Metraipolis › archive › dc_73877f9d5bcb

Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology — arXiv:2609.31712

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31712
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:25.295Z
SHA-256 of the archived text
3629196cb966d328b9cb3c7543b69510aa36277beec72c2ac4b3b2cd9c5d1166
Stable URL of this page
https://metraipolis.com/documento/dc_73877f9d5bcb

How to cite

Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology — arXiv:2609.31712 — arXiv (en), https://arxiv.org/abs/2609.31712 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73877f9d5bcb (Metraipolis archive dc_73877f9d5bcb, sha256 3629196cb966d328b9cb3c7543b69510aa36277beec72c2ac4b3b2cd9c5d1166)
BibTeX
@misc{dc73877f9d5bcb,
  title = {Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology — arXiv:2609.31712},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31712},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73877f9d5bcb; sha256 3629196cb966d328b9cb3c7543b69510aa36277beec72c2ac4b3b2cd9c5d1166},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31712. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multiple instance learning (MIL) is widely used in computational pathology because it enables weakly supervised analysis of whole-slide images (WSIs) without requiring patch-level annotations. In attention-based MIL, instances with high attention scores are often interpreted as diagnostically important regions and used as visual explanations. However, attention scores alone cannot determine whether selected high-attention instances are significantly different from normal instances, limiting the reliability of attention-based explanations. In this paper, we formulate the evaluation of high-attention instances as a statistical hypothesis testing problem. Specifically, we assess whether a selected high-attention instance significantly deviates from a representative normal reference instance selected based on feature similarity. A major challenge is that both the target instance and the reference instance are selected through data-dependent procedures, rendering standard hypothesis testing invalid. To address this issue, we introduce a selective inference (SI) framework that explicitly accounts for the selection events induced by attention-based instance selection and adaptive reference selection, thereby enabling the computation of valid selective $p$-values conditional on these events. Experiments demonstrate Type-I error control on synthetic and MNIST-based data and practical applicability to pathological WSIs, with higher statistical power than the conventional over-conditioning approach.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.31712 — 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 2026-10-07T22:14:28.529Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).