Metraipolis › archive › dc_25f8b41dfd9e

FedCoT-VQA: A Federated Learning and Unlearning Framework for Chain-of-Thought Planners in VideoQA — arXiv:2609.26814

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26814
License (as archived)
CC0-1.0
Archived
2026-10-08T10:13:04.535Z
SHA-256 of the archived text
1a22f91cd7797a9d9fc79fc5b734703fefd77bb81f58a07c68c50ad8b3fb5849
Stable URL of this page
https://metraipolis.com/documento/dc_25f8b41dfd9e

How to cite

FedCoT-VQA: A Federated Learning and Unlearning Framework for Chain-of-Thought Planners in VideoQA — arXiv:2609.26814 — arXiv (en), https://arxiv.org/abs/2609.26814 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25f8b41dfd9e (Metraipolis archive dc_25f8b41dfd9e, sha256 1a22f91cd7797a9d9fc79fc5b734703fefd77bb81f58a07c68c50ad8b3fb5849)
BibTeX
@misc{dc25f8b41dfd9e,
  title = {FedCoT-VQA: A Federated Learning and Unlearning Framework for Chain-of-Thought Planners in VideoQA — arXiv:2609.26814},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26814},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25f8b41dfd9e; sha256 1a22f91cd7797a9d9fc79fc5b734703fefd77bb81f58a07c68c50ad8b3fb5849},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26814. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Chain-of-Thought (CoT) planners have emerged as an effective design for VideoQA, where a lightweight planner first generates intermediate reasoning steps to guide temporal evidence selection before answer prediction. This modularity makes CoT-based VideoQA attractive for federated learning, since only the planner side needs collaborative adaptation while the heavy vision-language backbone can remain fixed. However, in decentralized settings, the planner must not only be trained efficiently across heterogeneous clients but also support later client deletion requests. This is challenging because deleted-client influence is reflected both in model parameters and the planner's reasoning-trace behavior. We present FedCoT-VQA, a federated learning and unlearning framework for CoT planners in VideoQA. FedCoT-VQA consists of three modules: planner-side partitioning (PSP), which exposes a compact shared-residual adaptation space for efficient federated training; server-side aggregation (SSA), which aggregates planner-side updates while maintaining a deletion-ready contribution log; and a residual unlearning module (RUM), which approximates the retained-only counterfactual planner through retained-client replay and selective residual correction, without full retraining. We evaluate FedCoT-VQA in terms of federated training utility, federated unlearning utility, forgetting quality, and efficiency. Results show that compared to current federated approaches, FedCoT-VQA preserves strong federated training utility, improving grounding quality by up to 4.45%. After unlearning, it retains high accuracy and achieves a counterfactual gap of only 7.38%.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.26814 — 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 2026-10-08T09:26:35.676Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).