Metraipolis › archive › dc_4037494cf70d

Post-Hoc Feature Selection Layer for Neural Networks Interpretability — arXiv:2610.31420

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31420
License (as archived)
CC0-1.0
Archived
2026-10-23T15:16:39.965Z
SHA-256 of the archived text
4402e178a27a9431f2ba9aef3036e2014bbc9e6db8cc335b83ff7ff3dcebedb4
Stable URL of this page
https://metraipolis.com/documento/dc_4037494cf70d

How to cite

Post-Hoc Feature Selection Layer for Neural Networks Interpretability — arXiv:2610.31420 — arXiv (en), https://arxiv.org/abs/2610.31420 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4037494cf70d (Metraipolis archive dc_4037494cf70d, sha256 4402e178a27a9431f2ba9aef3036e2014bbc9e6db8cc335b83ff7ff3dcebedb4)
BibTeX
@misc{dc4037494cf70d,
  title = {Post-Hoc Feature Selection Layer for Neural Networks Interpretability — arXiv:2610.31420},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31420},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4037494cf70d; sha256 4402e178a27a9431f2ba9aef3036e2014bbc9e6db8cc335b83ff7ff3dcebedb4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31420. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The interpretability of complex neural networks remains a critical challenge, especially for models already deployed in high-stakes domains. To address this, we adapted the Feature Selection Layer (FSL) to optimize feature weights post-training, a variant we term post-hoc FSL. Our approach reframes the FSL as a lightweight, trainable module that integrates with already frozen pre-trained models on tabular datasets to highlight the features the original model considers most important. This post-hoc FSL learns feature relevance by fine-tuning its weights based on the original model's learned outputs. Crucially, this process is non-invasive, operating without altering the original model's architecture or its learned parameters. We conducted our experiments using both statistical and visual metrics, including accuracy, F1 score, recall, precision, weighted t-SNE and silhouette score, and also analyzed the stability of the post-hoc FSL on high-dimensional synthetic and real-world tabular datasets. We compared the post-hoc FSL feature weighting method using these metrics against the original embedded FSL and other post-hoc interpretability methods, such as Integrated Gradients, Noise Tunnel, DeepLIFT, Gradient SHAP, and Feature Ablation. Experimental results demonstrate that the post-hoc FSL feature weighting method successfully identified relevant features across the different datasets, maintaining the predictive power of the original neural network while enhancing its interpretability.

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/2610.31420 — 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 2026-10-23T15:09:08.622Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).