arXiv Machine Learning November 2, 2026 By Anders Eklund

Federated learning for unpaired multimodal data

Read the original on arXiv Machine Learning →

The paper introduces a federated learning framework for training multimodal foundation models on unpaired, fragmented data distributed across private nodes. It uses a small public anchor set and Gram matrices to align disjoint private manifolds via centered kernel alignment, avoiding transmission of private samples. Additional techniques include subspace‑stabilized fine‑tuning to handle large transformers and precision‑weighted averaging to downweight uncertain nodes.

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.

arXiv Machine Learning

Jul 20

Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework

arXiv:2607. 15687v1 Announce Type: new Abstract: Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offering richer semantic signals than single-modality graphs.

By Xunkai Li, Guohao Fu, Yuming Ai, Zhengyu Wu, Hongchao Qin, Rong-Hua Li, Guoren Wang

fine-tuning multimodal safety

arXiv Machine Learning

Jul 28

FedTaste: Topology-Aware Structural Transfer for Multimodal Federated Learning with Missing Modalities

arXiv:2607. 23245v1 Announce Type: cross Abstract: Multimodal Federated Learning is often challenged by arbitrary modality missingness and Non-IID data distributions, which lead to severe representation drift and hinder effective collaboration across clients.

By Haochen Liang, Jie Zhang, Hideya Ochiai

multimodal safety

arXiv AI

Jul 8

MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning

arXiv:2409. 06067v3 Announce Type: replace Abstract: Previous studies on federated learning (FL) often encounter performance degradation due to data heterogeneity among different clients.

By Jianyi Zhang, Hao Frank Yang, Ang Li, Xin Guo, Pu Wang, Haiming Wang, Yiran Chen, Hai Li

llms nlp multimodal benchmarks safety

arXiv Machine Learning

Aug 4

Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach

arXiv:2601. 21369v2 Announce Type: replace Abstract: Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to train graph foundation models, and accommodate the reality of distributed, privacy-restricted data silos.

By Yinlin Zhu, Di Wu, Xianzhi Zhang, Yuming Ai, Xunkai Li, Miao Hu, Guocong Quan

llms rag fine-tuning efficiency safety

arXiv AI

Jul 9

Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning

arXiv:2607. 07565v1 Announce Type: cross Abstract: One-shot federated learning (OSFL) addresses the communication overhead of federated learning by limiting training to a single round, but doing so without sacrificing model quality is non-trivial, particularly when client data distributions diverge.

By Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek

diffusion safety

arXiv Computer Vision

Oct 2

FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains

FedCKA introduces a Centered Kernel Alignment (CKA)-based method for federated 3D perception that dynamically balances personalization and globalization. By computing layer-wise feature similarities between local client models and a global consensus model, FedCKA generates client‑specific aggregation masks to selectively share representation‑consistent layers. Experiments on a unified multi‑domain nuScenes benchmark demonstrate that FedCKA surpasses established federated baselines, improving average NDS by 7 percentage points.

By Jolle Verhoog, Ali Burak \"Unal, Holger Caesar

benchmarks safety

One email a morning, machine-written

Related stories

Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework

FedTaste: Topology-Aware Structural Transfer for Multimodal Federated Learning with Missing Modalities

MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning

Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach

Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning

FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains