Metraipolis › archive › dc_64dcd3f86022

Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design — arXiv:2609.14591

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14591
License (as archived)
CC0-1.0
Archived
2026-10-15T23:48:48.650Z
SHA-256 of the archived text
53c01231c1f533a7db60a5e1aa90ebbd61bad8d1e2a621f66253885a27d9102b
Stable URL of this page
https://metraipolis.com/documento/dc_64dcd3f86022

How to cite

Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design — arXiv:2609.14591 — arXiv (en), https://arxiv.org/abs/2609.14591 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_64dcd3f86022 (Metraipolis archive dc_64dcd3f86022, sha256 53c01231c1f533a7db60a5e1aa90ebbd61bad8d1e2a621f66253885a27d9102b)
BibTeX
@misc{dc64dcd3f86022,
  title = {Pathwise Individual Rationality in Federated Learning: A Mechanism-Architecture Co-Design — arXiv:2609.14591},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14591},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_64dcd3f86022; sha256 53c01231c1f533a7db60a5e1aa90ebbd61bad8d1e2a621f66253885a27d9102b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14591. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Participation in federated learning (FL) comes at a cost. Clients trade off privacy, communication, and compute costs for potentially greater gains in model efficacy. This paper explores this tradeoff under the aegis of individual rationality (IR) versus autarky, the basic game-theoretic requirement that the federation provide utility no worse than local training. Using the above as the design target, we examine pathwise performance of FL, as a per-round bound on cumulative surplus rather than only an asymptotic equilibrium guarantee under different degrees of client data heterogeneity. Along the learning path, clients can remain below their local-training baseline for hundreds of rounds. The natural remedy is to cap each client's per-round contribution so that this shortfall stays bounded. We prove that such a cap drives all contributions to zero, with high probability, when its tolerance is small relative to the warm-up deficit, and we observe learning collapse under it even at low heterogeneity. We then propose a design that combines a short-term participation guarantee, enforced after an announced grace window, with personalized model evaluation, while preserving the incentive properties of the underlying mechanism. We provide a theoretical basis for this approach and empirically demonstrate that, after the grace window, clients meet IR on nearly all rounds without harming overall performance under low to moderate heterogeneity; under severe heterogeneity, the design shows promising outcomes for clients compared to their local baseline at some cost in accuracy.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-15 in cs.GT).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2609.14591 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T23:17:52.856Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).