paper-with-me

홈 › Papers

FedUMM: A General Framework for Federated Learning with Unified Multimodal Models

2026-01-21 · Zhaolong Su, Leheng Zhao, Xiaoying Wu, Ziyue Xu, Jindong Wang arxiv

Unified multimodal models (UMMs) are emerging as strong foundation models that can do both generation and understanding tasks in a single architecture. However, they are typically trained in centralized settings where all training and downstream datasets are gathered in a central server, limiting the deployment in privacy-sensitive and geographically distributed scenarios. In this paper, we present FedUMM, a general federated learning framework for UMMs under non-IID multimodal data with low communication cost. Built on NVIDIA FLARE, FedUMM instantiates federation for a BLIP3o backbone via parameter-efficient fine-tuning: clients train lightweight LoRA adapters while freezing the foundation models, and the server aggregates only adapter updates. We evaluate on VQA v2 and the GenEval compositional generation benchmarks under Dirichlet-controlled heterogeneity with up to 16 clients. Results show slight degradation as client count and heterogeneity increase, while remaining competitive with centralized training. We further analyze computation--communication trade-offs and demonstrate that adapter-only federation reduces per-round communication by over an order of magnitude compared to full fine-tuning, enabling practical federated UMM training. This work provides empirical experience for future research on privacy-preserving federated unified multimodal models.

📄 PDF Abstract BibTeX arXiv:2601.15390

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningFederated Learning

Similar Papers 제목 키워드 기반

Adaptive Prototype Knowledge Transfer for Federated Learning with Mixed Modalities and Heterogeneous Tasks

2025-02-06 · Keke Gai, Mohan Wang, Jing Yu, Dongjue Wang 외

Multimodal Federated Learning (MFL) enables multiple clients to collaboratively train models on multimodal data while ensuring clients' privacy. However, modality and task heterogeneity hinder clients from learning a uni…

Federated LearningTransfer Learning

FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysis

2026-02-28 · Xianxun Zhu, Zezhong Sun, Imad Rida, Erik Cambria 외 arxiv

Multimodal sentiment analysis in federated learning environments faces significant challenges due to missing modalities, heterogeneous data distributions, and unreliable client updates. Existing federated approaches ofte…

Multimodal Sentiment AnalysisFederated Learning

MHARFedLLM: Multimodal Human Activity Recognition Using Federated Large Language Model

2025-08-03 · Asmit Bandyopadhyay, Rohit Basu, Tanmay Sen, Swagatam Das arxiv

Human Activity Recognition (HAR) plays a vital role in applications such as fitness tracking, smart homes, and healthcare monitoring. Traditional HAR systems often rely on single modalities, such as motion sensors or cam…

Human Activity RecognitionFederated Learning

FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathology

2024-02-24 · Yuanzhe Peng, Jieming Bian, Jie Xu

The fusion of complementary multimodal information is crucial in computational pathology for accurate diagnostics. However, existing multimodal learning approaches necessitate access to users' raw data, posing substantia…

Federated LearningPrivacy Preserving

FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning

2025-11-30 · Haozhe Wu arxiv

We propose FDRMFL, a task-driven multimodal feature extraction framework for federated regression under non-IID data distributions. Extracting predictive features from high-dimensional multimodal inputs is particularly c…

Dimensionality ReductionContrastive Learning