Ajay Kumar Shrestha, Sandhya Joshi · 2026 · arXiv
DOI: 10.48550/arXiv.2610.25714 · open-access PDF
Los mecanismos de confianza y reputación pueden reducir la influencia de los clientes maliciosos en el aprendizaje federado (FL), pero la filtración de actualizaciones estricta es difícil bajo los datos no independientes e idénticamente distribuidos (no-IID) porque las actualizaciones locales honestas pueden reducir temporalmente el rendimiento en un proxy de validación compartida.
Machine translation (Meta M2M100); the English original follows.
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
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange