Meta Matrix Factorization for Federated Rating Predictions

Yujie Lin, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Dongxiao Yu, Jun Ma, Maarten de Rijke, Xiuzhen Cheng
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
Federated recommender systems have distinct advantages in terms of privacy protection over traditional recommender systems that are centralized at a data center. With the widespread use and the growing computing power of mobile devices, it is becoming increasingly feasible to store and process data locally on the devices and to train recommender models in a federated manner. However, previous work on federated recommender systems does not fully account for the limitations in terms of storage,
more » ... M, energy and communication bandwidth in a mobile environment. The scales of the models proposed are too large to be easily run on mobile devices. Also, existing federated recommender systems need to fine-tune recommendation models on each device, which makes it hard to effectively exploit collaborative filtering information among users/devices. Our goal in this paper is to design a novel federated learning framework for rating prediction (RP) for mobile environments that operates on par with state-of-the-art fully centralized RP methods. To this end, we introduce a federated matrix factorization (MF) framework, named meta matrix factorization (MetaMF), that is able to generate private item embeddings and RP models with a meta network. Given a user, we first obtain a collaborative vector by collecting useful information with a collaborative memory module. Then, we employ a meta recommender module to generate private item embeddings and a RP model based on the collaborative vector in the server. To address the challenge of generating a large number of high-dimensional item embeddings, we devise a rise-dimensional generation strategy that first generates a low-dimensional item * Co-corresponding author. embedding matrix and a rise-dimensional matrix, and then multiply them to obtain high-dimensional embeddings. We use the generated model to produce private RPs for the given user on her device. MetaMF shows a high capacity even with a small RP model, which can adapt to the limitations of a mobile environment. We conduct extensive experiments on four benchmark datasets to compare MetaMF with existing MF methods and find that MetaMF can achieve competitive performance. Moreover, we find MetaMF achieves higher RP performance over existing federated methods by better exploiting collaborative filtering among users/devices. CCS CONCEPTS • Information systems → Recommender systems.
doi:10.1145/3397271.3401081 dblp:conf/sigir/LinRCRY0RC20 fatcat:y2udty4x4fgffagg67lb46ro3q