Optimal Model Scaling Factors for Federated LLM Code Generation Under IID and Non-IID Data

Abstract

Abstract: This report synthesises findings from 11 peer-reviewed papers addressing the following research question: What is the optimal model scaling factor for code generation quality (measured by HumanEval pass@10) when training federated LLMs with partial client participation and IID versus non-IID data. The proliferation of edge devices has brought Federated Learning (FL) to the forefront as a promising paradigm for decentralized and collaborative model training while preserving the privacy of clients' data. However, FL struggles with a significant performance reduction and. 6 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

What is the optimal model scaling factor for code generation quality (measured by HumanEval pass@10) when training federated LLMs with partial client participation and IID versus non-IID data distributions?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance