Multibehavior recommender systems are proficient at constructing precise representations of users and items by leveraging a variety of interaction behaviors, e.g., click, add-to-cart, and purchase. However, they are still facing the following challenges: 1) there are a large number of spurious correlations existing in auxiliary behaviors (i.e., noise unrelated to the target behavior preference); and 2) spurious correlations may be unintentionally introduced and amplified during the representation learning process in traditional multibehavior recommenders. Hence, we propose a novel framework-disentangling spurious correlations (DISC) to measure and disentangle the spurious correlations of the multibehavior recommendation. In particular, to precisely identify the intent representations for each user, we devise a cross-behavior self-attention layer incorporating lightweight graph convolution networks to encode graph nodes under specific behaviors, thereby enabling the model to supervise the subsequent spurious correlation disentanglement. Subsequently, to disentangle the spurious correlations among multiple behaviors, we design a time-sensitive Jaccard coefficient to dynamically measure the users’ spurious correlations. Building on this, we propose a dual mutual information (MI) bound structure to disentangle spurious correlations existing in auxiliary behaviors and transfer genuine correlated semantic information to the target behavior, thus alleviating the data sparsity. Extensive experiments on three real-world datasets demonstrate the consistent improvements obtained by DISC over 11 state-of-the-art baselines by effectively disentangling the spurious correlations.

In e-commerce, recommender systems help users find suitable products by leveraging diverse behaviors, e.g., view, cart and buy. In recent years, multi-behavior recommender systems have made strides by integrating auxiliary behaviors with purchase histories to deliver high-quality recommendations. However, most existing methods often fail to identify spurious correlation intents within auxiliary behaviors that conflict with users' target intents. Indiscriminately incorporating such correlations into the prediction of target intents may lead to performance degradation. Toward this end, we propose a Multi-Behavior Intent Disentanglement (MBID) framework based on Information Bottleneck (IB) principle, which focuses on disentangling spurious correlation intents in multi-behavior recommendations. In particular, we design a projection-based intent extraction method to decompose the genuine and spurious correlation intents in auxiliary behaviors. Building on this, we conceive an IB-based multi-intent learning task to disentangle the spurious correlation intents and transfer the genuine correlation intents from auxiliary behaviors into the target behavior, yielding high-quality target intent representations. Experiments on three real-world datasets show MBID significantly outperforms the state-of-the-art baselines by effectively disentangling the spurious correlation intents.

Graph Convolutional Networks (GCNs) have become increasingly popular in recommendation systems. However, recent studies have shown that GCN-based models will cause sensitive information to disseminate widely in the graph structure, amplifying data bias and raising fairness concerns. While various fairness methods have been proposed, most of them neglect the impact of biased data on representation learning, which results in limited fairness improvement. Moreover, some studies have focused on constructing fair and balanced data distributions through data augmentation, but these methods significantly reduce utility due to disruption of user preferences. In this paper, we aim to design a fair recommendation method from the perspective of data augmentation to improve fairness while preserving recommendation utility. To achieve fairness-aware data augmentation with minimal disruption to user preferences, we propose two prior hypotheses. The first hypothesis identifies sensitive interactions by comparing outcomes of performance-oriented and fairness-aware recommendations, while the second one focuses on detecting sensitive features by analyzing feature similarities between biased and debiased representations. Then, we propose a dual data augmentation framework for fair recommendation, which includes two data augmentation strategies to generate fair augmented graphs and feature representations. Furthermore, we introduce a debiasing learning method that minimizes the dependence between the learned representations and sensitive information to eliminate bias. Extensive experiments on two real-world datasets demonstrate the superiority of our proposed framework.

Eliminating bias from data representations is crucial to ensure fairness in recommendation. Existing studies primarily focus on weakening the correlation between data representations and sensitive attributes, yet may inadvertently steer the user representations toward another potential bias direction of the target attribute. Furthermore, they often overlook the impact of user preferences on capturing sensitive information, incurring inadequate bias elimination. In this paper, we propose a Fair Counterfactual Representations (FairCoRe) learning framework, which aims to ensure the neutrality of representations among all bias directions. Firstly, we intervene on sensitive attributes to construct a counterfactual scenario. Then, two opposing attribute prediction tasks are respectively performed in ground-truth and counterfactual scenarios to encode sensitive information along different bias directions. Secondly, we design a bias-aware enhancement learning method that quantifies the respective correlation of user preferences and sensitive attributes to enhance sensitive information encoding. Finally, we introduce two mutual information optimization methods that optimize the representations to capture users' interests and disentangle sensitive factors. Moreover, we propose an attribute neutralization strategy that refines the learned representations, ensuring sensitive attribute neutrality. Extensive experiments demonstrate that our method achieves the optimal fairness and competitive accuracy compared to state-of-the-art methods. The source code is available at: https://github.com/FairCoRe2024/FairCoRe.

Recently, multi-behavior recommendation has become a hot topic in the field of recommendation systems. Yet, existing methods still face challenges in effectively representing multi-behavior semantic information from the following perspectives: (i) Previous works’ heavy reliance on a unified embedding for modeling all behavior interaction graphs hindered accuratemining of fine-grained user preference semantics across multiple behaviors. (ii) Existing multi-behavior contrastive learning (CL) tasks fail to capture the dependency of user preferring to items under different behaviors, thereby constrains the model’s ability in characterizing the personalized features of users/items. (iii) The rich semantic information in the knowledge graph is not fully leveraged. To address the above challenges, we design a Contrastive Learning-based Multi-behavior Recommendation with Semantic Knowledge Enhancement (CLMRS) framework, which consists of two encoding modules with CL tasks and a joint learning module. Specifically, in the multi-behavior meta-network encoding module, we propose a novel behavior-supervised graph convolutional encoder to fully mine the user preference semantics in each behavior. Meanwhile, in the semantic knowledge enhanced encoding module, we use a knowledge graph to provide more robust embeddings for items. Finally, we integrate the user/item embeddings learned by the two encoding modules into a comprehensive semantic vector through the joint learning module, which is used for the final prediction of potential users. Extensive experiments on four real-world datasets indicate that CLMRS consistently outperforms various state-of-the-art recommendation methods. Our model code is available at https://github.com/yuwenxuan3197/CLMRS.

Abstract In context-aware recommendation systems, most existing methods encode users’ preferences by mapping item and category information into the same space, which is just a stack of information. The item and category information contained in the interaction behaviours is not fully utilized. Moreover, since users’ preferences for a candidate item are influenced by the changes in temporal and historical behaviours, it is unreasonable to predict correlations between users and candidates by using users’ fixed features. A fine-grained and coarse-grained information based framework proposed in our paper which considers multi-granularity information of users’ historical behaviours. First, a parallel structure is provided to mine users’ preference information under different granularities. Then, self-attention and attention mechanisms are used to capture the dynamic preferences. Experiment results on two publicly available datasets show that our framework outperforms state-of-the-art methods across the calculated evaluation metrics.

Tourism recommendation systems play a vital role in providing useful travel information to tourists. However, existing systems rarely aim at recommending tangible itineraries for tourists within a specific POI due to their lack of onsite travel behavioral data and related route mining algorithms. To this end, a novel travel route recommendation system is proposed, which collects tourist onsite travel behavior data automatically regarding a specific POI based on smart phone and IoT technology. Then, the proposed system preprocesses the behavior data to transform raw behavior sequences into Tourist-Behavior pattern sequences. Subsequently, the system discovers frequent travel routes from the generated pattern sequences by using an original route mining algorithm, named Tourist-Behavior PrefixSpan. Finally, a route-recommending method is designed to search and rank tangible travel routes according to the querying tourist’s profile and constraint. The experimental results demonstrate that the proposed system is efficient and effective in recommending POI-oriented tangible travel routes considering tourists’ route constraints and personal profile while ensuring that the suggested routes have considerable route values.