Impression-Informed Multi-Behavior Recommender System: A Hierarchical Graph Attention Approach

TL;DR

This paper introduces HMGN, a hierarchical graph attention network that effectively models multi-behavior interactions in recommender systems, significantly improving ranking performance by leveraging behavior hierarchies and attention mechanisms.

Contribution

The paper presents a novel hierarchical graph attention framework for multi-behavior recommendation, incorporating a multi-task HBPR and scalable sub-graph sampling for improved accuracy.

Findings

Up to 64% NDCG@100 improvement over baseline methods

Effective modeling of inter- and intra-behavior information

Seamless integration of knowledge metadata and time-series data

Abstract

While recommender systems have significantly benefited from implicit feedback, they have often missed the nuances of multi-behavior interactions between users and items. Historically, these systems either amalgamated all behaviors, such as \textit{impression} (formerly \textit{view}), \textit{add-to-cart}, and \textit{buy}, under a singular 'interaction' label, or prioritized only the target behavior, often the \textit{buy} action, discarding valuable auxiliary signals. Although recent advancements tried addressing this simplification, they primarily gravitated towards optimizing the target behavior alone, battling with data scarcity. Additionally, they tended to bypass the nuanced hierarchy intrinsic to behaviors. To bridge these gaps, we introduce the \textbf{H}ierarchical \textbf{M}ulti-behavior \textbf{G}raph Attention \textbf{N}etwork (HMGN). This pioneering framework leverages attention mechanisms to discern information from both inter and intra-behaviors while employing a multi-task Hierarchical Bayesian Personalized Ranking (HBPR) for optimization. Recognizing the need for scalability, our approach integrates a specialized multi-behavior sub-graph sampling technique. Moreover, the adaptability of HMGN allows for the seamless inclusion of knowledge metadata and time-series data. Empirical results attest to our model's prowess, registering a notable performance boost of up to 64\% in NDCG@100 metrics over conventional graph neural network methods.