Metraipolis › archive › dc_129fbbce92f1

More Is Better? Exploring Latent Correspondence in Federated Hypergraph Learning — arXiv:2610.39362

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39362
License (as archived)
CC0-1.0
Archived
2026-10-31T06:19:39.598Z
SHA-256 of the archived text
ad6c6798caa4c47e86121b4dfd927ecfecd6e9c71d2dc8b502abb7575c34e1f3
Stable URL of this page
https://metraipolis.com/documento/dc_129fbbce92f1

How to cite

More Is Better? Exploring Latent Correspondence in Federated Hypergraph Learning — arXiv:2610.39362 — arXiv (en), https://arxiv.org/abs/2610.39362 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_129fbbce92f1 (Metraipolis archive dc_129fbbce92f1, sha256 ad6c6798caa4c47e86121b4dfd927ecfecd6e9c71d2dc8b502abb7575c34e1f3)
BibTeX
@misc{dc129fbbce92f1,
  title = {More Is Better? Exploring Latent Correspondence in Federated Hypergraph Learning — arXiv:2610.39362},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39362},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_129fbbce92f1; sha256 ad6c6798caa4c47e86121b4dfd927ecfecd6e9c71d2dc8b502abb7575c34e1f3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39362. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated hypergraph learning with latent cross-client hyperedge correspondence poses fundamental identifiability and computational challenges, as the same local release can correspond to multiple global hypergraph structures. We characterize the tractability of recovering these latent correspondences, showing tractable pairwise assignment but generally intractable multi-client hyperedge matching. Building on this characterization, we derive a cross-entropy decomposition that reveals when local prediction can outperform predictors fitted with additional cross-client information. Motivated by this principle, we introduce Federated Adaptive Spectral Training with Representation Alignment (FedASTRA), which learns correspondence-invariant diffusion representations through adaptive heat diffusion and masked latent prediction while communicating model parameters only. We establish its asymptotic optimality with respect to the permitted local information and prove global population-risk convergence under explicit conditions on recovery, representation, and update alignment. Experiments on eight real-world datasets demonstrate the effectiveness of FedASTRA against identifier-free federated graph and hypergraph methods. On ogbn-papers100M, FedASTRA reaches the performance-communication Pareto frontier, achieving 50.07 Accuracy and 29.73 Macro-F1 while communicating only 59.60 MiB per round.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2610.39362 — 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 2026-10-31T06:07:53.396Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).