Metraipolis › archive › dc_ce1407dd57c4
NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption — arXiv:2608.16038
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.16038
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:06:53.879Z
- SHA-256 of the archived text
db64cd88043a460b7ac4c4bc189d3a36b3d0bfafe2d647243087219d83433db5- Stable URL of this page
https://metraipolis.com/documento/dc_ce1407dd57c4
How to cite
NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption — arXiv:2608.16038 — arXiv (en), https://arxiv.org/abs/2608.16038 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce1407dd57c4 (Metraipolis archive dc_ce1407dd57c4, sha256 db64cd88043a460b7ac4c4bc189d3a36b3d0bfafe2d647243087219d83433db5)
BibTeX
@misc{dcce1407dd57c4,
title = {NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption — arXiv:2608.16038},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.16038},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce1407dd57c4; sha256 db64cd88043a460b7ac4c4bc189d3a36b3d0bfafe2d647243087219d83433db5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16038. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Post-hoc Graph Neural Network (GNN) explainers commonly follow a Perturb-Query paradigm, inferring the importance of graph elements based on queried predictions to perturbed inputs. However, such perturbations often introduce substantial distribution shift, undermining the reliability of the queried predictions used to derive explanations. While existing efforts mainly improve perturbed graphs or stabilize model predictions on them, we revisit the perturbation mechanism itself. We show that the widely used Element-wise Masking(EM) suppresses edge-induced messages toward zero, causing deterministic scale contraction that accumulates across message-passing layers, a phenomenon we term Scale Drift. Consequently, prediction changes under EM may conflate information corruption with deviations in propagation scale. As a scale-stable alternative to EM, we introduce Noise Corruption (NC), which perturbs each message through matched-norm random-direction corruption while preserving the expected squared message norm. Building on NC, we propose NICE, a Noise Corruption-based explanation framework, which learns a Stochastic Restoration Boundary (SRB) under NC-induced uncertainty, balancing target-prediction restoration against compactness. Furthermore, Boundary-Integrated Gradient (BIG) converts this boundary into edge attributions by accumulating each edge's contribution to reducing restoration risk along the restoration path. Experiments across multiple benchmarks demonstrate stronger explanation performance and model faithfulness while confirming that NC substantially reduces the Scale Drift induced by masking. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.16038 — 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 2026-10-18T16:29:14.070Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).