ReFRS: Resource-efficient Federated Recommender System for Dynamic and Diversified User Preferences

TL;DR

ReFRS introduces a resource-efficient federated recommender system that adapts to dynamic, diverse user preferences by employing lightweight local models and adaptive clustering, improving accuracy and scalability in decentralized environments.

Contribution

The paper proposes ReFRS, a novel federated recommender system that handles resource constraints and user diversity through lightweight models and dynamic clustering for better personalization.

Findings

ReFRS outperforms baseline models in accuracy.

ReFRS demonstrates high scalability with limited resources.

Adaptive clustering improves recommendation relevance.

Abstract

Owing to its nature of scalability and privacy by design, federated learning (FL) has received increasing interest in decentralized deep learning. FL has also facilitated recent research on upscaling and privatizing personalized recommendation services, using on-device data to learn recommender models locally. These models are then aggregated globally to obtain a more performant model, while maintaining data privacy. Typically, federated recommender systems (FRSs) do not consider the lack of resources and data availability at the end-devices. In addition, they assume that the interaction data between users and items is i.i.d. and stationary across end-devices, and that all local recommender models can be directly averaged without considering the user's behavioral diversity. However, in real scenarios, recommendations have to be made on end-devices with sparse interaction data and limited resources. Furthermore, users' preferences are heterogeneous and they frequently visit new items. This makes their personal preferences highly skewed, and the straightforwardly aggregated model is thus ill-posed for such non-i.i.d. data. In this paper, we propose Resource Efficient Federated Recommender System (ReFRS) to enable decentralized recommendation with dynamic and diversified user preferences. On the device side, ReFRS consists of a lightweight self-supervised local model built upon the variational autoencoder for learning a user's temporal preference from a sequence of interacted items. On the server side, ReFRS utilizes a semantic sampler to adaptively perform model aggregation within each identified user cluster. The clustering module operates in an asynchronous and dynamic manner to support efficient global model update and cope with shifting user interests. As a result, ReFRS achieves superior performance in terms of both accuracy and scalability, as demonstrated by comparative experiments.