Abstract:Subgraph pattern detection aims to uncover complex interaction structures in graphs. However, state-of-the-art graph neural network (GNN)-based solutions assume centralized access to the entire graph. When graphs are instead distributed across multiple parties, client-local GNN computations diverge from those of a centralized model, resulting in a representation-equivalence gap. We formalize this as a structural observability problem, where subgraph patterns crossing partition boundaries become locally unidentifiable. To bridge this gap, we propose a per-step, layer-wise embedding exchange framework in which clients synchronize intermediate node representations at each layer of the forward pass, without exposing raw features or labels. Under an extended-subgraph assumption and shared model parameters across clients, this framework recovers the same node representations as a centralized GNN over the full graph. Experiments on synthetic directed multigraphs with cycles, bicliques, and scatter-gather patterns show that embedding exchange and federated parameter aggregation are complementary rather than interchangeable: their combination recovers most of the representation gap, provided exchanged embeddings are fresh per-step rather than stale per-epoch.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.06433 [cs.LG] |
| (or arXiv:2605.06433v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06433 arXiv-issued DOI via DataCite (pending registration) |
From: Selin Ceydeli [view email]
[v1]
Thu, 7 May 2026 15:35:37 UTC (333 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。