João Kenji Suwa, João Pedro Silveira e Silva, Bruno Iochins Grisci · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31420 · open-access PDF
La interpretabilidad de las complejas redes neuronales sigue siendo un desafío crítico, especialmente para los modelos ya implantados en dominios de alta apuesta. Para abordar esto, adaptamos la capa de selección de características (FSL) para optimizar los pesos de características post-entrenamiento, una variante que llamamos FSL post-hoc. Nuestro enfoque redefine el FSL como un módulo ligero, entrenable que se integra con modelos pre-entrenados ya congelados en conjuntos de datos tabulares para destacar las características que el modelo original considera más importantes.
Machine translation (Meta M2M100); the English original follows.
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 out
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31420, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange