Time-aware Hyperbolic Graph Attention Network for Session-based Recommendation

TL;DR

This paper introduces TA-HGAT, a hyperbolic graph neural network that incorporates temporal information for session-based recommendation, leveraging hyperbolic geometry to model hierarchical session structures and improve prediction accuracy.

Contribution

The paper proposes a novel hyperbolic graph attention network that explicitly models temporal intervals in session graphs, addressing the lack of temporal consideration in existing hyperbolic SBR methods.

Findings

TA-HGAT outperforms ten baseline models on real-world datasets.

Hyperbolic space effectively captures hierarchical session graph structures.

Temporal modeling improves recommendation accuracy.

Abstract

Session-based Recommendation (SBR) is to predict users' next interested items based on their previous browsing sessions. Existing methods model sessions as graphs or sequences to estimate user interests based on their interacted items to make recommendations. In recent years, graph-based methods have achieved outstanding performance on SBR. However, none of these methods consider temporal information, which is a crucial feature in SBR as it indicates timeliness or currency. Besides, the session graphs exhibit a hierarchical structure and are demonstrated to be suitable in hyperbolic geometry. But few papers design the models in hyperbolic spaces and this direction is still under exploration. In this paper, we propose Time-aware Hyperbolic Graph Attention Network (TA-HGAT) - a novel hyperbolic graph neural network framework to build a session-based recommendation model considering temporal information. More specifically, there are three components in TA-HGAT. First, a hyperbolic projection module transforms the item features into hyperbolic space. Second, the time-aware graph attention module models time intervals between items and the users' current interests. Third, an evolutionary loss at the end of the model provides an accurate prediction of the recommended item based on the given timestamp. TA-HGAT is built in a hyperbolic space to learn the hierarchical structure of session graphs. Experimental results show that the proposed TA-HGAT has the best performance compared to ten baseline models on two real-world datasets.