Federated Split Learning with Joint Personalization-Generalization for Inference-Stage Optimization in Wireless Edge Networks

Dong Jun Han, Do Yeon Kim, Minseok Choi, David Nickel, Jaekyun Moon, Mung Chiang, Christopher G. Brinton

Research output: Contribution to journalArticlepeer-review

Abstract

The demand for intelligent services at the network edge has introduced several research challenges. One is the need for a machine learning architecture that achieves personalization (to individual clients) and generalization (to unseen data) properties concurrently across different applications. Another is the need for an inference strategy that can satisfy network resource and latency constraints during testing-time. Existing techniques in federated learning have encountered a steep trade-off between personalization and generalization, and have not explicitly considered the resource requirements during the inference-stage. In this paper, we propose SplitGP, a joint edge-AI training and inference strategy that simultaneously captures generalization/personalization for efficient inference across resource-constrained clients. The training process of SplitGP is based on federated split learning, with the key idea of optimizing the client-side model to have personalization capability tailored to its main task, while training the server-side model to have generalization capability for handling out-of-distribution tasks. During testing-time, each client selectively offloads inference tasks to the server based on the uncertainty threshold tunable based on network resource availability. Through formal convergence analysis and inference time analysis, we provide guidelines on the selection of key meta-parameters in SplitGP. Experimental results confirm the advantage of SplitGP over existing baselines.

Original languageEnglish (US)
Pages (from-to)7048-7065
Number of pages18
JournalIEEE Transactions on Mobile Computing
Volume23
Issue number6
DOIs
StateAccepted/In press - 2023
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Software
  • Electrical and Electronic Engineering
  • Computer Networks and Communications

Keywords

  • Federated learning
  • edge-AI
  • inference
  • personalization
  • split learning
  • wireless edge network

Fingerprint

Dive into the research topics of 'Federated Split Learning with Joint Personalization-Generalization for Inference-Stage Optimization in Wireless Edge Networks'. Together they form a unique fingerprint.

Cite this