Joint Identifiability of Cross-Domain Recommendation via Hierarchical Subspace Disentanglement
Macquarie University（麦考瑞大学）；The University of New South Wales（新南威尔士大学）；Northwestern Polytechnical University（西北工业大学）；CSIRO’s Data 61（联邦科学与工业研究组织数据61部门）
跨域推荐（CDR）旨在实现跨领域的有效知识迁移。现有工作要么依赖表示对齐，要么依赖转换桥接，但它们在区分域共享潜在因子与域特定潜在因子方面存在困难。具体而言，虽然CDR将用户表示描述为两个域上的联合分布，但这些方法未能考虑其联合可识别性，因为它们主要关注特定域内的边际分布。这种不足可能会忽视两个域之间的条件关系及其对潜在因子解耦的贡献，从而在域间相关性较弱时导致负迁移。在本研究中，我们从因果关系的角度探讨跨域用户表示中应该迁移什么、不应该迁移什么。我们提出了一种层次子空间解耦方法，用于探索跨域联合分布的联合可识别性（Joint IDentifiability），称为HJID，以将域特定行为与域共享因子分离开来。HJID将用户表示组织为多个层次：通用浅层子空间和面向域的深层子空间。我们首先通过最小化初始层激活的最大均值差异（Maximum Mean Discrepancy）来编码浅层子空间中的通用模式。然后，为了剖析面向域的潜在因子如何在更深层激活中被编码，我们构建了一个基于跨域因果关系的数据生成图，该图识别跨域一致成分和域特定成分，并遵循最小变化原则（Minimal Change principle）。这使得HJID能够在保持稳定性的同时发现不同域的独特因子，所有这些都在一个可逆变换的生成框架内进行，从而保证联合可识别性。通过在真实世界数据集上的实验，我们表明HJID在一系列强相关和弱相关的CDR任务上优于SOTA方法。
英文摘要：
Cross-Domain Recommendation (CDR) seeks to enable effective knowledge transfer across domains. Existing works rely on either representation alignment or transformation bridges, but they struggle on identifying domain-shared from domain-specific latent factors. Specifically, while CDR describes user representations as a joint distribution over two domains, these methods fail to account for its joint identifiability as they primarily fixate on the marginal distribution within a particular domain. Such a failure may overlook the conditionality between two domains and how it contributes to latent factor disentanglement, leading to negative transfer when domains are weakly correlated. In this study, we explore what should and should not be transferred in cross-domain user representations from a causality perspective. We propose a Hierarchical subspace disentanglement approach to explore the Joint IDentifiability of cross-domain joint distribution, termed HJID, to preserve domain-specific behaviors from domain-shared factors. HJID organizes user representations into layers: generic shallow subspaces and domain-oriented deep subspaces. We first encode the generic pattern in the shallow subspace by minimizing the Maximum Mean Discrepancy of initial layer activation. Then, to dissect how domain-oriented latent factors are encoded in deeper layers activation, we construct a cross-domain causality-based data generation graph, which identifies cross-domain consistent and domain-specific components, adhering to the Minimal Change principle. This allows HJID to maintain stability whilst discovering unique factors for different domains, all within a generative framework of invertible transformations that guarantee the joint identifiability. With experiments on real-world datasets, we show that HJID outperforms SOTA methods on a range of strongly and weakly correlated CDR tasks.
University of Technology Sydney（悉尼科技大学）；Curtin University（科廷大学）；University of New South Wales（新南威尔士大学）；Tsinghua University（清华大学）
Traditional recommendation models trained on observational interaction data have generated large impacts in a wide range of applications, it faces bias problems that cover users' true intent and thus deteriorate the recommendation effectiveness. Existing methods tracks this problem as eliminating bias for the robust recommendation, e.g., by re-weighting training samples or learning disentangled representation. The disentangled representation methods as the state-of-the-art eliminate bias through revealing cause-effect of the bias generation. However, how to design the semantics-aware and unbia…
Contrastive Learning Method for Sequential Recommendation based on Multi-Intention Disentanglement
College of Computer, Qinghai Normal University（青海师范大学计算机学院）；The State Key Laboratory of Tibetan Intelligent Information Processing and Application（藏语智能信息处理及应用国家重点实验室）；Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province（青海省藏文信息处理与机器翻译重点实验室）；Key Laboratory of Tibetan Information Processing, Ministry of Education（藏文信息处理教育部重点实验室）
Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context Scenarios
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Alibaba Group（阿里巴巴集团）；The University of Melbourne（墨尔本大学）；Beijing Institute of Biotechnology（北京生物技术研究院）
DisenReason: Behavior Disentanglement and Latent Reasoning for Shared-Account Sequential Recommendation
School of Big Data and Software Engineering（大数据与软件工程学院）；College of Computer Science and Engineering（计算机科学与工程学院）；School of Computing and Mathematical Sciences（计算与数学科学学院）；Department of Plastic Surgery（整形外科部门）；College of Environmental Science and Engineering（环境科学与工程学院）
Arizona State University（亚利桑那州立大学）；City University of Hong Kong（香港城市大学）
Recommender systems aim to recommend new items to users by learning user and item representations. In practice, these representations are highly entangled as they consist of information about multiple factors, including user's interests, item attributes along with confounding factors such as user conformity, and item popularity. Considering these entangled representations for inferring user preference may lead to biased recommendations (e.g., when the recommender model recommends popular items even if they do not align with the user's interests). Recent research proposes to debias by modeling …
In this paper, we consider controllability as a means to satisfy dynamic preferences of users, enabling them to control recommendations such that their current preference is met. While deep models have shown improved performance for collaborative filtering, they are generally not amenable to fine grained control by a user, leading to the development of methods like deep language critiquing. We propose an alternate view, where instead of keyphrase based critiques, a user is provided 'knobs' in a disentangled latent space, with each knob corresponding to an item aspect. Disentanglement here refe…
One key property in recommender systems is the long-tail distribution in user-item interactions where most items only have few user feedback. Improving the recommendation of tail items can promote novelty and bring positive effects to both users and providers, and thus is a desirable property of recommender systems. Current novel recommendation studies over-emphasize the importance of tail items without differentiating the degree of users' intent on popularity and often incur a sharp decline of accuracy. Moreover, none of existing methods has ever taken the extreme case of tail items, i.e., co…
Enhancing POI Recommendation through Global Graph Disentanglement with POI Weighted Module
Department of Electrical Engineering, National Cheng Kung University（国立成功大学电子工程系）；USC Information Sciences Institute（美国南加洲大学信息科学研究所）；Department of Electrical Engineering, Academy of Innovative Semiconductor and Sustainable Manufacturing, National Cheng Kung University（国立成功大学电子工程系、创新半导体与可持续制造学院）
User behavior data in recommender systems are driven by the complex interactions of many latent factors behind the users' decision making processes. The factors are highly entangled, and may range from high-level ones that govern user intentions, to low-level ones that characterize a user's preference when executing an intention. Learning representations that uncover and disentangle these latent factors can bring enhanced robustness, interpretability, and controllability. However, learning such disentangled representations from user behavior is challenging, and remains largely neglected by the…
Relevant recommendation is a special recommendation scenario which provides relevant items when users express interests on one target item (e.g., click, like and purchase). Besides considering the relevance between recommendations and trigger item, the recommendations should also be diversified to avoid information cocoons. However, existing diversified recommendation methods mainly focus on item-level diversity which is insufficient when the recommended items are all relevant to the target item. Moreover, redundant or noisy item features might affect the performance of simple feature-aware re…
Causal Structure Representation Learning of Confounders in Latent Space for Recommendation
MIC Lab, College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院MIC实验室）；Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications（北京邮电大学可信分布式计算与服务重点实验室）；Institute of Artificial Intelligence, Beihang University and Zhongguancun Laboratory（北航人工智能研究院和中关村实验室）
DISCO: A Hierarchical Disentangled Cognitive Diagnosis Framework for Interpretable Job Recommendation
School of Artificial Intelligence, Anhui University（安徽大学人工智能学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；Institutes of Physical Science and Information Technology, Anhui University（安徽大学物理与信息技术研究院）；School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）
