A Payload Optimization Method for Federated Recommender Systems
- 13 September 2021
- conference paper
- conference paper
- Published by Association for Computing Machinery (ACM)
Abstract
In this study, we introduce the payload optimization method for federated recommender systems (FRS). In federated learning (FL), the global model payload that is moved between the server and users depends on the number of items to recommend. The model payload grows when there is an increasing number of items. This becomes challenging for FRS if it is running in production mode. To tackle the payload challenge, we formulated a multi-arm bandit solution that selected part of the global model and transmitted it to all users. The selection process was guided by a novel reward function suitable for FL systems. So far as we are aware, this is the first optimization method that seeks to address item dependent payloads. The method was evaluated using three benchmark recommendation datasets. The empirical validation confirmed that the proposed method outperforms the simpler methods that do not benefit from the bandits for the purpose of item selection. In addition, we have demonstrated the usefulness of our proposed method by rigorously evaluating the effects of a payload reduction on the recommendation performance degradation. Our method achieved up to a 90% reduction in model payload, yielding only a ∼ 4% - 8% loss in the recommendation performance for highly sparse datasets.Keywords
This publication has 17 references indexed in Scilit:
- A Privacy-Preserving Distributed Contextual Federated Online Learning Framework with Big Data Support in Social Recommender SystemsIEEE Transactions on Knowledge and Data Engineering, 2019
- Ensemble Recommendations via Thompson SamplingPublished by Association for Computing Machinery (ACM) ,2018
- The MovieLens DatasetsACM Transactions on Interactive Intelligent Systems, 2015
- Proceedings of the 2nd International Workshop on Information Heterogeneity and Fusion in Recommender SystemsPublished by Association for Computing Machinery (ACM) ,2011
- A modern Bayesian look at the multi‐armed banditApplied Stochastic Models in Business and Industry, 2010
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009
- Collaborative Filtering for Implicit Feedback DatasetsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Learning diverse rankings with multi-armed banditsPublished by Association for Computing Machinery (ACM) ,2008
- On the Theory of ApportionmentAmerican Journal of Mathematics, 1935
- ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLESBiometrika, 1933