:https://github.com/Coder-Yu/SELFRec
14. Modeling User Repeat Consumption Behavior for Online Novel Recommendation, RecSys2022
Yuncong Li, Cunxiang Yin, Yancheng He, Guoqiang Xu, Jing Cai, Leeven Luo, Sheng-hua Zhong
https://arxiv.org/abs/2209.01963
Given a user's historical interaction sequence, online novel recommendation suggests the next novel the user may be interested in. Online novel recommendation is important but underexplored. In this paper, we concentrate on recommending online novels to new users of an online novel reading platform, whose first visits to the platform occurred in the last seven days. We have two observations about online novel recommendation for new users. First, repeat novel consumption of new users is a common phenomenon. Second, interactions between users and novels are informative. To accurately predict whether a user will reconsume a novel, it is crucial to characterize each interaction at a fine-grained level. Based on these two observations, we propose a neural network for online novel recommendation, called NovelNet. NovelNet can recommend the next novel from both the user's consumed novels and new novels simultaneously. Specifically, an interaction encoder is used to obtain accurate interaction representation considering fine-grained attributes of interaction, and a pointer network with a pointwise loss is incorporated into NovelNet to recommend previously-consumed novels. Moreover, an online novel recommendation dataset is built from a well-known online novel reading platform and is released for public use as a benchmark. Experimental results on the dataset demonstrate the effectiveness of NovelNet.
15. The Best Decisions Are Not the Best Advice: Making Adherence-Aware Recommendations
Julien Grand-Clément, Jean Pauphilet
https://arxiv.org/abs/2209.01874
Many high-stake decisions follow an expert-in-loop structure in that a human operator receives recommendations from an algorithm but is the ultimate decision maker. Hence, the algorithm's recommendation may differ from the actual decision implemented in practice. However, most algorithmic recommendations are obtained by solving an optimization problem that assumes recommendations will be perfectly implemented. We propose an adherence-aware optimization framework to capture the dichotomy between the recommended and the implemented policy and analyze the impact of partial adherence on the optimal recommendation. We show that overlooking the partial adherence phenomenon, as is currently being done by most recommendation engines, can lead to arbitrarily severe performance deterioration, compared with both the current human baseline performance and what is expected by the recommendation algorithm. Our framework also provides useful tools to analyze the structure and to compute optimal recommendation policies that are naturally immune against such human deviations, and are guaranteed to improve upon the baseline policy.
16. Exposure-Aware Recommendation using Contextual Bandits
Masoud Mansoury, Bamshad Mobasher, Herke van Hoof
https://arxiv.org/abs/2209.01665
Exposure bias is a well-known issue in recommender systems where items and suppliers are not equally represented in the recommendation results. This is especially problematic when bias is amplified over time as a few items (e.g., popular ones) are repeatedly over-represented in recommendation lists and users' interactions with those items will amplify bias towards those items over time resulting in a feedback loop. This issue has been extensively studied in the literature on model-based or neighborhood-based recommendation algorithms, but less work has been done on online recommendation models, such as those based on top-K contextual bandits, where recommendation models are dynamically updated with ongoing user feedback. In this paper, we study exposure bias in a class of well-known contextual bandit algorithms known as Linear Cascading Bandits. We analyze these algorithms on their ability to handle exposure bias and provide a fair representation for items in the recommendation results. Our analysis reveals that these algorithms tend to amplify exposure disparity among items over time. In particular, we observe that these algorithms do not properly adapt to the feedback provided by the users and frequently recommend certain items even when those items are not selected by users. To mitigate this bias, we propose an Exposure-Aware (EA) reward model that updates the model parameters based on two factors: 1) user feedback (i.e., clicked or not), and 2) position of the item in the recommendation list. This way, the proposed model controls the utility assigned to items based on their exposure in the recommendation list. Extensive experiments on two real-world datasets using three contextual bandit algorithms show that the proposed reward model reduces exposure bias amplification in long run while maintaining the recommendation accuracy.
17. DMiner: Dashboard Design Mining and Recommendation
Yanna Lin, Haotian Li, Aoyu Wu, Yong Wang, Huamin Qu
https://arxiv.org/abs/2209.01599
Dashboards, which comprise multiple views on a single display, help analyze and communicate multiple perspectives of data simultaneously. However, creating effective and elegant dashboards is challenging since it requires careful and logical arrangement and coordination of multiple visualizations. To solve the problem, we propose a data-driven approach for mining design rules from dashboards and automating dashboard organization. Specifically, we focus on two prominent aspects of the organization: arrangement, which describes the position, size, and layout of each view in the display space; and coordination, which indicates the interaction between pairwise views. We build a new dataset containing 854 dashboards crawled online, and develop feature engineering methods for describing the single views and view-wise relationships in terms of data, encoding, layout, and interactions. Further, we identify design rules among those features and develop a recommender for dashboard design. We demonstrate the usefulness of DMiner through an expert study and a user study. The expert study shows that our extracted design rules are reasonable and conform to the design practice of experts. Moreover, a comparative user study shows that our recommender could help automate dashboard organization and reach human-level performance. In summary, our work offers a promising starting point for design mining visualizations to build recommenders.
18. Hierarchical Transformer with Spatio-Temporal Context Aggregation for Next Point-of-Interest Recommendation
Jiayi Xie, Zhenzhong Chen
https://arxiv.org/abs/2209.01559
Next point-of-interest (POI) recommendation is a critical task in location-based social networks, yet remains challenging due to a high degree of variation and personalization exhibited in user movements. In this work, we explore the latent hierarchical structure composed of multi-granularity short-term structural patterns in user check-in sequences. We propose a Spatio-Temporal context AggRegated Hierarchical Transformer (STAR-HiT) for next POI recommendation, which employs stacked hierarchical encoders to recursively encode the spatio-temporal context and explicitly locate subsequences of different granularities. More specifically, in each encoder, the global attention layer captures the spatio-temporal context of the sequence, while the local attention layer performed within each subsequence enhances subsequence modeling using the local context. The sequence partition layer infers positions and lengths of subsequences from the global context adaptively, such that semantics in subsequences can be well preserved. Finally, the subsequence aggregation layer fuses representations within each subsequence to form the corresponding subsequence representation, thereby generating a new sequence of higher-level granularity. The stacking of encoders captures the latent hierarchical structure of the check-in sequence, which is used to predict the next visiting POI. Extensive experiments on three public datasets demonstrate that the proposed model achieves superior performance whilst providing explanations for recommendations. Codes are available at: https://github.com/JennyXieJiayi/STAR-HiT
19. Disentangled Graph Contrastive Learning for Review-based Recommendation
Yuyang Ren, Haonan Zhang, Qi Li, Luoyi Fu, Jiaxin Ding, Xinde Cao, Xinbing Wang, Chenghu Zhou
https://arxiv.org/abs/2209.01524
User review data is helpful in alleviating the data sparsity problem in many recommender systems. In review-based recommendation methods, review data is considered as auxiliary information that can improve the quality of learned user/item or interaction representations for the user rating prediction task. However, these methods usually model user-item interactions in a holistic manner and neglect the entanglement of the latent factors behind them, e.g., price, quality, or appearance, resulting in suboptimal representations and reducing interpretability. In this paper, we propose a Disentangled Graph Contrastive Learning framework for Review-based recommendation (DGCLR), to separately model the user-item interactions based on different latent factors through the textual review data. To this end, we first model the distributions of interactions over latent factors from both semantic information in review data and structural information in user-item graph data, forming several factor graphs. Then a factorized message passing mechanism is designed to learn disentangled user/item representations on the factor graphs, which enable us to further characterize the interactions and adaptively combine the predicted ratings from multiple factors via a devised attention mechanism. Finally, we set two factor-wise contrastive learning objectives to alleviate the sparsity issue and model the user/item and interaction features pertinent to each factor more accurately. Empirical results over five benchmark datasets validate the superiority of DGCLR over the state-of-the-art methods. Further analysis is offered to interpret the learned intent factors and rating prediction in DGCLR.
20. Explanation Guided Contrastive Learning for Sequential Recommendation, CIKM2022
Lei Wang, Ee-Peng Lim, Zhiwei Liu, Tianxiang Zhao
https://arxiv.org/abs/2209.01347
Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions. Nevertheless, the existing contrastive learning-based methods fail to ensure that the positive (or negative) sequence obtained by some random augmentation (or sequence sampling) on a given anchor user sequence remains to be semantically similar (or different). When the positive and negative sequences turn out to be false positive and false negative respectively, it may lead to degraded recommendation performance. In this work, we address the above problem by proposing Explanation Guided Augmentations (EGA) and Explanation Guided Contrastive Learning for Sequential Recommendation (EC4SRec) model framework. The key idea behind EGA is to utilize explanation method(s) to determine items' importance in a user sequence and derive the positive and negative sequences accordingly. EC4SRec then combines both self-supervised and supervised contrastive learning over the positive and negative sequences generated by EGA operations to improve sequence representation learning for more accurate recommendation results. Extensive experiments on four real-world benchmark datasets demonstrate that EC4SRec outperforms the state-of-the-art sequential recommendation methods and two recent contrastive learning-based sequential recommendation methods, CL4SRec and DuoRec. Our experiments also show that EC4SRec can be easily adapted for different sequence encoder backbones (e.g., GRU4Rec and Caser), and improve their recommendation performance.
21. Ordinal Graph Gamma Belief Network for Social Recommender Systems
Dongsheng Wang, Chaojie Wang, Bo Chen, Mingyuan Zhou
https://arxiv.org/abs/2209.05106
To build recommender systems that not only consider user-item interactions represented as ordinal variables, but also exploit the social network describing the relationships between the users, we develop a hierarchical Bayesian model termed ordinal graph factor analysis (OGFA), which jointly models user-item and user-user interactions. OGFA not only achieves good recommendation performance, but also extracts interpretable latent factors corresponding to representative user preferences. We further extend OGFA to ordinal graph gamma belief network, which is a multi-stochastic-layer deep probabilistic model that captures the user preferences and social communities at multiple semantic levels. For efficient inference, we develop a parallel hybrid Gibbs-EM algorithm, which exploits the sparsity of the graphs and is scalable to large datasets. Our experimental results show that the proposed models not only outperform recent baselines on recommendation datasets with explicit or implicit feedback, but also provide interpretable latent representations.
22. Random Isn't Always Fair: Candidate Set Imbalance and Exposure Inequality in Recommender Systems
Amanda Bower, Kristian Lum, Tomo Lazovich, Kyra Yee, Luca Belli
https://arxiv.org/abs/2209.05000
Traditionally, recommender systems operate by returning a user a set of items, ranked in order of estimated relevance to that user. In recent years, methods relying on stochastic ordering have been developed to create "fairer" rankings that reduce inequality in who or what is shown to users. Complete randomization -- ordering candidate items randomly, independent of estimated relevance -- is largely considered a baseline procedure that results in the most equal distribution of exposure. In industry settings, recommender systems often operate via a two-step process in which candidate items are first produced using computationally inexpensive methods and then a full ranking model is applied only to those candidates.
23. Fair Matrix Factorisation for Large-Scale Recommender Systems
Riku Togashi, Kenshi Abe
https://arxiv.org/abs/2209.04394
Modern recommender systems are hedged with various requirements, such as ranking quality, optimisation efficiency, and item fairness. It is challenging to reconcile these requirements at a practical level. In this study, we argue that item fairness is particularly hard to optimise in a large-scale setting. The notion of item fairness requires controlling the opportunity of items (e.g. exposure) by considering the entire ranked lists for users. It hence breaks the independence of optimisation subproblems for users and items, which is the essential property for conventional scalable algorithms, such as implicit alternating least squares (iALS). This paper explores a collaborative filtering method for fairness-aware item recommendation, achieving computational efficiency comparable to iALS, the most efficient method for item recommendation.
24. Recommender Systems and Algorithmic Hate, RecSys2022
Jessie J. Smith, Lucia Jayne, Robin Burke
https://arxiv.org/abs/2209.02159
Despite increasing reliance on personalization in digital platforms, many algorithms that curate content or information for users have been met with resistance. When users feel dissatisfied or harmed by recommendations, this can lead users to hate, or feel negatively towards these personalized systems. Algorithmic hate detrimentally impacts both users and the system, and can result in various forms of algorithmic harm, or in extreme cases can lead to public protests against ''the algorithm'' in question. In this work, we summarize some of the most common causes of algorithmic hate and their negative consequences through various case studies of personalized recommender systems. We explore promising future directions for the RecSys research community that could help alleviate algorithmic hate and improve the relationship between recommender systems and their users.
25. A Brief History of Recommender Systems, DLP-KDD2022
Zhenhua Dong, Zhe Wang, Jun Xu, Ruiming Tang, Jirong Wen
https://arxiv.org/abs/2209.01860
Soon after the invention of the Internet, the recommender system emerged and related technologies have been extensively studied and applied by both academia and industry. Currently, recommender system has become one of the most successful web applications, serving billions of people in each day through recommending different kinds of contents, including news feeds, videos, e-commerce products, music, movies, books, games, friends, jobs etc. These successful stories have proved that recommender system can transfer big data to high values. This article briefly reviews the history of web recommender systems, mainly from two aspects: (1) recommendation models, (2) architectures of typical recommender systems. We hope the brief review can help us to know the dots about the progress of web recommender systems, and the dots will somehow connect in the future, which inspires us to build more advanced recommendation services for changing the world better.
欢迎干货投稿 \ 论文宣传 \ 合作交流