Session-based Recommendation with Hypergraph Attention Networks

TL;DR

This paper introduces a hypergraph attention network for session-based recommendations, effectively modeling item correlations and user intent in short sessions to improve recommendation accuracy.

Contribution

It proposes a novel hypergraph attention network that constructs session-specific hypergraphs, uses attention layers for item embedding, and dynamically infers user intent for better recommendations.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively models item correlations within sessions.

Generates dynamic item embeddings for accurate next-item prediction.

Abstract

Session-based recommender systems aim to improve recommendations in short-term sessions that can be found across many platforms. A critical challenge is to accurately model user intent with only limited evidence in these short sessions. For example, is a flower bouquet being viewed meant as part of a wedding purchase or for home decoration? Such different perspectives greatly impact what should be recommended next. Hence, this paper proposes a novel session-based recommendation system empowered by hypergraph attention networks. Three unique properties of the proposed approach are: (i) it constructs a hypergraph for each session to model the item correlations defined by various contextual windows in the session simultaneously, to uncover item meanings; (ii) it is equipped with hypergraph attention layers to generate item embeddings by flexibly aggregating the contextual information from correlated items in the session; and (iii) it aggregates the dynamic item representations for each session to infer the general purpose and current need, which is decoded to infer the next interesting item in the session. Through experiments on three benchmark datasets, we find the proposed model is effective in generating informative dynamic item embeddings and providing more accurate recommendations compared to the state-of-the-art.