Metraipolis › archive › dc_156d24cd45ff

A Topological Signature of Learning under Noisy Labels — arXiv:2610.23491

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23491
License (as archived)
CC0-1.0
Archived
2026-10-19T08:43:16.582Z
SHA-256 of the archived text
0c37c8c3e2af3fff662dfdccabb1e33e4352223bb3e73378d688ffad6959bcb7
Stable URL of this page
https://metraipolis.com/documento/dc_156d24cd45ff

How to cite

A Topological Signature of Learning under Noisy Labels — arXiv:2610.23491 — arXiv (en), https://arxiv.org/abs/2610.23491 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_156d24cd45ff (Metraipolis archive dc_156d24cd45ff, sha256 0c37c8c3e2af3fff662dfdccabb1e33e4352223bb3e73378d688ffad6959bcb7)
BibTeX
@misc{dc156d24cd45ff,
  title = {A Topological Signature of Learning under Noisy Labels — arXiv:2610.23491},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23491},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_156d24cd45ff; sha256 0c37c8c3e2af3fff662dfdccabb1e33e4352223bb3e73378d688ffad6959bcb7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23491. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

How does noisy supervision change the representations learned by a neural network? Training accuracy measures agreement with training labels but provides little information about representation geometry. We use persistent homology to track loop structure across distance thresholds in neural activations. Experiments span image classification, text classification, and modular arithmetic. On a fixed CIFAR-10/ResNet-18 training probe, equally sized clean-label and corrupted-label subsets show no detectable persistence difference at epoch 10, whereas corrupted-label subsets have higher persistence at epoch 50. The contrast survives uniform-scale controls, even though predictions match the assigned noisy labels for only 7-11% of corrupted probe examples at that checkpoint. Normalisation preserves the crossover between clean and noisy training trajectories on CIFAR-10/ResNet-18, whereas CIFAR-100/ResNet-18 shows no crossover under any of the five evaluated constructions. In a separate noise-rate calibration comparison across five pipelines, mean activation norm achieves a higher mean in-sample R2 than raw persistence (0.936 versus 0.908). These findings show that noisy supervision leaves a measurable geometric signature even when agreement with corrupted labels is low. Comparing persistence under scale controls with label-fitting measurements offers a way to study how representations respond to label corruption beyond what training accuracy reveals.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.23491 — 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 2026-10-19T08:39:10.157Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).