Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization
Authors:
- 20 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 631-640
Abstract
While providing machine learning model as a service to process users’ inference requests, online applications can periodically upgrade the model utilizing newly collected data. Federated learning (FL) is beneficial for enabling the training of models across distributed clients while keeping the data locally. However, existing work has overlooked the coexistence of model training and inference under clients’ limited resources. This paper focuses on the joint optimization of model training and inference to maximize inference performance at clients. Such an optimization faces several challenges. The first challenge is to characterize the clients’ inference performance when clients may partially participate in FL. To resolve this challenge, we introduce a new notion of age of model (AoM) to quantify client-side model freshness, based on which we use FL’s global model convergence error as an approximate measure of inference performance. The second challenge is the tight coupling among clients’ decisions, including participation probability in FL, model download probability, and service rates. Toward the challenges, we propose an online problem approximation to reduce the problem complexity and optimize the resources to balance the needs of model training and inference. Experimental results demonstrate that the proposed algorithm improves the average inference accuracy by up to 12%.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
- Shenzhen Science and Technology Innovation Program
This publication has 29 references indexed in Scilit:
- AoI-Driven Client Scheduling for Federated Learning: A Lagrangian Index Approach2023
- A Reinforcement Learning Approach for Minimizing Job Completion Time in Clustered Federated Learning2023
- Heterogeneity-Aware Federated Learning with Adaptive Client Selection and Gradient Compression2023
- Adaptive Configuration for Heterogeneous Participants in Decentralized Federated Learning2023
- AnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devices2023
- A Profit-Maximizing Model Marketplace with Differentially Private Federated Learning2022
- Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimization2022
- Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networks2020
- Stochastic Network Optimization with Application to Communication and Queueing Systems2010
- Biconvex sets and optimization with biconvex functions: a survey and extensionsMathematical Methods of Operations Research, 2007