Metraipolis › archive › dc_283045b18797

TopoSHAP: Shapley for Explainable and Efficient Topological Deep Learning — arXiv:2611.08789

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08789
License (as archived)
CC0-1.0
Archived
2026-11-09T22:41:15.765Z
SHA-256 of the archived text
b3b2528a9d8ba229aa34a6abf07e163a1b55a3b4562a356fd59ea36605aa8b08
Stable URL of this page
https://metraipolis.com/documento/dc_283045b18797

How to cite

TopoSHAP: Shapley for Explainable and Efficient Topological Deep Learning — arXiv:2611.08789 — arXiv (en), https://arxiv.org/abs/2611.08789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_283045b18797 (Metraipolis archive dc_283045b18797, sha256 b3b2528a9d8ba229aa34a6abf07e163a1b55a3b4562a356fd59ea36605aa8b08)
BibTeX
@misc{dc283045b18797,
  title = {TopoSHAP: Shapley for Explainable and Efficient Topological Deep Learning — arXiv:2611.08789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_283045b18797; sha256 b3b2528a9d8ba229aa34a6abf07e163a1b55a3b4562a356fd59ea36605aa8b08},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Topological deep learning (TDL) extends learning on graphs, such as molecules or social networks, to higher-order structures, such as rings in a molecule or groups in a social network. Explaining which of these structures drive a model's predictions, and which architectural components matter most for its performance, remains challenging. We introduce TopoSHAP, an efficient and general explanation framework that addresses both questions across topological domains and model architectures. TopoSHAP-cell assigns Shapley values to topological data cells and extracts compact explanations. These explanations match or outperform graph-based counterparts on GraphXAI benchmark data while running up to 112$\times$ faster. They also reveal advantageous topological feature design, leading to measured improvements in explanation recovery and predictive accuracy. On the architecture side, TopoSHAP-neighbor explains how neighborhoods contribute to model performance, and turns these evaluations into a backward-elimination search that identifies smaller, competitive architectures early in training. This is up to $11.3\times$ cheaper than traditional TDL training sweeps.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.08789 — 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 2026-11-09T22:33:47.141Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).