arXiv Machine Learning

FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space

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.

arXiv Machine Learning

2d ago

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

agents safety

arXiv AI

Jun 16

Guiding Federated Graph Recommendation with LLM-encoded knowledge

arXiv:2606. 15277v1 Announce Type: cross Abstract: Graph-based recommender systems are highly effective at extracting collaborative signals from user--item interactions, and federated learning (FL) allows these models to be trained while preserving user privacy.

By Thi Minh Chau Nguyen, Hien Trang Nguyen, Duc Anh Nguyen, Van Ho-Long, Thanh Trung Huynh, Zhao Ren

llms rag benchmarks safety

arXiv AI

Jun 3

Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation

arXiv:2606. 03307v1 Announce Type: cross Abstract: Graph foundation models (GFMs) emerged as a dominant paradigm in graph representation learning by leveraging large-scale pre-training for cross-domain inference.

By Yifan Jin, Qirui Ji, Bin Qin, Jiangmeng Li, Lixiang Liu, Fuchun Sun, Changwen Zheng

rag benchmarks

arXiv AI

Jul 10

FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning

arXiv:2607. 08368v1 Announce Type: new Abstract: With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of federated learning.

By Lingyu Qiu, Daniela Annunziata, Stefano Izzo, Fabio Giampaolo, Francesco Piccialli

fine-tuning efficiency benchmarks

arXiv Machine Learning

Jun 5

The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning

arXiv:2606. 06397v1 Announce Type: new Abstract: Current evaluation practices in relational learning rely heavily on flat leaderboards that average performance across heterogeneous datasets, implicitly assuming a uniform underlying structure.

By Shuo Wang, Xiangyu Wang, Quanxin Wang, Bailin Wu, Bokui Wang, Shunyang Huang, Boyan Deng, Haonan Liu, Ruiyi Fang, Zhenxiang Xu, Boyu Wang, Zhao Kang

benchmarks safety

Hugging Face Trending Papers

Jul 9

FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning

With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of federated learning. Although one-shot federated learning alleviates this problem by minimizing communication rounds, existing iterative fine-tuning or knowledge distillation methods still face challenges such as high server-side computational costs and hyperparameter sensitivity.

fine-tuning efficiency benchmarks

arXiv Machine Learning

Jul 14

COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication

arXiv:2605. 11165v3 Announce Type: replace Abstract: Federated learning (FL) in heterogeneous environments remains challenging because client models often differ in both architecture and data distribution.

By Ben Rachmut, Luise Ge, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik

efficiency benchmarks

arXiv AI

5d ago

Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts

arXiv:2602.06859v3 Announce Type: replace-cross Abstract: Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to e...

By Xinyu Zhao, Qingyun Sun, Jiayi Luo, Xingcheng Fu, Jianxin Li

rag benchmarks safety

arXiv AI

Jul 28

AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt

arXiv:2512. 24625v3 Announce Type: replace-cross Abstract: Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and vehicle fleet management.

By Zijian Zhao, Yitong Shang, Sen Li

safety

arXiv Machine Learning

3d ago

Similarity-Aware Personalized Federated Learning in Heterogeneous Environments

arXiv:2609.02241v1 Announce Type: new Abstract: Federated Learning (FL) allows decentralized clients to train models collaboratively while preserving data privacy. However, distribution mismatch acro...

By Arun Kumar A V, Sunil Gupta, Dang Ngyuen, Bao Duong, Dat Phan Trong

benchmarks safety

arXiv Machine Learning

Aug 13

Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning

arXiv:2608. 12108v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training across distributed clients while keeping data local.

By Mirko Konstantin, Stefan Zachow, Anirban Mukhopadhyay

arXiv Machine Learning

Aug 28

Aitchison Embeddings for Learning Compositional Graph Representations

The paper introduces a compositional graph embedding framework based on Aitchison geometry, where nodes are represented as simplex-valued mixtures over latent archetypal factors. By embedding these mixtures using isometric log-ratio coordinates, the method preserves Aitchison distances while allowing unconstrained optimization in Euclidean space, yielding intrinsically interpretable embeddings. The approach achieves competitive performance on node classification and link prediction tasks and enables principled component restriction through subcompositional coherence, allowing analysis of how archetype groups influence representations and predictions.

By Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis, Giannis Nikolentzos

rag

Related stories