Metraipolis › archive › dc_7f2b09ab53dd

Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition — arXiv:2610.23623

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23623
License (as archived)
CC0-1.0
Archived
2026-10-19T09:10:22.670Z
SHA-256 of the archived text
47f3fd7a27c58506c7b9b69babeaf00a03ad92a0583ef9a78146b34e0cfc1976
Stable URL of this page
https://metraipolis.com/documento/dc_7f2b09ab53dd

How to cite

Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition — arXiv:2610.23623 — arXiv (en), https://arxiv.org/abs/2610.23623 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f2b09ab53dd (Metraipolis archive dc_7f2b09ab53dd, sha256 47f3fd7a27c58506c7b9b69babeaf00a03ad92a0583ef9a78146b34e0cfc1976)
BibTeX
@misc{dc7f2b09ab53dd,
  title = {Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition — arXiv:2610.23623},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23623},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f2b09ab53dd; sha256 47f3fd7a27c58506c7b9b69babeaf00a03ad92a0583ef9a78146b34e0cfc1976},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23623. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing multi-task active learning (MTL-AL) methods predominantly rely on linear scalarization of heterogeneous objectives such as uncertainty, diversity, and gradient conflict. We argue that this entangled formulation is fundamentally limited, as linear combination fails to capture Pareto-optimal trade-offs under conflicting objectives. We propose a shift from combination to deconstruction and introduce a principled framework that rethinks MTL-AL along three orthogonal dimensions. First, we identify the Conflict Paradox: although the optimization literature treats gradient conflict as interference to be suppressed, penalizing conflict when ranking candidates is measurably worse than not scoring it at all. We therefore decouple the two concerns: the acquisition function does not score conflict, and the resulting interference is resolved by gradient surgery during training. Second, we introduce Orthogonal Decomposition, separating acquisition into Informativeness and Exploration. This two-stage process, informativeness filtering followed by coverage maximization, prevents "diversity dilution" by excluding uninformative outliers before enforcing diversity. Third, we propose Cross-Task Mutual Information (CTMI), a covariance-based statistic of cross-task dependency computed from MC-dropout task entropies. Extensive experiments on COCO, Cityscapes, and NYUv2, including comparisons against recent MTL-AL and data-selection baselines, demonstrate consistent improvements over state-of-the-art methods, highlighting that structural rethinking of acquisition yields larger gains than incremental heuristic design. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.23623 — 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 2026-10-19T09:06:29.562Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).