Incorporating Like-Minded Peers to Overcome Friend Data Sparsity in Session-Based Social Recommendations

TL;DR

This work proposes a novel model named Transformer Encoder with Graph Attention Aggregator Recommendation (TEGAARec), which includes the TEGAA module and the GAT-based social aggregation module, which includes users whose preferences align with the target user's current session based on their historical sessions and uses LMP to enhance the modeling of social influence in SSR.

Abstract

Session-based Social Recommendation (SSR) leverages social relationships within online networks to enhance the performance of Session-based Recommendation (SR). However, existing SSR algorithms often encounter the challenge of "friend data sparsity". Moreover, significant discrepancies can exist between the purchase preferences of social network friends and those of the target user, reducing the influence of friends relative to the target user's own preferences. To address these challenges, this paper introduces the concept of "Like-minded Peers" (LMP), representing users whose preferences align with the target user's current session based on their historical sessions. This is the first work, to our knowledge, that uses LMP to enhance the modeling of social influence in SSR. This approach not only alleviates the problem of friend data sparsity but also effectively incorporates users with similar preferences to the target user. We propose a novel model named Transformer Encoder with Graph Attention Aggregator Recommendation (TEGAARec), which includes the TEGAA module and the GAT-based social aggregation module. The TEGAA module captures and merges both long-term and short-term interests for target users and LMP users. Concurrently, the GAT-based social aggregation module is designed to aggregate the target users' dynamic interests and social influence in a weighted manner. Extensive experiments on four real-world datasets demonstrate the efficacy and superiority of our proposed model and ablation studies are done to illustrate the contributions of each component in TEGAARec.

Figures (8)

• Figure 1: Like-minded Peers (LMP) mined by Mike in different sessions -- Session $k_x$ and Session $t_x$ denote that the LMP has interacted with the same items as Mike in Session $a$ and Session $b$ respectively, where $k_x \in [1, a-1 ]$ and $t_x \in [1, b-1]$.
• Figure 2: The overall framework of TEGAARec.
• Figure 3: Effect of different embedding dimension sizes on model performance
• Figure 4: Effect of different number of Transformer encoder layers on model performance
• Figure 5: Effect of different number of LMP users on model performance

Theorems & Definitions (4)

• Definition 1
• Definition 2
• Definition 3
• Definition 4