One-Shot Federated Group Collaborative Filtering

Abstract

Non-negative matrix factorization (NMF) with missing-value completion is a well-known effective Collaborative Filtering (CF) method used to provide personalized user recommendations. However, traditional CF relies on a privacy-invasive collection of user data to build a central recommender model. One-shot federated learning has recently emerged as a method to mitigate the privacy problem while addressing the traditional communication bottleneck of federated learning. In this paper, we present the first one-shot federated CF implementation, named One-FedCF, for groups of users or collaborating organizations. In our solution, the clients first apply local CF in-parallel to build distinct, client-specific recommenders. Then, the privacy-preserving local item patterns and biases from each client are shared with the processor to perform joint factorization in order to extract the global item patterns. Extracted patterns are then aggregated to each client to build the local models via information retrieval transfer. In our experiments, we demonstrate our approach with two MovieLens datasets and show results competitive with the state-of-the-art federated recommender systems at a substantial decrease in the number of communications.

@INPROCEEDINGS{10069271,
  author={Eren, Maksim E. and Bhattarai, Manish and Solovyev, Nicholas and Richards, Luke E. and Yus, Roberto and Nicholas, Charles and Alexandrov, Boian S.},
  booktitle={2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)}, 
  title={One-Shot Federated Group Collaborative Filtering}, 
  year={2022},
  volume={},
  number={},
  pages={647-652},
  notes={Awarded Best M.S. Research at 2023 UMBC CSEE Research Day.},
  doi={10.1109/ICMLA55696.2022.00107}}

Maksim E. Eren

Scientist

My research interests lie at the intersection of the machine learning and cybersecurity disciplines, with a concentration in tensor decomposition.