Newest papers

Peer-Relative Trust-Guided Update Screening for Robust Semi-Decentralized Federated Learning under Label-Flipping Attacks

Ajay Kumar Shrestha, Sandhya Joshi · 2026 · arXiv

DOI: 10.48550/arXiv.2610.25714 · open-access PDF

Portuguese

Os mecanismos de confiança e reputação podem reduzir a influência de clientes maliciosos na aprendizagem federada (FL), mas a filtragem rigorosa de atualizações é difícil sob dados não independentes e idênticamente distribuídos (não-IID), porque as atualizações locais honestas podem reduzir temporariamente o desempenho em um proxy de validação compartilhada.Com base em nosso anterior framework de FL semi-decentralizado (SDFL) baseado em confiança, este artigo operacionaliza os sinais de confiança e introduz o rastreamento de atualização relacionado a pares que combina uma robusta pontuação de validação-utilidade com a qualidade de atualização baseada em direção e norma.

Machine translation (Meta M2M100); the English original follows.

Abstract

Trust and reputation mechanisms can reduce the influence of malicious clients in federated learning (FL), but strict update filtering is difficult under non-independent and identically distributed (non-IID) data because honest local updates may temporarily reduce performance on a shared validation proxy. Building on our earlier trust-based semi-decentralized FL (SDFL) framework, this paper operationalizes the trust signals and introduces peer-relative update screening that combines a robust validation-utility score with direction- and norm-based update quality. The method is evaluated with 50

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25714, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange