Metraipolis › archive › dc_6e5fef6cbbc3

Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths — arXiv:2610.22126

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22126
License (as archived)
CC0-1.0
Archived
2026-10-16T09:31:01.608Z
SHA-256 of the archived text
03ccebdc8d9f836b1816caeb65df39ba3785bf4e0b045b28d3d48c257cbbc606
Stable URL of this page
https://metraipolis.com/documento/dc_6e5fef6cbbc3

How to cite

Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths — arXiv:2610.22126 — arXiv (en), https://arxiv.org/abs/2610.22126 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e5fef6cbbc3 (Metraipolis archive dc_6e5fef6cbbc3, sha256 03ccebdc8d9f836b1816caeb65df39ba3785bf4e0b045b28d3d48c257cbbc606)
BibTeX
@misc{dc6e5fef6cbbc3,
  title = {Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths — arXiv:2610.22126},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22126},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e5fef6cbbc3; sha256 03ccebdc8d9f836b1816caeb65df39ba3785bf4e0b045b28d3d48c257cbbc606},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22126. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing feature attribution methods that account for feature dependencies do not scale to high dimensions. We propose causal integrated gradients (CIG) and causal expected gradients (CEG), which extend integrated gradients to incorporate prior causal structure among input features while retaining its computational efficiency and, under conditions on the causal graph, its axiomatic guarantees. In many settings, some causal structure between features is already known, for example, that a transcription factor causally regulates a target gene's expression. Yet existing gradient-based methods cannot exploit this structure, instead crediting a feature's downstream effects over its true upstream cause, such as ranking the target gene above the transcription factor that regulates it. Our key idea is to embed this causal structure by routing the integration path along the causal graph. The method thereby decomposes each feature's attribution into a direct effect and effects mediated through its causal descendants. We evaluate CIG in three settings of increasing realism. First, on a synthetic benchmark with a known causal model, CIG's attributions best match the ground-truth causal effect from Pearl's do-calculus, matching the accuracy of causal Shapley values at a fraction of the computational cost. Second, on simulated single-cell gene expression data with a known gene regulatory network (Dyngen), CIG most accurately recovers the transcription factors driving the simulation. Third, on real interferon-$\beta$ stimulation data, where only an approximate causal graph is available, CIG better prioritizes the transcription factors driving the measured response than DeepSHAP and integrated gradients. Together, these results show that incorporating causal structure into gradient-based attributions recovers upstream drivers that existing methods miss, without sacrificing scalability.

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/2610.22126 — 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 2026-10-16T08:44:18.028Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).