Cross-domain recommendation (CDR) offers an effective strategy for improving recommendation quality in a target domain by leveraging auxiliary signals from source domains. Nonetheless, emerging evidence shows that CDR can inadvertently heighten group-level unfairness. In this work, we conduct a comprehensive theoretical and empirical analysis to uncover why these fairness issues arise. Specifically, we identify two key challenges: (i) Cross-Domain Disparity Transfer, wherein existing group-level disparities in the source domain are systematically propagated to the target domain; and (ii) Unfairness from Cross-Domain Information Gain, where the benefits derived from cross-domain knowledge are unevenly allocated among distinct groups.

Representation learning is essential for deep-neural-network-based recommender systems to capture user preferences and item features within fixed-dimensional user and item vectors. Unlike existing representation learning methods that either treat each user preference and item feature uniformly or categorize them into discrete clusters, we argue that in the real world, user preferences and item features are naturally expressed and organized in a hierarchical manner, leading to a new direction for representation learning. In this article, we introduce a novel matryoshka representation learning method for recommendation (MRL4Rec) , by which we restructure user and item vectors into matryoshka representations with nested vector spaces to explicitly represent user preferences and item features at different hierarchical layers. We theoretically establish that training with the same triplets for each sliced vector cannot guarantee representation learning with hierarchical structures. Subsequently, we propose the layer- and hardness-adaptive negative sampling (LHANS) mechanism to construct training triplets, which further ensures the soundness of learned matryoshka representations in capturing hierarchical user preferences and item features. The experiments demonstrate that MRL4Rec can consistently and substantially outperform a number of state-of-the-art competitors on several real-life datasets. Our code is publicly available at https://github.com/Riwei-HEU/MRL .

Recommender systems have been popularly employed to address information overload problems for users, for which unfairness issues are essential to be mitigated. Current user-side fairness studies in recommendations aim to ensure the independence of users’ sensitive attributes in terms of outcome or process . Specifically, the former emphasizes the outcome metric equity across user groups based on sensitive attributes, for which regularization has been proposed as a typical approach to reducing the recommendation imbalance among them. The latter process fairness focuses on independence between sensitive attributes and recommendations in the process, for which adversarial learning has been popularly adopted to remove sensitive information from user representation for individual users. However, little work has investigated the effects of these methods on balancing both group-level outcome fairness and individual-level process fairness in a particular scenario. Moreover, existing experiments have primarily been performed on one type of user attributes, e.g., behavioral attributes or demographic attributes, but neglected other possible sensitive attributes such as psychological attributes. In this article, we have investigated both outcome and process fairness performance of regularization and adversarial learning methods over multiple types of sensitive attributes, including behavioral (e.g., activity level), demographic (e.g., gender, age), and psychological attributes (e.g., big-five personality, curiosity). The experiments on four datasets show that unfairness can exist in different forms for different types of sensitive attributes, and relative to the regularization-based method, adversarial learning owns a higher potential to achieve a balance between outcome and process user-side fairness in recommendations. Our source code is available at https://github.com/WeixinChen98/OtPrFairness-MultiAttr .

Cross-domain recommendation (CDR) methods predominantly leverage overlapping users to transfer knowledge from a source domain to a target domain.However, through empirical studies, we uncover a critical bias inherent in these approaches: while overlapping users experience significant enhancements in recommendation quality, non-overlapping users benefit minimally and even face performance degradation.This unfairness may erode user trust, and, consequently, negatively impact business engagement and revenue.To address this issue, we propose a novel solution that generates virtual source-domain users for non-overlapping target-domain users.Our method utilizes a dual attention mechanism to discern similarities between overlapping and non-overlapping users, thereby synthesizing realistic virtual user embeddings.We further introduce a limiter component that ensures the generated virtual users align with real-data distributions while preserving each user's unique characteristics.Notably, our method is model-agnostic and can be seamlessly integrated into any CDR model.Comprehensive experiments conducted on three public datasets with five CDR baselines demonstrate that our method effectively mitigates the CDR nonoverlapping user bias, without loss of overall accuracy.Our code is publicly available at https://github.com/WeixinChen98/VUG.

Recently, multimodal recommendations (MMRs) have gained increasing attention for alleviating the data sparsity problem of traditional recommender systems by incorporating modality-based representations. Although MMR exhibits notable improvement in recommendation accuracy, we empirically validate that an increase in the quantity or variety of modalities leads to a higher degree of users’ sensitive information leakage due to entangled causal relationships, risking fair representation learning. On the other hand, existing fair representation learning approaches are mostly based on the assumption that sensitive information is solely leaked from users’ interaction data and do not explicitly model the causal relationships introduced by multimodal data, which limits their applicability in multimodal scenarios. To address this limitation, we propose a novel fair multimodal recommendation approach (dubbed FMMRec) through causality-inspired fairness-oriented modal disentanglement and relation-aware fairness learning. Particularly, we disentangle biased and filtered modal embeddings inspired by causal inference techniques, enabling the mining of modality-based unfair and fair user–user relations, thereby enhancing the fairness and informativeness of user representations. By addressing the causal effects of sensitive attributes on user preferences, our approach aims to achieve counterfactual fairness in MMRs. Experiments on two public datasets demonstrate the superiority of our FMMRec relative to the state-of-the-art baselines. Our source code is available at https://github.com/WeixinChen98/FMMRec .

Heterogeneous sequential recommendation (HSR) is a very important recommendation problem, which aims to predict a user’s next interacted item under a target behavior type (e.g., purchase in e-commerce sites) based on his/her historical interactions with different behaviors. Though existing sequential methods have achieved advanced performance by considering the varied impacts of interactions with sequential information, a large body of them still have two major shortcomings. Firstly, they usually model different behaviors separately without considering the correlations between them. The transitions from item to item under diverse behaviors indicate some users’ potential behavior manner. Secondly, though the behavior information contains a user’s fine-grained interests, the insufficient consideration of the local context information limits them from well understanding user intentions. Utilizing the adjacent interactions to better understand a user’s behavior could improve the certainty of prediction. To address these two issues, we propose a novel solution utilizing global and personalized graphs for HSR (GPG4HSR) to learn behavior transitions and user intentions. Specifically, our GPG4HSR consists of two graphs, i.e., a global graph to capture the transitions between different behaviors, and a personalized graph to model items with behaviors by further considering the distinct user intentions of the adjacent contextually relevant nodes. Extensive experiments on four public datasets with the state-of-the-art baselines demonstrate the effectiveness and general applicability of our method GPG4HSR.