Pith. sign in

REVIEW 1 cited by

SplitGP: Achieving Both Generalization and Personalization in Federated Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2212.08343 v2 pith:J65ESVHI submitted 2022-12-16 cs.LG

classification cs.LG
keywords modelsplitgpgeneralizationinferencelearningpersonalizationclientssplit
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing techniques in federated learning (FL) have encountered a steep tradeoff between these objectives and impose large computational requirements on edge devices during training and inference. In this paper, we propose SplitGP, a new split learning solution that can simultaneously capture generalization and personalization capabilities for efficient inference across resource-constrained clients (e.g., mobile/IoT devices). Our key idea is to split the full ML model into client-side and server-side components, and impose different roles to them: the client-side model is trained to have strong personalization capability optimized to each client's main task, while the server-side model is trained to have strong generalization capability for handling all clients' out-of-distribution tasks. We analytically characterize the convergence behavior of SplitGP, revealing that all client models approach stationary points asymptotically. Further, we analyze the inference time in SplitGP and provide bounds for determining model split ratios. Experimental results show that SplitGP outperforms existing baselines by wide margins in inference time and test accuracy for varying amounts of out-of-distribution samples.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Generalising Battery Control in Net-Zero Buildings via Personalised Federated RL

    cs.LG 2024-12 reject novelty 4.0 of 10

    In a simplified net-zero microgrid, untuned federated TRPO learns useful battery policies, but tuned PPO gets much closer to the known optimal policy; personal encoding and feature grouping sometimes shrink the gap.

Pith tools