Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences. However, real-life interactions among users are very complicated and user relations can be high-order. Hypergraph provides a natural way to model complex high-order relations, while its potentials for improving social recommendation are under-explored. In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations. Technically, each channel in the network encodes a hypergraph that depicts a common high-order user relation pattern via hypergraph convolution. By aggregating the embeddings learned through multiple channels, we obtain comprehensive user representations to generate recommendation results. However, the aggregation operation might also obscure the inherent characteristics of different types of high-order connectivity information. To compensate for the aggregating loss, we innovatively integrate self-supervised learning into the training of the hypergraph convolutional network to regain the connectivity information with hierarchical mutual information maximization. The experimental results on multiple real-world datasets show that the proposed model outperforms the SOTA methods, and the ablation study verifies the effectiveness of the multi-channel setting and the selfsupervised task. The implementation of our model is available via https://github.com/Coder-Yu/RecQ.

No abstract

The explicitly observed social relations from online social platforms have been widely incorporated into recommender systems to mitigate the data sparsity issue. However, the direct usage of explicit social relations may lead to an inferior performance due to the unreliability (e.g., noises) of observed links. To this end, the discovery of reliable relations among users plays a central role in advancing social recommendation. In this paper, we propose a novel approach to adaptively identify implicit friends toward discovering more credible user relations. Particularly, implicit friends are those who share similar tastes but could be distant from each other on the network topology of social relations. Methodologically, to find the implicit friends for each user, we first model the whole system as a heterogeneous information network, and then capture the similarity of users through the meta-path based embedding representation learning. Finally, based on the intuition that social relations have varying degrees of impact on different users, our approach adaptively incorporates different numbers of similar users as implicit friends for each user to alleviate the adverse impact of unreliable social relations for a more effective recommendation. Experimental analysis on three real-world datasets demonstrates the superiority of our method and explain why implicit friends are helpful in improving social recommendation.

Session-based recommendation (SBR) focuses on next-item prediction at a certain time point. As user profiles are generally not available in this scenario, capturing the user intent lying in the item transitions plays a pivotal role. Recent graph neural networks (GNNs) based SBR methods regard the item transitions as pairwise relations, which neglect the complex high-order information among items. Hypergraph provides a natural way to capture beyond-pairwise relations, while its potential for SBR has remained unexplored. In this paper, we fill this gap by modeling session-based data as a hypergraph and then propose a dual channel hypergraph convolutional network -- DHCN to improve SBR. Moreover, to enhance hypergraph modeling, we innovatively integrate self-supervised learning into the training of our network by maximizing mutual information between the session representations learned via the two channels in DHCN, serving as an auxiliary task to improve the recommendation task. Extensive experiments on three benchmark datasets demonstrate the superiority of our model over the SOTA methods, and the ablation study validates the effectiveness and rationale of hypergraph modeling and self-supervised task. The implementation of our model is available via https://github.com/xiaxin1998/DHCN.

Recent reports from industry show that social recommender systems consistently fail in practice. According to the negative findings, the failure is attributed to: (1) a majority of users only have a very limited number of neighbors in social networks and can hardly benefit from relations; (2) social relations are noisy but they are often indiscriminately used; (3) social relations are assumed to be universally applicable to multiple scenarios while they are actually multi-faceted and show heterogeneous strengths in different scenarios. Most existing social recommendation models only consider the homophily in social networks and neglect these drawbacks.In this paper we propose a deep adversarial framework based on graph convolutional networks (GCN) to address these problems. Concretely, for the relation sparsity and noises problems, a GCN-based autoencoder is developed to augment the relation data by encoding high-order and complex connectivity patterns, and meanwhile is optimized subject to the constraint of reconstructing the original social profile to guarantee the validity of new identified neighborhood. After obtaining enough purified social relations for each user, a GCN-based attentive social recommendation module is designed to capture the heterogeneous strengths of social relations. These designs deal with the three problems faced by social recommender systems respectively. Finally, we adopt adversarial training to unify and intensify all components by playing a minimax game and ensure a coordinated effort to enhance social recommendation. Experimental results on multiple open datasets demonstrate the superiority of our framework and the ablation study confirms the importance and effectiveness of each component.

Self-supervised learning (SSL), which can automatically generate ground-truth samples from raw data, holds vast potential to improve recommender systems. Most existing SSL-based methods perturb the raw data graph with uniform node/edge dropout to generate new data views and then conduct the self-discrimination based contrastive learning over different views to learn generalizable representations. Under this scheme, only a bijective mapping is built between nodes in two different views, which means that the self-supervision signals from other nodes are being neglected. Due to the widely observed homophily in recommender systems, we argue that the supervisory signals from other nodes are also highly likely to benefit the representation learning for recommendation. To capture these signals, a general socially-aware SSL framework that integrates tri-training is proposed in this paper. Technically, our framework first augments the user data views with the user social information. And then under the regime of tri-training for multi-view encoding, the framework builds three graph encoders (one for recommendation) upon the augmented views and iteratively improves each encoder with self-supervision signals from other users, generated by the other two encoders. Since the tri-training operates on the augmented views of the same data sources for self-supervision signals, we name it self-supervised tri-training. Extensive experiments on multiple real-world datasets consistently validate the effectiveness of the self-supervised tritraining framework for improving recommendation.

Session-based recommendation targets next-item prediction by exploiting user behaviors within a short time period. Compared with other recommendation paradigms, session-based recommendation suffers more from the problem of data sparsity due to the very limited short-term interactions. Self-supervised learning, which can discover ground-truth samples from the raw data, holds vast potentials to tackle this problem. However, existing self-supervised recommendation models mainly rely on item/segment dropout to augment data, which are not fit for session-based recommendation because the dropout leads to sparser data, creating unserviceable self-supervision signals. In this paper, for informative sessionbased data augmentation, we combine self-supervised learning with co-training, and then develop a framework to enhance sessionbased recommendation. Technically, we first exploit the sessionbased graph to augment two views that exhibit the internal and external connectivities of sessions, and then we build two distinct graph encoders over the two views, which recursively leverage the different connectivity information to generate ground-truth samples to supervise each other by contrastive learning. In contrast to the dropout strategy, the proposed self-supervised graph co-training preserves the complete session information and fulfills genuine data augmentation. Extensive experiments on multiple benchmark datasets show that, session-based recommendation can be remarkably enhanced under the regime of self-supervised graph co-training, achieving the state-of-the-art performance.

No abstract