Metraipolis › archive › dc_653ef085a25f

Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation — arXiv:2610.02517

Source
arXiv
Original
https://arxiv.org/abs/2610.02517
License (as archived)
CC0-1.0
Archived
2026-10-05T23:09:26.941Z
SHA-256 of the archived text
e3f67ebe43a9f2bd75d0f569ae6f6fa76222c82ff01dcb51d556d3586da52f79
Stable URL of this page
https://metraipolis.com/documento/dc_653ef085a25f

How to cite

Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation — arXiv:2610.02517 — arXiv, https://arxiv.org/abs/2610.02517 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_653ef085a25f (Metraipolis archive dc_653ef085a25f, sha256 e3f67ebe43a9f2bd75d0f569ae6f6fa76222c82ff01dcb51d556d3586da52f79)
BibTeX
@misc{dc653ef085a25f,
  title = {Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation — arXiv:2610.02517},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02517},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_653ef085a25f; sha256 e3f67ebe43a9f2bd75d0f569ae6f6fa76222c82ff01dcb51d556d3586da52f79},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02517. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection and observational constraints, severely limiting the effectiveness of modern graph learning pipelines. While existing Graph Data Augmentation (GDA) methods attempt to refine graph structures for improved downstream performance, they are typically label-dependent, computationally expensive, and inherently transductive, limiting their applicability in practical scenarios. In this work, we present a novel feature-centric graph data augmentation framework that bypasses explicit structure modeling by operating directly in the embedding space. Through a self-supervised inverse masking process, our method captures latent ties between observed and complete graphs, enabling recovery of unobserved structural signals through refined node representations. To enhance robustness under noisy and sparse supervision, we introduce a message regularizer and a bootstrap strategy for effective training and generalization. Evaluated on ten graph datasets spanning multiple domains, our approach, SelfAug, consistently outperforms state-of-the-art methods in both accuracy and efficiency across inductive and cold-start settings, highlighting its potential as a scalable and generalizable solution for real-world graph learning scenarios.

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/2610.02517 — 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 2026-10-05T23:01:38.595Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).