arXiv Machine Learning June 30, 2026 By Davide Domini, Gianluca Aguzzi, Ivana Dusparic, Danilo Pianini, Mirko Viroli

Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning

Read the original on arXiv Machine Learning →

arXiv:2606. 30499v1 Announce Type: new Abstract: Federated Learning often suffers under non-independently and identically distributed data, where a single global model may fail to represent the diversity of client distributions.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 16

Single-Round Clustered Federated Learning via Data Collaboration Analysis for Non-IID Data

arXiv:2601. 09304v2 Announce Type: replace Abstract: Federated Learning (FL) enables distributed learning across multiple clients without sharing raw data.

By Sota Sugawara, Yuji Kawamata, Akihiro Toyoda, Tomoru Nakayama, Yukihiko Okada

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

Jun 16

CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings

arXiv:2506. 22427v2 Announce Type: replace-cross Abstract: We propose CLoVE (Clustering of Loss Vector Embeddings), a novel algorithm for Clustered Federated Learning (CFL).

By Randeep Bhatia, Nikos Papadis, Murali Kodialam, TV Lakshman, Sayak Chakrabarty

rag benchmarks

arXiv AI

Jun 17

C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift

arXiv:2606. 18003v1 Announce Type: cross Abstract: Collective Adaptive Systems (CAS) increasingly rely on machine learning to let each node learn from locally sensed data, aligning its behavior with the surrounding environment.

By Davide Domini, Gianluca Aguzzi, Lorenzo Pellegrini, Mirko Viroli, Lukas Esterle

robotics safety

arXiv Machine Learning

Jun 8

Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizers

arXiv:2606. 06687v1 Announce Type: new Abstract: We investigate cluster formation, involving the number and composition of clusters, in decentralized federated learning (FL) with heterogeneous machine learning (ML) optimizers.

By Su Wang, Mung Chiang, H. Vincent Poor

Hugging Face Trending Papers

Jul 29

FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning

Federated learning (FL) enables collaborative learning over decentralized data silos without centralizing raw data. However, heterogeneous local architectures often induce non-aligned representation spaces, making it difficult to transfer global knowledge across silos.

efficiency safety

Related stories

Single-Round Clustered Federated Learning via Data Collaboration Analysis for Non-IID Data

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

CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings

C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift

Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizers

FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning