Session-Based Recommendation (SBR) systems are facing considerable challenges, with their primary objective being to implement precise recommendations based on users’ historical behavior sequences. Graph Neural Networks (GNNs) have emerged as powerful tools for processing graph-structured data in recommendation systems. Although recent research has advanced in this area, a significant gap remains in the in-depth exploration of transitional relationships between user interests. Additionally, real-world recommendation scenarios typically involve various heterogeneous relationships, which contain a wealth of information that can significantly enhance the learning of user preferences. To address this research gap, in this paper, we introduce a model termed the Sentiment-Time Heterogeneous Residual Graph Attention Transformer (STH-ResGAT), which is designed to capture the dynamic nature of user interests and the complexity inherent in heterogeneous graphs. In STH-ResGAT, we develop a Sentiment-Time-Heterogeneous Graph (STH-Graph) that integrates sentiment and time factors into the edges of the graph structure. Furthermore, the Residual Graph Attention Transformer for Heterogeneous Networks (ResGAT-Het) is designed to manage diverse node and edge types based on the STH-Graph. Extensive experiments are conducted on four widely-used benchmark datasets: Ciao, Yelp, Epinions and LibraryThing. The results demonstrate that our proposed STH-ResGAT method significantly outperforms previous state-of-the-art baseline approaches.The implementation of ResGAT-Het is available in https://github.com/zhangyu2234/ResGAT-Het.git .

Abstract Identifying influential nodes is a fundamental and open issue in analysis of the complex networks. The measurement of the spreading capabilities of nodes is an attractive challenge in this field. Node centrality is one of the most popular methods used to identify the influential nodes, which includes the degree centrality (DC), betweenness centrality (BC) and closeness centrality (CC). The DC is an efficient method but not effective. The BC and CC are effective but not efficient. They have high computational complexity. To balance the effectiveness and efficiency, this paper proposes the neighborhood entropy centrality to rank the influential nodes. The proposed method uses the notion of entropy to improve the DC. For evaluating the performance, the susceptible-infected-recovered model is used to simulate the information spreading process of messages on nine real-world networks. The experimental results reveal the accuracy and efficiency of the proposed method.

The purpose of influence maximization problem is to select a small seed set to maximize the number of nodes influenced by the seed set. For viral marketing, the problem of influence maximization plays a vital role. Current works mainly focus on the unsigned social networks, which include only positive relationship between users. However, the influence maximization in the signed social networks including positive and negative relationships between users is still a challenging issue. Moreover, the existing works pay more attention to the positive influence. Therefore, this paper first analyzes the positive maximization influence in the signed social networks. The purpose of this problem is to select the seed set with the most positive influence in the signed social networks. Afterwards, this paper proposes a model that incorporates the state of node, the preference of individual and polarity relationship, called Independent Cascade with the Negative and Polarity (ICWNP) propagation model. On the basis of the ICWNP model, this paper proposes a Greedy with ICWNP algorithm. Finally, on four real social networks, experimental results manifest that the proposed algorithm has higher accuracy and efficiency than the related methods.

Influence maximization is a problem that aims to select top [Formula: see text] influential nodes to maximize the spread of influence in social networks. The classical greedy-based algorithms and their improvements are relatively slow or not scalable. The efficiency of heuristic algorithms is fast but their accuracy is unacceptable. Some algorithms improve the accuracy and efficiency by consuming a large amount of memory usage. To overcome the above shortcoming, this paper proposes a fast and scalable algorithm for influence maximization, called K-paths, which utilizes the influence tree to estimate the influence spread. Additionally, extensive experiments demonstrate that the K-paths algorithm outperforms the comparison algorithms in terms of efficiency while keeping competitive accuracy.