KDD22 | 推荐系统论文集锦(附pdf下载)
往年KDD推荐系统论文整理可参考：
Research Track Papers
通过对本次接收的论文进行总结发现，从所涉及的研究主题角度来看，此次大会主要聚焦在了推荐系统中的公平性[1]、Bias问题[9,10,12,17,23]、对话推荐系统[8,15]、推荐中的隐私和安全问题[6,9]、推荐系统的特征交叉[3]、可解释推荐系统[13]、捆绑推荐[14]、基于图的推荐系统[2,11,18,19,24]、轻量化推荐模型[24]、点击率预估问题[22,23]、序列推荐模型[7,10,13]等，与去年所关注的主题类似；
从推荐技术的角度来看，包括对于经典协同过滤的改进[20,21]、基于对抗学习的推荐算法[22]、基于元学习的推荐系统[1]、基于强化学习的推荐算法[15,24]、基于提示学习的推荐算法[8]、基于注意力机制的推荐算法[13,17]、基于对比学习的推荐算法[14]、基于Transformer的推荐算法[18,19]等。
[1] Comprehensive Fair Meta-learned Recommender System
[2] Graph-Flashback Network for Next Location Recommendation
[3] Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
[4] Practical Counterfactual Policy Learning for Top-K Recommendations
[5] Addressing Unmeasured Confounder for Recommendation with Sensitivity Analysis
[6] Knowledge-enhanced Black-box Attacks for Recommendations
[7] Towards Universal Sequence Representation Learning for Recommender Systems
[8] Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning
[9] Debiasing Learning for Membership Inference Attacks Against Recommender Systems
[10] Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
[11] User-Event Graph Embedding Learning for Context-Aware Recommendation
[12] Invariant Preference Learning for General Debiasing in Recommendation
[13] PARSRec: Explainable Personalized Attention-fused Recurrent Sequential Recommendation Using Session Partial Actions
[14] CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
[15] Learning Relevant Information in Conversational Search and Recommendation using Deep Reinforcement Learning
[16] MDP2 Forest: A Constrained Continuous Multi-dimensional Policy Optimization Approach for Short-video Recommendation
[17] Counteracting User Attention Bias in Music Streaming Recommendation via Reward Modification
[18] Multi-Behavior Hypergraph-Enhanced Transformer for Next-Item Recommendation
[19] Self-Augmented Hypergraph Transformer for Recommender Systems
[20] Towards Representation Alignment and Uniformity in Collaborative Filtering
[21] HICF: Hyperbolic Informative Collaborative Filtering
[22] Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction
[23] A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Prediction
[24] Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation
[1] Comprehensive Fair Meta-learned Recommender System
Tianxin Wei (University of Illinois Urbana Champaign)*; Jingrui He (University of Illinois at Urbana-Champaign)
https://arxiv.org/abs/2206.04789
In recommender systems, one common challenge is the cold-start problem, where interactions are very limited for fresh users in the systems. To address this challenge, recently, many works introduce the meta-optimization idea into the recommendation scenarios, i.e. learning to learn the user preference by only a few past interaction items. The core idea is to learn global shared meta-initialization parameters for all users and rapidly adapt them into local parameters for each user respectively. They aim at deriving general knowledge across preference learning of various users, so as to rapidly adapt to the future new user with the learned prior and a small amount of training data. However, previous works have shown that recommender systems are generally vulnerable to bias and unfairness. Despite the success of meta-learning at improving the recommendation performance with cold-start, the fairness issues are largely overlooked. In this paper, we propose a comprehensive fair meta-learning framework, named CLOVER, for ensuring the fairness of meta-learned recommendation models. We systematically study three kinds of fairness - individual fairness, counterfactual fairness, and group fairness in the recommender systems, and propose to satisfy all three kinds via a multi-task adversarial learning scheme. Our framework offers a generic training paradigm that is applicable to different meta-learned recommender systems. We demonstrate the effectiveness of CLOVER on the representative meta-learned user preference estimator on three real-world data sets. Empirical results show that CLOVER achieves comprehensive fairness without deteriorating the overall cold-start recommendation performance.
[2] Graph-Flashback Network for Next Location Recommendation
Xuan Rao (University of Electronic Science and Technology of China)*; Lisi Chen (KAUST); Yong Liu (Nanyang Technological University); Shuo Shang (KAUST); Bin Yao (Shanghai Jiao Tong University); Peng Han (KAUST)
[3] Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
Yixin Su (The University of Melbourne)*; Yunxiang Zhao (The University of Melbourne); Sarah Erfani (University of Melbourne); Junhao Gan (University of Melbourne); Rui Zhang (ruizhang.info)
https://arxiv.org/abs/2206.13764
Detecting beneficial feature interactions is essential in recommender systems, and existing approaches achieve this by examining all the possible feature interactions. However, the cost of examining all the possible higher-order feature interactions is prohibitive (exponentially growing with the order increasing). Hence existing approaches only detect limited order (e.g., combinations of up to four features) beneficial feature interactions, which may miss beneficial feature interactions with orders higher than the limitation. In this paper, we propose a hypergraph neural network based model named HIRS. HIRS is the first work that directly generates beneficial feature interactions of arbitrary orders and makes recommendation predictions accordingly. The number of generated feature interactions can be specified to be much smaller than the number of all the possible interactions and hence, our model admits a much lower running time. To achieve an effective algorithm, we exploit three properties of beneficial feature interactions, and propose deep-infomax-based methods to guide the interaction generation. Our experimental results show that HIRS outperforms state-of-the-art algorithms by up to 5% in terms of recommendation accuracy.
[4] Practical Counterfactual Policy Learning for Top-K Recommendations
Yaxu Liu (National Taiwan University)*; Jui-Nan Yen (National Taiwan University); Bowen Yuan (National Taiwan University); Rundong Shi (Meituan); Peng Yan (Meituan); Chih-Jen Lin (National Taiwan University)
[5] Addressing Unmeasured Confounder for Recommendation with Sensitivity Analysis
Sihao Ding (University of Science and Technology of China)*; Peng Wu (Peking University); Fuli Feng (University of Science and Technology of China); Yitong Wang (University of Science and Technology of China); Xiangnan He (University of Science and Technology of China); Yong Liao (University of Sciences and Technology of China); Yongdong Zhang (University of Science and Technology of China)
[6] Knowledge-enhanced Black-box Attacks for Recommendations
Jingfan Chen (Nanjing University)*; Wenqi FAN (The Hong Kong Polytechnic University); Guanghui Zhu (Nanjing University); Xiangyu Zhao (City University of Hong Kong); Chunfeng Yuan (Nanjing University); Qing Li (The Hong Kong Polytechnic University ); Yihua Huang (Nanjing University)
https://arxiv.org/abs/2207.10307
Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles (i.e., a set of items that fake users have interacted with) into a target recommender system to achieve malicious purposes, such as promote or demote a set of target items. Due to the security and privacy concerns, it is more practical to perform adversarial attacks under the black-box setting, where the architecture/parameters and training data of target systems cannot be easily accessed by attackers. However, generating high-quality fake user profiles under black-box setting is rather challenging with limited resources to target systems. To address this challenge, in this work, we introduce a novel strategy by leveraging items' attribute information (i.e., items' knowledge graph), which can be publicly accessible and provide rich auxiliary knowledge to enhance the generation of fake user profiles. More specifically, we propose a knowledge graph-enhanced black-box attacking framework (KGAttack) to effectively learn attacking policies through deep reinforcement learning techniques, in which knowledge graph is seamlessly integrated into hierarchical policy networks to generate fake user profiles for performing adversarial black-box attacks. Comprehensive experiments on various real-world datasets demonstrate the effectiveness of the proposed attacking framework under the black-box setting.
[7] Towards Universal Sequence Representation Learning for Recommender Systems
Yupeng Hou (Renmin University of China)*; Shanlei Mu (Renmin University of China); Wayne Xin Zhao (Renmin University of China); Yaliang Li (Alibaba Group); Bolin Ding (Data Analytics and Intelligence Lab, Alibaba Group); Ji-Rong Wen (Renmin University of China)
https://arxiv.org/abs/2206.05941
In order to develop effective sequential recommenders, a series of sequence representation learning (SRL) methods are proposed to model historical user behaviors. Most existing SRL methods rely on explicit item IDs for developing the sequence models to better capture user preference. Though effective to some extent, these methods are difficult to be transferred to new recommendation scenarios, due to the limitation by explicitly modeling item IDs. To tackle this issue, we present a novel universal sequence representation learning approach, named UniSRec. The proposed approach utilizes the associated description text of items to learn transferable representations across different recommendation scenarios. For learning universal item representations, we design a lightweight item encoding architecture based on parametric whitening and mixture-of-experts enhanced adaptor. For learning universal sequence representations, we introduce two contrastive pre-training tasks by sampling multi-domain negatives. With the pre-trained universal sequence representation model, our approach can be effectively transferred to new recommendation domains or platforms in a parameter-efficient way, under either inductive or transductive settings. Extensive experiments conducted on real-world datasets demonstrate the effectiveness of the proposed approach. Especially, our approach also leads to a performance improvement in a cross-platform setting, showing the strong transferability of the proposed universal SRL method. The code and pre-trained model are available at: https://github.com/RUCAIBox/UniSRec.
[8] Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning
Xiaolei Wang (Renmin University of China); Kun Zhou (Renmin University of China); Ji-Rong Wen (Renmin University of China); Wayne Xin Zhao (Renmin University of China)*
https://arxiv.org/abs/2206.09363
Conversational recommender systems (CRS) aim to proactively elicit user preference and recommend high-quality items through natural language conversations. Typically, a CRS consists of a recommendation module to predict preferred items for users and a conversation module to generate appropriate responses. To develop an effective CRS, it is essential to seamlessly integrate the two modules. Existing works either design semantic alignment strategies, or share knowledge resources and representations between the two modules. However, these approaches still rely on different architectures or techniques to develop the two modules, making it difficult for effective module integration. To address this problem, we propose a unified CRS model named UniCRS based on knowledge-enhanced prompt learning. Our approach unifies the recommendation and conversation subtasks into the prompt learning paradigm, and utilizes knowledge-enhanced prompts based on a fixed pre-trained language model (PLM) to fulfill both subtasks in a unified approach. In the prompt design, we include fused knowledge representations, task-specific soft tokens, and the dialogue context, which can provide sufficient contextual information to adapt the PLM for the CRS task. Besides, for the recommendation subtask, we also incorporate the generated response template as an important part of the prompt, to enhance the information interaction between the two subtasks. Extensive experiments on two public CRS datasets have demonstrated the effectiveness of our approach. The code is available at: https://github.com/RUCAIBox/UniCRS.
[9] Debiasing Learning for Membership Inference Attacks Against Recommender Systems
Zihan Wang (Shandong University)*; Na Huang (Shandong University); Fei Sun (Alibaba Group); Pengjie Ren (Shandong University); Zhumin Chen (Shandong University); Hengliang Luo (Meituan); Maarten de Rijke (University of Amsterdam); Zhaochun Ren (Shandong University)
https://arxiv.org/abs/2206.12401
Learned recommender systems may inadvertently leak information about their training data, leading to privacy violations. We investigate privacy threats faced by recommender systems through the lens of membership inference. In such attacks, an adversary aims to infer whether a user's data is used to train the target recommender. To achieve this, previous work has used a shadow recommender to derive training data for the attack model, and then predicts the membership by calculating difference vectors between users' historical interactions and recommended items. State-of-the-art methods face two challenging problems: (1) training data for the attack model is biased due to the gap between shadow and target recommenders, and (2) hidden states in recommenders are not observational, resulting in inaccurate estimations of difference vectors. To address the above limitations, we propose a Debiasing Learning for Membership Inference Attacks against recommender systems (DL-MIA) framework that has four main components: (1) a difference vector generator, (2) a disentangled encoder, (3) a weight estimator, and (4) an attack model. To mitigate the gap between recommenders, a variational auto-encoder (VAE) based disentangled encoder is devised to identify recommender invariant and specific features. To reduce the estimation bias, we design a weight estimator, assigning a truth-level score for each difference vector to indicate estimation accuracy. We evaluate DL-MIA against both general recommenders and sequential recommenders on three real-world datasets. Experimental results show that DL-MIA effectively alleviates training and estimation biases simultaneously, and achieves state-of-the-art attack performance.
[10] Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
Khalil Damak (University of Louisville)*; Sami Khenissi (University of Louisville); Olfa Nasraoui (university of Louisville)
[11] User-Event Graph Embedding Learning for Context-Aware Recommendation
Dugang Liu (Shenzhen University)*; Mingkai He (Shenzhen University); Jinwei Luo (Shenzhen University); Jiangxu Lin (Southeast University); Meng Wang (Southeast University); Xiaolian Zhang (Huawei 2012 lab); Weike Pan (Shenzhen University); Zhong Ming (Shenzhen University)
[12] Invariant Preference Learning for General Debiasing in Recommendation
Zimu Wang (Tsinghua University)*; Yue He (Tsinghua University); Jiashuo Liu (Tsinghua University); Wenchao Zou (Siemens China); Philip S Yu (UNIVERSITY OF ILLINOIS AT CHICAGO); Peng Cui (Tsinghua University)
[13] PARSRec: Explainable Personalized Attention-fused Recurrent Sequential Recommendation Using Session Partial Actions
Ehsan Gholami (University of California, Davis)*; Mohammad Motamedi (University of California, Davis); Ashwin Aravindakshan (University of California-Davis)
[14] CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
Yunshan Ma (National University of Singapore )*; Yingzhi He (National University of Singapore); An Zhang (National University of Singapore); Xiang Wang (National University of Singapore); Tat-Seng Chua (National university of Singapore)
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.
[15] Learning Relevant Information in Conversational Search and Recommendation using Deep Reinforcement Learning
Ali Montazeralghaem (University of Massachusetts Amherst)*; James Allan (University of Massachusetts Amherst)
[16] MDP2 Forest: A Constrained Continuous Multi-dimensional Policy Optimization Approach for Short-video Recommendation
Sizhe Yu (Shanghai University of Finance and Economics)*; Ziyi Liu (School of Statistics, Renmin University of China); Shixiang Wan (Tencent); zero Jay (Tencent); Zang Li (DiDi AI Labs, Didi Chuxing); Fan Zhou (Shanghai University of Finance and Economics
[17] Counteracting User Attention Bias in Music Streaming Recommendation via Reward Modification
Xiao Zhang (Renmin University of China ); Sunhao Dai (Renmin University of China); Jun Xu (Renmin University of China)*; Zhenhua Dong (Huawei Noah's Ark Lab); Quanyu Dai (Huawei Noah's Ark Lab); Ji-Rong Wen (Renmin University of China)
[18] Multi-Behavior Hypergraph-Enhanced Transformer for Next-Item Recommendation
Yuhao Yang (Wuhan University); Chao Huang (University of Hong Kong)*; Lianghao Xia (South China University of Technology); Yuxuan Liang (National University of Singapore); Yanwei Yu (Ocean University of China); Chenliang Li (Wuhan University)
[19] Self-Augmented Hypergraph Transformer for Recommender Systems
Lianghao Xia (South China University of Technology); Chao Huang (University of Hong Kong)*; Chuxu Zhang (Brandeis University)
[20] Towards Representation Alignment and Uniformity in Collaborative Filtering
Chenyang Wang (Tsinghua University)*; Yuanqing Yu (Tsinghua University); Weizhi Ma (Tsinghua University); Min Zhang (Tsinghua University); Chong Chen (Tsinghua University); Yiqun LIU (Tsinghua University); Shaoping Ma (Tsinghua University)
https://arxiv.org/abs/2206.12811
Collaborative filtering (CF) plays a critical role in the development of recommender systems. Most CF methods utilize an encoder to embed users and items into the same representation space, and the Bayesian personalized ranking (BPR) loss is usually adopted as the objective function to learn informative encoders. Existing studies mainly focus on designing more powerful encoders (e.g., graph neural network) to learn better representations. However, few efforts have been devoted to investigating the desired properties of representations in CF, which is important to understand the rationale of existing CF methods and design new learning objectives. In this paper, we measure the representation quality in CF from the perspective of alignment and uniformity on the hypersphere. We first theoretically reveal the connection between the BPR loss and these two properties. Then, we empirically analyze the learning dynamics of typical CF methods in terms of quantified alignment and uniformity, which shows that better alignment or uniformity both contribute to higher recommendation performance. Based on the analyses results, a learning objective that directly optimizes these two properties is proposed, named DirectAU. We conduct extensive experiments on three public datasets, and the proposed learning framework with a simple matrix factorization model leads to significant performance improvements compared to state-of-the-art CF methods. Our implementations are publicly available at https://github.com/THUwangcy/DirectAU.
[21] HICF: Hyperbolic Informative Collaborative Filtering
Menglin Yang (The Chinese University of Hong Kong)*; Li Zhihao (Harbin Institute of Technology, Shenzhen); Min Zhou (Huawei Technologies co. ltd); Jiahong Liu (Harbin Institute of Technology(Shenzhen)); Irwin King (The Chinese University of Hong Kong)
https://arxiv.org/abs/2207.09051
Considering the prevalence of the power-law distribution in user-item networks, hyperbolic space has attracted considerable attention and achieved impressive performance in the recommender system recently. The advantage of hyperbolic recommendation lies in that its exponentially increasing capacity is well-suited to describe the power-law distributed user-item network whereas the Euclidean equivalent is deficient. Nonetheless, it remains unclear which kinds of items can be effectively recommended by the hyperbolic model and which cannot. To address the above concerns, we take the most basic recommendation technique, collaborative filtering, as a medium, to investigate the behaviors of hyperbolic and Euclidean recommendation models. The results reveal that (1) tail items get more emphasis in hyperbolic space than that in Euclidean space, but there is still ample room for improvement; (2) head items receive modest attention in hyperbolic space, which could be considerably improved; (3) and nonetheless, the hyperbolic models show more competitive performance than Euclidean models. Driven by the above observations, we design a novel learning method, named hyperbolic informative collaborative filtering (HICF), aiming to compensate for the recommendation effectiveness of the head item while at the same time improving the performance of the tail item. The main idea is to adapt the hyperbolic margin ranking learning, making its pull and push procedure geometric-aware, and providing informative guidance for the learning of both head and tail items. Extensive experiments back up the analytic findings and also show the effectiveness of the proposed method. The work is valuable for personalized recommendations since it reveals that the hyperbolic space facilitates modeling the tail item, which often represents user-customized preferences or new products.
[22] Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction
Kailun Wu (Alibaba Group)*; Weijie Bian (Alibaba Group); Zhangming Chan (Alibaba Group); Lejian Ren (Alibaba Group); SHIMING XIANG (Chinese Academy of Sciences, China); Shu-Guang Han (Alibaba Group); Hongbo Deng (Alibaba Group); Bo Zheng (Alibaba Group)
https://arxiv.org/abs/2112.11136
Exploration-Exploitation (E{&}E) algorithms are commonly adopted to deal with the feedback-loop issue in large-scale online recommender systems. Most of existing studies believe that high uncertainty can be a good indicator of potential reward, and thus primarily focus on the estimation of model uncertainty. We argue that such an approach overlooks the subsequent effect of exploration on model training. From the perspective of online learning, the adoption of an exploration strategy would also affect the collecting of training data, which further influences model learning. To understand the interaction between exploration and training, we design a Pseudo-Exploration module that simulates the model updating process after a certain item is explored and the corresponding feedback is received. We further show that such a process is equivalent to adding an adversarial perturbation to the model input, and thereby name our proposed approach as an the Adversarial Gradient Driven Exploration (AGE). For production deployment, we propose a dynamic gating unit to pre-determine the utility of an exploration. This enables us to utilize the limited amount of resources for exploration, and avoid wasting pageview resources on ineffective exploration. The effectiveness of AGE was firstly examined through an extensive number of ablation studies on an academic dataset. Meanwhile, AGE has also been deployed to one of the world-leading display advertising platforms, and we observe significant improvements on various top-line evaluation metrics.
[23] A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Prediction
Quanyu Dai (Huawei Noah's Ark Lab)*; Peng Wu (Peking University); Haoxuan Li (Peking University); Zhenhua Dong (Huawei Noah's Ark Lab); Xiao-Hua Zhou (Peking University); Rui Zhang (ruizhang.info); Rui zhang (Huawei Technologies Co., Ltd.); Jie Sun (Theory Lab, Huawei Hong Kong Research Center)
[24] Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation
Yankai Chen (The Chinese University of Hong Kong)*; Huifeng Guo (Huawei Noah's Ark Lab); Yingxue Zhang (Huawei Technologies Canada); Chen Ma (City University of Hong Kong); Ruiming Tang (Huawei Noah's Ark Lab); Jingjie Li (Huawei Noah's Ark Lab); Irwin King (The Chinese University of Hong Kong)
https://arxiv.org/abs/2206.02115
Learning vectorized embeddings is at the core of various recommender systems for user-item matching. To perform efficient online inference, representation quantization, aiming to embed the latent features by a compact sequence of discrete numbers, recently shows the promising potentiality in optimizing both memory and computation overheads. However, existing work merely focuses on numerical quantization whilst ignoring the concomitant information loss issue, which, consequently, leads to conspicuous performance degradation. In this paper, we propose a novel quantization framework to learn Binarized Graph Representations for Top-K Recommendation (BiGeaR). BiGeaR introduces multi-faceted quantization reinforcement at the pre-, mid-, and post-stage of binarized representation learning, which substantially retains the representation informativeness against embedding binarization. In addition to saving the memory footprint, BiGeaR further develops solid online inference acceleration with bitwise operations, providing alternative flexibility for the realistic deployment. The empirical results over five large real-world benchmarks show that BiGeaR achieves about 22%~40% performance improvement over the state-of-the-art quantization-based recommender system, and recovers about 95%~102% of the performance capability of the best full-precision counterpart with over 8x time and space reduction.
相关内容
微信扫码咨询专知VIP会员