Session-based recommendation, which has witnessed a booming interest recently, focuses on predicting a user’s next interested item(s) based on an anonymous session. Most existing studies adopt complex deep learning techniques (e.g., graph neural networks) for effective session-based recommendation. However, they merely address co-occurrence between items, but fail to distinguish a causality and correlation relationship. Considering the varied interpretations and characteristics of causality and correlation relationships between items, in this study, we propose a novel method denoted as CGSR by jointly modeling causality and correlation relationships between items. In particular, we construct cause, effect, and correlation graphs from sessions by simultaneously considering the false causality problem. We further design a graph neural network–based method for session-based recommendation. To conclude, we strive to explore the relationship between items from specific “causality” (directed) and “correlation” (undirected) perspectives. Extensive experiments on three datasets show that our model outperforms other state-of-the-art methods in terms of recommendation accuracy. Moreover, we further propose an explainable framework on CGSR and demonstrate the explainability of our model via case studies on an Amazon dataset.

Session-based recommendation (SR) has gained increasing attention in recent years. Quite a great amount of studies have been devoted to designing complex algorithms to improve recommendation performance, where deep learning methods account for the majority. However, most of these methods are black-box ones and ignore to provide moderate explanations to facilitate users’ understanding, which thus might lead to lowered user satisfaction and reduced system revenues. Therefore, in our study, we propose a generic Reinforced Explainable framework with Knowledge graph for Session-based recommendation (i.e., REKS), which strives to improve the existing black-box SR models (denoted as non-explainable ones) with Markov decision process. In particular, we construct a knowledge graph with session behaviors and treat SR models as part of the policy network of Markov decision process. Based on our particularly designed state vector, reward strategy, and loss function, the reinforcement learning (RL)-based framework not only achieves improved recommendation accuracy, but also provides appropriate explanations at the same time. Finally, we instantiate the REKS in five representative, state-of-the-art SR models (i.e., GRU4REC, NARM, SR-GNN, GCSAN, BERT4REC), whereby extensive experiments towards these methods on four datasets demonstrate the effectiveness of our framework on both recommendation and explanation tasks.

With the rapid information explosion on online social network sites (SNSs), it becomes difficult for users to seek new friends or broaden their social networks in an efficient way. Link prediction, which can effectively conquer this problem, has thus attracted wide attention. Previous methods on link prediction fail to comprehensively capture the factors leading to new link formation: 1) few models have considered the varied impacts of users' short-term and long-term interests on link prediction. Besides, they fail to jointly model the influence from social influence and “weak links”; 2) considering that different factors should be derived from information sources of different modalities, there is a lack of effective multi-modal framework for link prediction. In this view, we propose a novel multi-modal framework for link prediction (referred as LP-UIT) which fuses a comprehensive set of features (i.e., user information and topological features) extracted from multi-modal information (i.e., textual information, graph information, and numerical information). Specifically, we adopt graph convolutional network to process the network information to capture topological features, employ natural language processing techniques (i.e., TF-IDF and word2Vec) to model users' short-term and long-term interests, and identify social influence and “weak links” from numerical features. We further use an attention mechanism to model the relationship between textual and topological features. Finally, a multi-layer perceptron (MLP) is designed to combine the representations from three modalities for link prediction. Extensive experiments on two real-world datasets demonstrate the superiority of LP-UIT over the state-of-the-art methods.