Metraipolis › archive › dc_32041a9f2c53

FCx: An algorithm for finding Feasible Counterfactual Explanations — arXiv:2609.19383

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.19383
License (as archived): CC0-1.0
Archived: 2026-10-10T04:08:37.446Z
SHA-256 of the archived text: 77beff53463b3be3ace624459dd1d1c23b932f0e220e1548281cb64286dcdc92
Stable URL of this page: https://metraipolis.com/documento/dc_32041a9f2c53

How to cite

FCx: An algorithm for finding Feasible Counterfactual Explanations — arXiv:2609.19383 — arXiv (en), https://arxiv.org/abs/2609.19383 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_32041a9f2c53 (Metraipolis archive dc_32041a9f2c53, sha256 77beff53463b3be3ace624459dd1d1c23b932f0e220e1548281cb64286dcdc92)

BibTeX

@misc{dc32041a9f2c53,
  title = {FCx: An algorithm for finding Feasible Counterfactual Explanations — arXiv:2609.19383},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19383},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_32041a9f2c53; sha256 77beff53463b3be3ace624459dd1d1c23b932f0e220e1548281cb64286dcdc92},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19383. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Counterfactual (CF) explanations identify changes that alter an input's classification. While existing methods produce realistic and low-cost CFs, they often fail to ensure feasibility, by suggesting non-constructive modifications or incompatible with future changes (e.g., changing an individual's race to secure a job offer). We introduce a refinement of CF explanations that explicitly enforces feasibility. Our approach is the first to efficiently generate CFs that are realistic, low-cost and feasible. We accommodate both hard feasible constraints, specified by domain knowledge users, and soft feasible constraints, inferred automatically via causal inference from the dataset. Our method, Feasible Counterfactual Explanations (FCx), is based on a modified Variational Autoencoder (VAE) optimized with a multi-factor loss function. We measure the cost of a change based on the absolute change in values (proximity) as well as the number of features changed (sparsity) while realism is measured based on the LOF for density estimation, guaranteeing that CFs reside in densely populated regions. Extensive experiments on four public datasets show that our approach matches state-of-the-art performance across multiple metrics while guaranteeing feasibility.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.19383 — 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 2026-10-10T03:48:18.254Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).