Metraipolis › archive › dc_298289cd6b2a

Generating Intervention Hypotheses using Explainable Explanations on Graphs: G2I, a Two-Stage Greedy Framework — arXiv:2608.23835

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23835
License (as archived)
CC0-1.0
Archived
2026-10-18T06:27:36.907Z
SHA-256 of the archived text
9b8315edf45a9dfb2e12c0e5152b6eb456d278896ed2ec25c200dda543e2b924
Stable URL of this page
https://metraipolis.com/documento/dc_298289cd6b2a

How to cite

Generating Intervention Hypotheses using Explainable Explanations on Graphs: G2I, a Two-Stage Greedy Framework — arXiv:2608.23835 — arXiv (en), https://arxiv.org/abs/2608.23835 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_298289cd6b2a (Metraipolis archive dc_298289cd6b2a, sha256 9b8315edf45a9dfb2e12c0e5152b6eb456d278896ed2ec25c200dda543e2b924)
BibTeX
@misc{dc298289cd6b2a,
  title = {Generating Intervention Hypotheses using Explainable Explanations on Graphs: G2I, a Two-Stage Greedy Framework — arXiv:2608.23835},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23835},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_298289cd6b2a; sha256 9b8315edf45a9dfb2e12c0e5152b6eb456d278896ed2ec25c200dda543e2b924},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23835. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-world decision-making in public health and social science can greatly benefit from predictive models, yet translating predictions into effective interventions requires explaining the model behavior. While Graph Neural Networks (GNNs) are well-suited for modeling relational data, existing explanation methods largely operate at the node level and fall short of supporting actionable, network-level intervention design. Existing counterfactual GNN explainers, such as CF-GNNExplainer and CF$^2$, rely on continuous mask optimization over features and edges, which implicitly assume feasible edge manipulation, may allocate effort to immutable or non-actionable attributes, and incur substantial computational overhead. Further, the method of arriving at the explanation itself is difficult to explain to a domain specialist who is not an AI expert. Can simple methods generate good explanations? To explore this, we reframe counterfactual explanation as an intervention design problem. At the local level, we generate counterfactuals via a greedy search that directly identifies minimal, actionable changes to node features and neighbor-level conditions. We derive conditions under which the greedy search provides guarantees, and empirically show that these conditions are approximately met. These counterfactuals are converted into interpretable rules suitable for real-world intervention. At the network level, we formulate intervention selection as a Disjunctive Normal Form (DNF) coverage problem under a budget constraint, which is nondecreasing and approximately submodular, enabling a greedy algorithm with theoretical guarantees. Experiments on synthetic graphs and real-world suicide risk networks demonstrate that our approach produces scalable, cost-effective intervention strategies with significantly improved efficiency over mask-based counterfactual methods.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-26 in cs.SI).
Categorie arXiv: Machine Learning (cs.LG) ; Social and Information Networks (cs.SI).
Pagina del lavoro: https://arxiv.org/abs/2608.23835 — 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 2026-10-18T06:27:15.927Z dalla pagina https://arxiv.org/catchup/cs.SI/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).