Metraipolis › archive › dc_ff964fca15aa
Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs — arXiv:2610.10520
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10520
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:36:33.517Z
- SHA-256 of the archived text
d050a6833b8187eb123016327c115869098785ed584a6be1138d080c43352adf- Stable URL of this page
https://metraipolis.com/documento/dc_ff964fca15aa
How to cite
Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs — arXiv:2610.10520 — arXiv (en), https://arxiv.org/abs/2610.10520 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff964fca15aa (Metraipolis archive dc_ff964fca15aa, sha256 d050a6833b8187eb123016327c115869098785ed584a6be1138d080c43352adf)
BibTeX
@misc{dcff964fca15aa,
title = {Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs — arXiv:2610.10520},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10520},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff964fca15aa; sha256 d050a6833b8187eb123016327c115869098785ed584a6be1138d080c43352adf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10520. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
GNN-to-MLP distillation aims to retain the predictive accuracy of a message-passing teacher while deploying a graph-free MLP at inference. Existing methods mainly transfer node-wise predictions or use confidence-based reweighting, but they do not specify where the student should preserve the teacher's graph-induced geometry. We show that this omission leads to two spectral failure modes in the student's representation space. On sparse graphs, the student suffers from spectral underfit, missing high-energy teacher directions concentrated near boundary regions. On dense graphs, it suffers from spectral overfit, retaining spurious directions that the teacher has collapsed through aggregation. Motivated by an energy-weighted teacher-student alignment objective, we propose Graph Geometry-aware MLP (G^2MLP), a training-time distillation framework guided by Ollivier-Ricci curvature. Curvature identifies where the two spectral errors concentrate and is used to allocate supervision between prediction-level and representation-level alignment. The deployed model remains a standard MLP and requires no graph access at inference. Across node-classification benchmarks, G^2MLP consistently improves over graph-free distillation baselines, reduces the teacher-student rank gap in both regimes, and transfers without architectural changes to Graph Transformer teachers and link prediction. 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/2610.10520 — 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 2026-10-08T12:14:15.355Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).