Metraipolis › archive › dc_149e11779183
Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks — arXiv:2609.13712
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13712
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:47:13.191Z
- SHA-256 of the archived text
08b75c468e2cfd0cfa9360da931894f497fca981a30685ebf601ec65b9124168- Stable URL of this page
https://metraipolis.com/documento/dc_149e11779183
How to cite
Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks — arXiv:2609.13712 — arXiv (en), https://arxiv.org/abs/2609.13712 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_149e11779183 (Metraipolis archive dc_149e11779183, sha256 08b75c468e2cfd0cfa9360da931894f497fca981a30685ebf601ec65b9124168)
BibTeX
@misc{dc149e11779183,
title = {Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks — arXiv:2609.13712},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13712},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_149e11779183; sha256 08b75c468e2cfd0cfa9360da931894f497fca981a30685ebf601ec65b9124168},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13712. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many real-world scenarios can be represented using graph-structured data. However, traditional GNNs that transmit messages based on first-order neighbors have long faced several fundamental contradictions: increasing depth leads to over-smoothing, long-range dependencies cause over-compression, fixed neighborhoods restrict the receptive field, and on heterophilous graphs, topological neighbors become a source of noise. Although many works have addressed these issues individually, few mechanisms can simultaneously alleviate all of these challenges. To address the aforementioned problems, we propose a Position Encoding-Based Deformable Spatial Aggregation Module (PEBDSAM) that solves them all in one step. Specifically, we utilize a deformable mechanism in the position space to identify relevant nodes to supplement the original first-order neighbor information of GNNs, allowing traditional GNNs to adapt to heterophilous scenarios. Through diagnostic experiments, we obtained several major findings: current offsets fail to have any effect; subsequently, we analyzed the causes of offset failure and why model performance still improves even after offset failure, pointing out future research directions. Based on these diagnostic experiments, we streamlined the original PEBDSAM, resulting in a simplified version, which we call the Position Encoding-Based Spatial Aggregation Module (PEBSAM). In addition, we propose a PEBSAM-Speed to adapt to large datasets. Finally, we designed the module to be plug-and-play and applied it to GCN, GAT, GIN, and GraphSAGE, achieving desirable results on three homophilous datasets and six heterophilous graph datasets. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.13712 — 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 2026-10-15T22:29:03.119Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).