Metraipolis › archive › dc_398ed99484a7

Graph Additive Models disentangling feature, topology, and interactions — arXiv:2610.20662

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20662
License (as archived)
CC0-1.0
Archived
2026-10-16T10:24:58.207Z
SHA-256 of the archived text
fe7c66f570688ceff314c62dc43d37bc5c383e200d508f57ac8e326f692a0b80
Stable URL of this page
https://metraipolis.com/documento/dc_398ed99484a7

How to cite

Graph Additive Models disentangling feature, topology, and interactions — arXiv:2610.20662 — arXiv (en), https://arxiv.org/abs/2610.20662 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_398ed99484a7 (Metraipolis archive dc_398ed99484a7, sha256 fe7c66f570688ceff314c62dc43d37bc5c383e200d508f57ac8e326f692a0b80)
BibTeX
@misc{dc398ed99484a7,
  title = {Graph Additive Models disentangling feature, topology, and interactions — arXiv:2610.20662},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20662},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_398ed99484a7; sha256 fe7c66f570688ceff314c62dc43d37bc5c383e200d508f57ac8e326f692a0b80},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20662. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph Neural Additive Networks (GNANs) have emerged as effective, interpretable-by-design architectures for graph learning. They achieve transparency by combining per-feature shape functions with simple distance-based reweighting. However, GNANs have three limitations. First, node-wise relevance scores aggregate information from all graph nodes, allowing irrelevant nodes to inherit spurious relevance from relevant ones. Second, topology is represented only through shortest-path distances, so structurally distinct graphs may share identical distance profiles. Third, feature and distance information are combined multiplicatively, entangling feature, distance, and interaction effects in a single rescalable term. We introduce AMIGA, which represents topology through a vocabulary of mined motifs and decomposes each node contribution into three additive channels: feature, structure, and feature-structure interaction. The channels are centered around a graph-balanced training baseline, making the decomposition well-defined and unique under the chosen reference distribution. Across ten graph classification and regression benchmarks, AMIGA outperforms GNAN on most datasets and narrows the gap with standard black-box GNNs. Because each channel is centered and assigned to a single node, AMIGA produces node-local explanations that reconstruct the model output exactly and support interpretation at multiple levels of granularity.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.20662 — 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 2026-10-16T08:48:02.832Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).