Metraipolis › archive › dc_f78deb0ab8d2

Certifying Graph Neural Networks Against Label and Structure Poisoning — arXiv:2611.03350

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.03350
License (as archived): CC0-1.0
Archived: 2026-11-03T18:38:59.219Z
SHA-256 of the archived text: 1df4b0b1ee69170ace5ef165516244fa6e9ec8674640302dbb8563ac19da406c
Stable URL of this page: https://metraipolis.com/documento/dc_f78deb0ab8d2

How to cite

Certifying Graph Neural Networks Against Label and Structure Poisoning — arXiv:2611.03350 — arXiv (en), https://arxiv.org/abs/2611.03350 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f78deb0ab8d2 (Metraipolis archive dc_f78deb0ab8d2, sha256 1df4b0b1ee69170ace5ef165516244fa6e9ec8674640302dbb8563ac19da406c)

BibTeX

@misc{dcf78deb0ab8d2,
  title = {Certifying Graph Neural Networks Against Label and Structure Poisoning — arXiv:2611.03350},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03350},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f78deb0ab8d2; sha256 1df4b0b1ee69170ace5ef165516244fa6e9ec8674640302dbb8563ac19da406c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03350. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robust machine learning for graph-structured data has made significant progress against test-time attacks, yet certified robustness to poisoning - where adversaries manipulate the training data - remains largely underexplored. For image data, state-of-the-art poisoning certificates rely on partitioning-and-aggregation schemes. However, we show that these methods fail when applied in the graph domain due to the inherent label and structure sparsity found in common graph datasets, making effective graph-partitioning difficult. To address this challenge, we propose a novel semi-supervised learning framework called deep Self-Training Graph Partition Aggregation (ST-GPA), which enriches each graph partition with informative pseudo-labels and synthetic edges, enabling effective certification against node-label and graph-structure poisoning under sparse conditions. Our method is architecture-agnostic, scales to large numbers of partitions, and consistently and significantly improves robustness guarantees against both label and structure poisoning across multiple benchmarks, while maintaining strong clean accuracy. Overall, our results establish a promising direction for certifiably robust learning on graph-structured data against poisoning under sparse conditions.

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/2611.03350 — 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 2026-11-03T18:12:54.634Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).