← Back to all news
arXiv Machine Learning By Jiahong Liu, Ram Samarth B B, Xinyu Fu, Menglin Yang, Weixi Zhang, Rex Ying, Irwin King

FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space

Read the original on arXiv Machine Learning →

FlatLand is a personalized federated learning approach that embeds each client’s graph data into a tailored Lorentz space, leveraging hyperbolic geometry’s negative curvature to model graph structures. The method introduces a parameter decoupling strategy that separates client‑specific heterogeneity (time‑like parameters) from shared knowledge (space‑like parameters), allowing direct aggregation without extra similarity estimation. Experiments on various federated graph learning tasks show that FlatLand outperforms existing methods, especially in low‑dimensional settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 4

From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning

The paper surveys collaborative learning methods that move beyond traditional Euclidean data to graph-structured data. It reviews foundational principles for Euclidean settings—learning effectiveness, efficiency, and privacy—and then extends the discussion to graph data, presenting a taxonomy of distribution scenarios, statistical heterogeneities, and standardized problem formulations. The survey also outlines open challenges and future research directions in this emerging field.

By R\'emi Bourgerie, \v{S}ar\=unas Girdzijauskas, Viktoria Fodor
agentssafety
More like this →
Hugging Face Trending Papers
6d ago

Euclidean Crowding-Driven Adaptive Euclidean-Hyperbolic Graph Learning

The paper investigates why hyperbolic space outperforms Euclidean space for hierarchical graph data. It quantifies Euclidean crowding by showing that fixed‑dimensional Euclidean embeddings of tree‑like graphs inevitably suffer layer‑wise crowding, leading to weaker generalization bounds. The authors then derive a generalization bound that explains hyperbolic geometry’s advantage and introduce EH‑Fusion, a framework that maps Euclidean GNN representations into hyperbolic space and adaptively fuses both geometries based on neighborhood expansion patterns, with experiments confirming its effectiveness.

ragbenchmarks
More like this →
Hugging Face Trending Papers
4d ago

More Is Better? Exploring Latent Correspondence in Federated Hypergraph Learning

The paper investigates federated hypergraph learning where local hyperedge releases can correspond to multiple global hypergraph structures, highlighting identifiability and computational challenges. It shows that pairwise assignment of latent correspondences is tractable while multi-client hyperedge matching is generally intractable, and introduces FedASTRA—a method that learns correspondence‑invariant diffusion representations via adaptive heat diffusion and masked latent prediction, communicating only model parameters. Experiments on eight real‑world datasets, including ogbn‑papers100M, demonstrate that FedASTRA achieves state‑of‑the‑art performance‑communication trade‑offs, reaching 50.07 % accuracy and 29.73 % Macro‑F1 while sending only 59.60 MiB per round.

diffusionsafety
More like this →