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
本文精选了上周（0530-0605）最新发布的16篇推荐系统相关论文，方向主要包括基于对比学习的推荐算法、基于因果的推荐算法、基于公平性的推荐算法、基于图的推荐算法、序列化推荐算法等，还包括一篇基于公平性的推荐系统综述文章。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. CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
2. Semantically-enhanced Topic Recommendation System for Software Projects
3. Stepping beyond your comfort zone: Diffusion-based network analytics for knowledge trajectory recommendation
4. From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse
5. A multimedia recommendation model based on collaborative graph
6. Enhancing Sequential Recommendation with Graph Contrastive Learning
7. Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
8. Deep Deconfounded Content-based Tag Recommendation for UGC with Causal Intervention
9. RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation
10. Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder
11. Fairness in Recommendation: A Survey
12. Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems
13. Fairness in the First Stage of Two-Stage Recommender Systems
14. A Personalized Recommender System for Pervasive Social Networks
15. Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever
16. Sequential Nature of Recommender Systems Disrupts the Evaluation Process
1. CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
Yunshan Ma, Yingzhi He, An Zhang, Xiang Wang, Tat-Seng Chua
https://arxiv.org/abs/2206.00242
Bundle recommendation aims to recommend a bundle of related items to users, which can satisfy the users' various needs with one-stop convenience. Recent methods usually take advantage of both user-bundle and user-item interactions information to obtain informative representations for users and bundles, corresponding to bundle view and item view, respectively. However, they either use a unified view without differentiation or loosely combine the predictions of two separate views, while the crucial cooperative association between the two views' representations is overlooked. In this work, we propose to model the cooperative association between the two different views through cross-view contrastive learning. By encouraging the alignment of the two separately learned views, each view can distill complementary information from the other view, achieving mutual enhancement. Moreover, by enlarging the dispersion of different users/bundles, the self-discrimination of representations is enhanced. Extensive experiments on three public datasets demonstrate that our method outperforms SOTA baselines by a large margin. Meanwhile, our method requires minimal parameters of three set of embeddings (user, bundle, and item) and the computational costs are largely reduced due to more concise graph structure and graph learning module. In addition, various ablation and model studies demystify the working mechanism and justify our hypothesis. Codes and datasets are available at https://github.com/mysbupt/CrossCBR.
2. Semantically-enhanced Topic Recommendation System for Software Projects
Maliheh Izadi, Mahtab Nejati, Abbas Heydarnoori
https://arxiv.org/abs/2206.00085
Software-related platforms have enabled their users to collaboratively label software entities with topics. Tagging software repositories with relevant topics can be exploited for facilitating various downstream tasks. For instance, a correct and complete set of topics assigned to a repository can increase its visibility. Consequently, this improves the outcome of tasks such as browsing, searching, navigation, and organization of repositories. Unfortunately, assigned topics are usually highly noisy, and some repositories do not have well-assigned topics. Thus, there have been efforts on recommending topics for software projects, however, the semantic relationships among these topics have not been exploited so far. We propose two recommender models for tagging software projects that incorporate the semantic relationship among topics. Our approach has two main phases; (1) we first take a collaborative approach to curate a dataset of quality topics specifically for the domain of software engineering and development. We also enrich this data with the semantic relationships among these topics and encapsulate them in a knowledge graph we call SED-KGraph. Then, (2) we build two recommender systems; The first one operates only based on the list of original topics assigned to a repository and the relationships specified in our knowledge graph. The second predictive model, however, assumes there are no topics available for a repository, hence it proceeds to predict the relevant topics based on both textual information of a software project and SED-KGraph. We built SED-KGraph in a crowd-sourced project with 170 contributors from both academia and industry. The experiment results indicate that our solutions outperform baselines that neglect the semantic relationships among topics by at least 25% and 23% in terms of ASR and MAP metrics.
3. Stepping beyond your comfort zone: Diffusion-based network analytics for knowledge trajectory recommendation
Yi Zhang, Mengjia Wu, Jie Lu
https://arxiv.org/abs/2205.15504
Interest in tracing the research interests of scientific researchers is rising, and particularly that of predicting a researcher's knowledge trajectories beyond their current foci into potential inter-/cross-/multi-disciplinary interactions. Hence, in this study, we present a method of diffusion-based network analytics for knowledge trajectory recommendation. The method begins by constructing a heterogeneous bibliometric network consisting of a co-topic layer and a co-authorship layer. A novel link prediction approach with a diffusion strategy is then used to reflect real-world academic activity, such as knowledge sharing between co-authors or diffusing between similar research topics. This strategy differentiates the interactions occurring between homogeneous and heterogeneous nodes and weights the strengths of these interactions. Two sets of experiments - one with a local dataset and another with a global dataset - demonstrate that the proposed method is prior to selected baselines. In addition, to further examine the reliability of our method, we conducted a case study on recommending knowledge trajectories of selected information scientists and their research groups. The results demonstrate the empirical insights our method yields for individual researchers, communities, and research institutions in the information science discipline.
4. From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse
Emily Sullivan, Philippe Verreault-Julien
https://arxiv.org/abs/2205.15406
People are increasingly subject to algorithmic decisions, and it is generally agreed that end-users should be provided an explanation or rationale for these decisions. There are different purposes that explanations can have, such as increasing user trust in the system or allowing users to contest the decision. One specific purpose that is gaining more traction is algorithmic recourse. We first propose that recourse should be viewed as a recommendation problem, not an explanation problem. Then, we argue that the capability approach provides plausible and fruitful ethical standards for recourse. We illustrate by considering the case of diversity constraints on algorithmic recourse. Finally, we discuss the significance and implications of adopting the capability approach for algorithmic recourse research.
5. A multimedia recommendation model based on collaborative graph
Breda Lim, Shubhi Bansal, Ahmed Buru, Kayla Manthey
https://arxiv.org/abs/2205.14931
As one of the main solutions to the information overload problem, recommender systems are widely used in daily life. In the recent emerging micro-video recommendation scenario, micro-videos contain rich multimedia information, involving text, image, video and other multimodal data, and these rich multimodal information conceals users' deep interest in the items. Most of the current recommendation algorithms based on multimodal data use multimodal information to expand the information on the item side, but ignore the different preferences of users for different modal information, and lack the fine-grained mining of the internal connection of multimodal information. To investigate the problems in the micro-video recommendr system mentioned above, we design a hybrid recommendation model based on multimodal information, introduces multimodal information and user-side auxiliary information in the network structure, fully explores the deep interest of users, measures the importance of each dimension of user and item feature representation in the scoring prediction task, makes the application of graph neural network in the recommendation system is improved by using an attention mechanism to fuse the multi-layer state output information, allowing the shallow structural features provided by the intermediate layer to better participate in the prediction task. The recommendation accuracy is improved compared with the traditional recommendation algorithm on different data sets, and the feasibility and effectiveness of our model is verified.
6. Enhancing Sequential Recommendation with Graph Contrastive Learning
Yixin Zhang, Yong Liu, Yonghui Xu, Hao Xiong, Chenyi Lei, Wei He, Lizhen Cui, Chunyan Miao
https://arxiv.org/abs/2205.14837
The sequential recommendation systems capture users' dynamic behavior patterns to predict their next interaction behaviors. Most existing sequential recommendation methods only exploit the local context information of an individual interaction sequence and learn model parameters solely based on the item prediction loss. Thus, they usually fail to learn appropriate sequence representations. This paper proposes a novel recommendation framework, namely Graph Contrastive Learning for Sequential Recommendation (GCL4SR). Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data. Moreover, GCL4SR uses subgraphs of WITG to augment the representation of each interaction sequence. Two auxiliary learning objectives have also been proposed to maximize the consistency between augmented representations induced by the same interaction sequence on WITG, and minimize the difference between the representations augmented by the global context on WITG and the local representation of the original sequence. Extensive experiments on real-world datasets demonstrate that GCL4SR consistently outperforms state-of-the-art sequential recommendation methods.
7. Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
Guillaume Salha-Galvan
https://arxiv.org/abs/2205.14651
Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as two powerful groups of unsupervised node embedding methods, with various applications to graph-based machine learning problems such as link prediction and community detection. Nonetheless, at the beginning of this Ph.D. project, GAE and VGAE models were also suffering from key limitations, preventing them from being adopted in the industry. In this thesis, we present several contributions to improve these models, with the general aim of facilitating their use to address industrial-level problems involving graph representations. Firstly, we propose two strategies to overcome the scalability issues of previous GAE and VGAE models, permitting to effectively train these models on large graphs with millions of nodes and edges. These strategies leverage graph degeneracy and stochastic subgraph decoding techniques, respectively. Besides, we introduce Gravity-Inspired GAE and VGAE, providing the first extensions of these models for directed graphs, that are ubiquitous in industrial applications. We also consider extensions of GAE and VGAE models for dynamic graphs. Furthermore, we argue that GAE and VGAE models are often unnecessarily complex, and we propose to simplify them by leveraging linear encoders. Lastly, we introduce Modularity-Aware GAE and VGAE to improve community detection on graphs, while jointly preserving good performances on link prediction. In the last part of this thesis, we evaluate our methods on several graphs extracted from the music streaming service Deezer. We put the emphasis on graph-based music recommendation problems. In particular, we show that our methods can improve the detection of communities of similar musical items to recommend to users, that they can effectively rank similar artists in a cold start setting, and that they permit modeling the music genre perception across cultures.
8. Deep Deconfounded Content-based Tag Recommendation for UGC with Causal Intervention
Yaochen Zhu, Xubin Ren, Jing Yi, Zhenzhong Chen
https://arxiv.org/abs/2205.14380
Traditional content-based tag recommender systems directly learn the association between user-generated content (UGC) and tags based on collected UGC-tag pairs. However, since a UGC uploader simultaneously creates the UGC and selects the corresponding tags, her personal preference inevitably biases the tag selections, which prevents these recommenders from learning the causal influence of UGCs' content features on tags. In this paper, we propose a deep deconfounded content-based tag recommender system, namely, DecTag, to address the above issues. We first establish a causal graph to represent the relations among uploader, UGC, and tag, where the uploaders are identified as confounders that spuriously correlate UGC and tag selections. Specifically, to eliminate the confounding bias, causal intervention is conducted on the UGC node in the graph via backdoor adjustment, where uploaders' influence on tags leaked through backdoor paths can be eliminated for causal effect estimation. Observing that adjusting the causal graph with do-calculus requires integrating the entire uploader space, which is infeasible, we design a novel Monte Carlo (MC)-based estimator with bootstrap, which can achieve asymptotic unbiasedness provided that uploaders for the collected UGCs are i.i.d. samples from the population. In addition, the MC estimator has the intuition of substituting the biased uploaders with a hypothetical random uploader from the population in the training phase, where deconfounding can be achieved in an interpretable manner. Finally, we establish a YT-8M-Causal dataset based on the widely used YouTube-8M dataset with causal intervention and propose an evaluation strategy accordingly to unbiasedly evaluate causal tag recommenders. Extensive experiments show that DecTag is more robust to confounding bias than state-of-the-art causal recommenders.
9. RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation
Yijun Tian, Chuxu Zhang, Zhichun Guo, Chao Huang, Ronald Metoyer, Nitesh V. Chawla
https://arxiv.org/abs/2205.14005
Recipe recommendation systems play an essential role in helping people decide what to eat. Existing recipe recommendation systems typically focused on content-based or collaborative filtering approaches, ignoring the higher-order collaborative signal such as relational structure information among users, recipes and food items. In this paper, we formalize the problem of recipe recommendation with graphs to incorporate the collaborative signal into recipe recommendation through graph modeling. In particular, we first present URI-Graph, a new and large-scale user-recipe-ingredient graph. We then propose RecipeRec, a novel heterogeneous graph learning model for recipe recommendation. The proposed model can capture recipe content and collaborative signal through a heterogeneous graph neural network with hierarchical attention and an ingredient set transformer. We also introduce a graph contrastive augmentation strategy to extract informative graph knowledge in a self-supervised manner. Finally, we design a joint objective function of recommendation and contrastive learning to optimize the model. Extensive experiments demonstrate that RecipeRec outperforms state-of-the-art methods for recipe recommendation. Dataset and codes are available at
10. Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder
Xu Zhao, Yi Ren, Ying Du, Shenzheng Zhang, Nian Wang
https://arxiv.org/abs/2205.13795
Embedding & MLP has become a paradigm for modern large-scale recommendation system. However, this paradigm suffers from the cold-start problem which will seriously compromise the ecological health of recommendation systems. This paper attempts to tackle the item cold-start problem by generating enhanced warmed-up ID embeddings for cold items with historical data and limited interaction records. From the aspect of industrial practice, we mainly focus on the following three points of item cold-start: 1) How to conduct cold-start without additional data requirements and make strategy easy to be deployed in online recommendation scenarios. 2) How to leverage both historical records and constantly emerging interaction data of new items. 3) How to model the relationship between item ID and side information stably from interaction data. To address these problems, we propose a model-agnostic Conditional Variational Autoencoder based Recommendation(CVAR) framework with some advantages including compatibility on various backbones, no extra requirements for data, utilization of both historical data and recent emerging interactions. CVAR uses latent variables to learn a distribution over item side information and generates desirable item ID embeddings using a conditional decoder. The proposed method is evaluated by extensive offline experiments on public datasets and online A/B tests on Tencent News recommendation platform, which further illustrate the advantages and robustness of CVAR.
11. Fairness in Recommendation: A Survey
Yunqi Li, Hanxiong Chen, Shuyuan Xu, Yingqiang Ge, Juntao Tan, Shuchang Liu, Yongfeng Zhang
https://arxiv.org/abs/2205.13619
As one of the most pervasive applications of machine learning, recommender systems are playing an important role on assisting human decision making. The satisfaction of users and the interests of platforms are closely related to the quality of the generated recommendation results. However, as a highly data-driven system, recommender system could be affected by data or algorithmic bias and thus generate unfair results, which could weaken the reliance of the systems. As a result, it is crucial to address the potential unfairness problems in recommendation settings. Recently, there has been growing attention on fairness considerations in recommender systems with more and more literature on approaches to promote fairness in recommendation. However, the studies are rather fragmented and lack a systematic organization, thus making it difficult to penetrate for new researchers to the domain. This motivates us to provide a systematic survey of existing works on fairness in recommendation. This survey focuses on the foundations for fairness in recommendation literature. It first presents a brief introduction about fairness in basic machine learning tasks such as classification and ranking in order to provide a general overview of fairness research, as well as introduce the more complex situations and challenges that need to be considered when studying fairness in recommender systems. After that, the survey will introduce fairness in recommendation with a focus on the taxonomies of current fairness definitions, the typical techniques for improving fairness, as well as the datasets for fairness studies in recommendation. The survey also talks about the challenges and opportunities in fairness research with the hope of promoting the fair recommendation research area and beyond.
12. Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems
Jia-Qi Yang, De-Chuan Zhan
https://arxiv.org/abs/2206.00407
Predicting conversion rate (e.g., the probability that a user will purchase an item) is a fundamental problem in machine learning based recommender systems. However, accurate conversion labels are revealed after a long delay, which harms the timeliness of recommender systems. Previous literature concentrates on utilizing early conversions to mitigate such a delayed feedback problem. In this paper, we show that post-click user behaviors are also informative to conversion rate prediction and can be used to improve timeliness. We propose a generalized delayed feedback model (GDFM) that unifies both post-click behaviors and early conversions as stochastic post-click information, which could be utilized to train GDFM in a streaming manner efficiently. Based on GDFM, we further establish a novel perspective that the performance gap introduced by delayed feedback can be attributed to a temporal gap and a sampling gap. Inspired by our analysis, we propose to measure the quality of post-click information with a combination of temporal distance and sample complexity. The training objective is re-weighted accordingly to highlight informative and timely signals. We validate our analysis on public datasets, and experimental performance confirms the effectiveness of our method.
13. Fairness in the First Stage of Two-Stage Recommender Systems
Lequn Wang, Thorsten Joachims
https://arxiv.org/abs/2205.15436
Many large-scale recommender systems consist of two stages, where the first stage focuses on efficiently generating a small subset of promising candidates from a huge pool of items for the second-stage model to curate final recommendations from. In this paper, we investigate how to ensure group fairness to the items in this two-stage paradigm. In particular, we find that existing first-stage recommenders might select an irrecoverably unfair set of candidates such that there is no hope for the second-stage recommender to deliver fair recommendations. To this end, we propose two threshold-policy selection rules that, given any relevance model of queries and items and a point-wise lower confidence bound on the expected number of relevant items for each policy, find near-optimal sets of candidates that contain enough relevant items in expectation from each group of items. To instantiate the rules, we demonstrate how to derive such confidence bounds from potentially partial and biased user feedback data, which are abundant in many large-scale recommender systems. In addition, we provide both finite-sample and asymptotic analysis of how close the two threshold selection rules are to the optimal thresholds. Beyond this theoretical analysis, we show empirically that these two rules can consistently select enough relevant items from each group while minimizing the size of the candidate sets for a wide range of settings.
14. A Personalized Recommender System for Pervasive Social Networks
Valerio Arnaboldi, Mattia G. Campana, Franca Delmastro, Elena Pagani
https://arxiv.org/abs/2205.15063
The current availability of interconnected portable devices, and the advent of the Web 2.0, raise the problem of supporting anywhere and anytime access to a huge amount of content, generated and shared by mobile users. In this work we propose a novel framework for pervasive social networks, called Pervasive PLIERS (pPLIERS), able to discover and select, in a highly personalized way, contents of interest for single mobile users. pPLIERS exploits the recently proposed PLIERS tag based recommender system as context a reasoning tool able to adapt recommendations to heterogeneous interest profiles of different users. pPLIERS effectively operates also when limited knowledge about the network is maintained. It is implemented in a completely decentralized environment, in which new contents are continuously generated and diffused through the network, and it relies only on the exchange of single nodes knowledge during proximity contacts and through device to device communications. We evaluated pPLIERS by simulating its behaviour in three different scenarios: a big event (Expo 2015), a conference venue (ACM KDD 2015), and a working day in the city of Helsinki. For each scenario, we used real or synthetic mobility traces and we extracted real datasets from Twitter interactions to characterise the generation and sharing of user contents.
15. Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever
Jin Chen, Defu Lian, Yucheng Li, Baoyun Wang, Kai Zheng, Enhong Chen
https://arxiv.org/abs/2205.14859
Recommender retrievers aim to rapidly retrieve a fraction of items from the entire item corpus when a user query requests, with the representative two-tower model trained with the log softmax loss. For efficiently training recommender retrievers on modern hardwares, inbatch sampling, where the items in the mini-batch are shared as negatives to estimate the softmax function, has attained growing interest. However, existing inbatch sampling based strategies just correct the sampling bias of inbatch items with item frequency, being unable to distinguish the user queries within the mini-batch and still incurring significant bias from the softmax. In this paper, we propose a Cache-Augmented Inbatch Importance Resampling (XIR) for training recommender retrievers, which not only offers different negatives to user queries with inbatch items, but also adaptively achieves a more accurate estimation of the softmax distribution. Specifically, XIR resamples items for the given mini-batch training pairs based on certain probabilities, where a cache with more frequently sampled items is adopted to augment the candidate item set, with the purpose of reusing the historical informative samples. XIR enables to sample query-dependent negatives based on inbatch items and to capture dynamic changes of model training, which leads to a better approximation of the softmax and further contributes to better convergence. Finally, we conduct experiments to validate the superior performance of the proposed XIR compared with competitive approaches.
16. Sequential Nature of Recommender Systems Disrupts the Evaluation Process
Ali Shirali
https://arxiv.org/abs/2205.13681
Datasets are often generated in a sequential manner, where the previous samples and intermediate decisions or interventions affect subsequent samples. This is especially prominent in cases where there are significant human-AI interactions, such as in recommender systems. To characterize the importance of this relationship across samples, we propose to use adversarial attacks on popular evaluation processes. We present sequence-aware boosting attacks and provide a lower bound on the amount of extra information that can be exploited from a confidential test set solely based on the order of the observed data. We use real and synthetic data to test our methods and show that the evaluation process on the MovieLense-100k dataset can be affected by which is important when considering the close competition. Codes are publicly available.
推荐阅读
SIGIR2022 | 基于Prompt的用户自选公平性推荐算法