PerFedRec++: Enhancing Personalized Federated Recommendation with Self-Supervised Pre-Training

TL;DR

PerFedRec++ introduces a self-supervised pre-training framework for federated recommendation systems, improving personalization, convergence speed, and communication efficiency by leveraging contrastive graph learning and client clustering.

Contribution

It proposes a novel self-supervised pre-training approach combined with federated graph neural networks and user clustering to enhance personalization and reduce communication costs.

Findings

Achieves superior recommendation accuracy on real-world datasets.

Speeds up training convergence compared to existing methods.

Reduces communication overhead through effective pre-training.

Abstract

Federated recommendation systems employ federated learning techniques to safeguard user privacy by transmitting model parameters instead of raw user data between user devices and the central server. Nevertheless, the current federated recommender system faces challenges such as heterogeneity and personalization, model performance degradation, and communication bottleneck. Previous studies have attempted to address these issues, but none have been able to solve them simultaneously. In this paper, we propose a novel framework, named PerFedRec++, to enhance the personalized federated recommendation with self-supervised pre-training. Specifically, we utilize the privacy-preserving mechanism of federated recommender systems to generate two augmented graph views, which are used as contrastive tasks in self-supervised graph learning to pre-train the model. Pre-training enhances the performance of federated models by improving the uniformity of representation learning. Also, by providing a better initial state for federated training, pre-training makes the overall training converge faster, thus alleviating the heavy communication burden. We then construct a collaborative graph to learn the client representation through a federated graph neural network. Based on these learned representations, we cluster users into different user groups and learn personalized models for each cluster. Each user learns a personalized model by combining the global federated model, the cluster-level federated model, and its own fine-tuned local model. Experiments on three real-world datasets show that our proposed method achieves superior performance over existing methods.