CF-KAN: Kolmogorov-Arnold Network-based Collaborative Filtering to Mitigate Catastrophic Forgetting in Recommender Systems

TL;DR

CF-KAN introduces a novel collaborative filtering approach using Kolmogorov-Arnold networks to address catastrophic forgetting, improving recommendation accuracy and interpretability in dynamic environments.

Contribution

The paper proposes CF-KAN, a new CF method leveraging KANs to enhance robustness against forgetting and improve recommendation performance.

Findings

CF-KAN outperforms state-of-the-art methods in accuracy.

CF-KAN demonstrates resilience to catastrophic forgetting.

CF-KAN offers edge-level interpretability of recommendations.

Abstract

Collaborative filtering (CF) remains essential in recommender systems, leveraging user--item interactions to provide personalized recommendations. Meanwhile, a number of CF techniques have evolved into sophisticated model architectures based on multi-layer perceptrons (MLPs). However, MLPs often suffer from catastrophic forgetting, and thus lose previously acquired knowledge when new information is learned, particularly in dynamic environments requiring continual learning. To tackle this problem, we propose CF-KAN, a new CF method utilizing Kolmogorov-Arnold networks (KANs). By learning nonlinear functions on the edge level, KANs are more robust to the catastrophic forgetting problem than MLPs. Built upon a KAN-based autoencoder, CF-KAN is designed in the sense of effectively capturing the intricacies of sparse user--item interactions and retaining information from previous data instances. Despite its simplicity, our extensive experiments demonstrate 1) CF-KAN's superiority over state-of-the-art methods in recommendation accuracy, 2) CF-KAN's resilience to catastrophic forgetting, underscoring its effectiveness in both static and dynamic recommendation scenarios, and 3) CF-KAN's edge-level interpretation facilitating the explainability of recommendations.