Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Song, Zeyu, Galhotra, Sainyam, Mehnaz, Shagufta
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909774593916928
author Song, Zeyu
Galhotra, Sainyam
Mehnaz, Shagufta
author_facet Song, Zeyu
Galhotra, Sainyam
Mehnaz, Shagufta
contents The rise of distributed and privacy-preserving machine learning has sparked interest in decentralized gradient marketplaces, where participants trade intermediate artifacts like gradients. However, existing Federated Learning (FL) benchmarks overlook critical economic and systemic factors unique to such marketplaces-cost-effectiveness, fairness to sellers, and market stability-especially when a buyer relies on a private baseline dataset for evaluation. We introduce a comprehensive benchmark framework to holistically evaluate robust gradient aggregation methods within these buyer-baseline-reliant marketplaces. Our contributions include: (1) a simulation environment modeling marketplace dynamics with a variable buyer baseline and diverse seller distributions; (2) an evaluation methodology augmenting standard FL metrics with marketplace-centric dimensions such as Economic Efficiency, Fairness, and Selection Dynamics; (3) an in-depth empirical analysis of the existing Distributed Gradient Marketplace framework, MartFL, including the integration and comparative evaluation of adapted FLTrust and SkyMask as alternative aggregation strategies within it. This benchmark spans diverse datasets, local attacks, and Sybil attacks targeting the marketplace selection process; and (4) actionable insights into the trade-offs between model performance, robustness, cost, fairness, and stability. This benchmark equips the community with essential tools and empirical evidence to evaluate and design more robust, equitable, and economically viable decentralized gradient marketplaces.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05833
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces
Song, Zeyu
Galhotra, Sainyam
Mehnaz, Shagufta
Machine Learning
Computer Science and Game Theory
The rise of distributed and privacy-preserving machine learning has sparked interest in decentralized gradient marketplaces, where participants trade intermediate artifacts like gradients. However, existing Federated Learning (FL) benchmarks overlook critical economic and systemic factors unique to such marketplaces-cost-effectiveness, fairness to sellers, and market stability-especially when a buyer relies on a private baseline dataset for evaluation. We introduce a comprehensive benchmark framework to holistically evaluate robust gradient aggregation methods within these buyer-baseline-reliant marketplaces. Our contributions include: (1) a simulation environment modeling marketplace dynamics with a variable buyer baseline and diverse seller distributions; (2) an evaluation methodology augmenting standard FL metrics with marketplace-centric dimensions such as Economic Efficiency, Fairness, and Selection Dynamics; (3) an in-depth empirical analysis of the existing Distributed Gradient Marketplace framework, MartFL, including the integration and comparative evaluation of adapted FLTrust and SkyMask as alternative aggregation strategies within it. This benchmark spans diverse datasets, local attacks, and Sybil attacks targeting the marketplace selection process; and (4) actionable insights into the trade-offs between model performance, robustness, cost, fairness, and stability. This benchmark equips the community with essential tools and empirical evidence to evaluate and design more robust, equitable, and economically viable decentralized gradient marketplaces.
title Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces
topic Machine Learning
Computer Science and Game Theory
url https://arxiv.org/abs/2509.05833