DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedback

TL;DR

This paper introduces DFGNN, a novel graph neural network that effectively models both positive and negative feedback in recommendation systems by capturing different frequency signals, improving recommendation accuracy.

Contribution

The paper proposes a dual-frequency graph filter and signed graph regularization to better utilize negative feedback and address representation degeneration in graph-based recommendations.

Findings

DFGNN outperforms existing models on real-world datasets.

The dual-frequency filter captures both positive and negative feedback signals.

Signed regularization alleviates embedding degeneration.

Abstract

The graph-based recommendation has achieved great success in recent years. However, most existing graph-based recommendations focus on capturing user preference based on positive edges/feedback, while ignoring negative edges/feedback (e.g., dislike, low rating) that widely exist in real-world recommender systems. How to utilize negative feedback in graph-based recommendations still remains underexplored. In this study, we first conducted a comprehensive experimental analysis and found that (1) existing graph neural networks are not well-suited for modeling negative feedback, which acts as a high-frequency signal in a user-item graph. (2) The graph-based recommendation suffers from the representation degeneration problem. Based on the two observations, we propose a novel model that models positive and negative feedback from a frequency filter perspective called Dual-frequency Graph Neural Network for Sign-aware Recommendation (DFGNN). Specifically, in DFGNN, the designed dual-frequency graph filter (DGF) captures both low-frequency and high-frequency signals that contain positive and negative feedback. Furthermore, the proposed signed graph regularization is applied to maintain the user/item embedding uniform in the embedding space to alleviate the representation degeneration problem. Additionally, we conduct extensive experiments on real-world datasets and demonstrate the effectiveness of the proposed model. Codes of our model will be released upon acceptance.