HMAR: Hierarchical Masked Attention for Multi-Behaviour Recommendation

TL;DR

HMAR introduces a hierarchical masked attention model that effectively captures multi-behavior user interactions and sequential patterns, improving recommendation accuracy in complex behavioral data.

Contribution

The paper proposes a novel hierarchical masked attention mechanism with behavior indicators and multi-task learning for enhanced multi-behavior recommendation.

Findings

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

Effectively models sequential and multi-behavior user interactions.

Demonstrates significant improvements in recommendation accuracy.

Abstract

In the context of recommendation systems, addressing multi-behavioral user interactions has become vital for understanding the evolving user behavior. Recent models utilize techniques like graph neural networks and attention mechanisms for modeling diverse behaviors, but capturing sequential patterns in historical interactions remains challenging. To tackle this, we introduce Hierarchical Masked Attention for multi-behavior recommendation (HMAR). Specifically, our approach applies masked self-attention to items of the same behavior, followed by self-attention across all behaviors. Additionally, we propose historical behavior indicators to encode the historical frequency of each items behavior in the input sequence. Furthermore, the HMAR model operates in a multi-task setting, allowing it to learn item behaviors and their associated ranking scores concurrently. Extensive experimental results on four real-world datasets demonstrate that our proposed model outperforms state-of-the-art methods. Our code and datasets are available here (https://github.com/Shereen-Elsayed/HMAR).