Compressed Interaction Graph based Framework for Multi-behavior Recommendation

TL;DR

This paper introduces CIGF, a framework that models high-order relations in multi-behavior recommendation data using a compressed interaction graph and multi-expert network to improve recommendation accuracy.

Contribution

The paper proposes a novel Compressed Interaction Graph Convolution Network and a Multi-Expert with Separate Input network to better model multi-behavior data and reduce gradient conflicts in multi-task learning.

Findings

CIGF outperforms existing methods on three large-scale datasets.

The model effectively captures high-order relations in multi-behavior data.

Ablation studies confirm the importance of each component in CIGF.

Abstract

Multi-types of user behavior data (e.g., clicking, adding to cart, and purchasing) are recorded in most real-world recommendation scenarios, which can help to learn users' multi-faceted preferences. However, it is challenging to explore multi-behavior data due to the unbalanced data distribution and sparse target behavior, which lead to the inadequate modeling of high-order relations when treating multi-behavior data ''as features'' and gradient conflict in multitask learning when treating multi-behavior data ''as labels''. In this paper, we propose CIGF, a Compressed Interaction Graph based Framework, to overcome the above limitations. Specifically, we design a novel Compressed Interaction Graph Convolution Network (CIGCN) to model instance-level high-order relations explicitly. To alleviate the potential gradient conflict when treating multi-behavior data ''as labels'', we propose a Multi-Expert with Separate Input (MESI) network with separate input on the top of CIGCN for multi-task learning. Comprehensive experiments on three large-scale real-world datasets demonstrate the superiority of CIGF. Ablation studies and in-depth analysis further validate the effectiveness of our proposed model in capturing high-order relations and alleviating gradient conflict. The source code and datasets are available at https://github.com/MC-CV/CIGF.