Interactive Graph Convolutional Filtering

TL;DR

This paper introduces an Interactive Graph Convolutional Filtering model for recommender systems that leverages graph-based collaborative filtering, variational inference, and Bayesian meta-learning to improve accuracy and address cold-start and data sparsity issues.

Contribution

The paper presents a novel graph convolutional filtering approach combined with variational inference and Bayesian meta-learning, enhancing interactive collaborative filtering performance.

Findings

Outperforms existing baselines on three real-world datasets.

Provides theoretical regret bounds for the proposed method.

Effectively addresses cold-start and data sparsity problems.

Abstract

Interactive Recommender Systems (IRS) have been increasingly used in various domains, including personalized article recommendation, social media, and online advertising. However, IRS faces significant challenges in providing accurate recommendations under limited observations, especially in the context of interactive collaborative filtering. These problems are exacerbated by the cold start problem and data sparsity problem. Existing Multi-Armed Bandit methods, despite their carefully designed exploration strategies, often struggle to provide satisfactory results in the early stages due to the lack of interaction data. Furthermore, these methods are computationally intractable when applied to non-linear models, limiting their applicability. To address these challenges, we propose a novel method, the Interactive Graph Convolutional Filtering model. Our proposed method extends interactive collaborative filtering into the graph model to enhance the performance of collaborative filtering between users and items. We incorporate variational inference techniques to overcome the computational hurdles posed by non-linear models. Furthermore, we employ Bayesian meta-learning methods to effectively address the cold-start problem and derive theoretical regret bounds for our proposed method, ensuring a robust performance guarantee. Extensive experimental results on three real-world datasets validate our method and demonstrate its superiority over existing baselines.