Metraipolis › archive › dc_5fccec72eafd
Rethinking One-Shot Federated Graph Learning: Training-Free Statistical Estimation — arXiv:2609.06154
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06154
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:56:39.483Z
- SHA-256 of the archived text
4a5523e28523e054385b402903df847183ea3ca72c99e412fed2df579f7529df- Stable URL of this page
https://metraipolis.com/documento/dc_5fccec72eafd
How to cite
Rethinking One-Shot Federated Graph Learning: Training-Free Statistical Estimation — arXiv:2609.06154 — arXiv (en), https://arxiv.org/abs/2609.06154 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5fccec72eafd (Metraipolis archive dc_5fccec72eafd, sha256 4a5523e28523e054385b402903df847183ea3ca72c99e412fed2df579f7529df)
BibTeX
@misc{dc5fccec72eafd,
title = {Rethinking One-Shot Federated Graph Learning: Training-Free Statistical Estimation — arXiv:2609.06154},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06154},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5fccec72eafd; sha256 4a5523e28523e054385b402903df847183ea3ca72c99e412fed2df579f7529df},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06154. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
One-shot federated graph learning generally aims to train Graph Neural Networks (GNNs) across clients with disconnected subgraphs in a single communication round. Existing methods predominantly design advanced optimization strategies under the premise that local GNN training is indispensable. However, empirical observations reveal that under extreme non-IID conditions, local GNN training suffers from severe cross-client representation misalignment, becoming a major source of error rather than a remedy. Motivated by this, we reformulate one-shot FGL as a statistical estimation problem. We propose SPEAR (Statistical Prototype Estimation with Adaptive Reliability), a completely training-free framework that directly computes topology-smoothed class prototypes from local graphs in the original feature space. The server then aggregates these prototypes using a sample-size-adaptive shrinkage estimator that down-weights unreliable local estimates, producing robust global class prototypes. Extensive experiments across seven benchmarks demonstrate that SPEAR consistently achieves state-of-the-art accuracy under extreme heterogeneity. Moreover, SPEAR delivers at least an order-of-magnitude speedup over all baselines, reaching several orders of magnitude against generative and distillation-based methods. Our findings suggest that training-free statistical estimation, rather than local GNN optimization, provides the key to robust and efficient one-shot federated graph learning. The code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.06154 — 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 2026-10-16T13:39:42.848Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).