Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigms

• URL: http://arxiv.org/abs/2505.21792v1
• Date: Tue, 27 May 2025 21:47:20 GMT
• Title: Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigms
• Authors: Yuanzhe Peng, Jieming Bian, Lei Wang, Yin Huang, Jie Xu,
• Abstract summary: Multimodal Federated Learning (MFL) aims to improve downstream inference performance and enable distributed training to enhance efficiency and preserve privacy.<n>Despite the growing interest in MFL, there is currently no comprehensive taxonomy that organizes MFL through the lens of different Federated Learning (FL) paradigms.<n>This paper systematically examines MFL within the context of three major FL paradigms: horizontal FL (HFL), vertical FL (VFL), and hybrid FL.
• Score: 5.280048850098648
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Federated Learning (MFL) lies at the intersection of two pivotal research areas: leveraging complementary information from multiple modalities to improve downstream inference performance and enabling distributed training to enhance efficiency and preserve privacy. Despite the growing interest in MFL, there is currently no comprehensive taxonomy that organizes MFL through the lens of different Federated Learning (FL) paradigms. This perspective is important because multimodal data introduces distinct challenges across various FL settings. These challenges, including modality heterogeneity, privacy heterogeneity, and communication inefficiency, are fundamentally different from those encountered in traditional unimodal or non-FL scenarios. In this paper, we systematically examine MFL within the context of three major FL paradigms: horizontal FL (HFL), vertical FL (VFL), and hybrid FL. For each paradigm, we present the problem formulation, review representative training algorithms, and highlight the most prominent challenge introduced by multimodal data in distributed settings. We also discuss open challenges and provide insights for future research. By establishing this taxonomy, we aim to uncover the novel challenges posed by multimodal data from the perspective of different FL paradigms and to offer a new lens through which to understand and advance the development of MFL.

Related papers

• One-shot Federated Learning Methods: A Practical Guide [23.737787001337082]
  One-shot Federated Learning (OFL) is a distributed machine learning paradigm that constrains client-server communication to a single round.<n>This paper presents a systematic analysis of the challenges faced by OFL and thoroughly reviews the current methods.
  arXiv  Detail & Related papers  (2025-02-13T09:26:44Z)
• FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data [56.08867996209236]
  Fine-tuning Multimodal Large Language Models (MLLMs) with Federated Learning (FL) allows for expanding the training data scope by including private data sources.<n>We introduce a benchmark to evaluate the performance of federated fine-tuning of MLLMs across various multimodal heterogeneous scenarios.<n>We develop a general FedMLLM framework that integrates classic FL methods alongside two modality-agnostic strategies.
  arXiv  Detail & Related papers  (2024-11-22T04:09:23Z)
• Heterogeneous Federated Learning: State-of-the-art and Research Challenges [117.77132819796105]
  Heterogeneous Federated Learning (HFL) is much more challenging and corresponding solutions are diverse and complex. New advances in HFL are reviewed and a new taxonomy of existing HFL methods is proposed. Several critical and promising future research directions in HFL are discussed.
  arXiv  Detail & Related papers  (2023-07-20T06:32:14Z)
• Deep Equilibrium Models Meet Federated Learning [71.57324258813675]
  This study explores the problem of Federated Learning (FL) by utilizing the Deep Equilibrium (DEQ) models instead of conventional deep learning networks. We claim that incorporating DEQ models into the federated learning framework naturally addresses several open problems in FL. To the best of our knowledge, this study is the first to establish a connection between DEQ models and federated learning.
  arXiv  Detail & Related papers  (2023-05-29T22:51:40Z)
• Bayesian Federated Learning: A Survey [54.40136267717288]
  Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. The robustness and capabilities of existing FL methods are challenged by limited and dynamic data and conditions. BFL has emerged as a promising approach to address these issues.
  arXiv  Detail & Related papers  (2023-04-26T03:41:17Z)
• Vertical Federated Learning: A Structured Literature Review [0.0]
  Federated learning (FL) has emerged as a promising distributed learning paradigm with an added advantage of data privacy. In this paper, we present a structured literature review discussing the state-of-the-art approaches in VFL.
  arXiv  Detail & Related papers  (2022-12-01T16:16:41Z)
• Vertical Federated Learning: Concepts, Advances and Challenges [18.38260017835129]
  We review the concept and algorithms of Vertical Federated Learning (VFL) We provide an exhaustive categorization for VFL settings and privacy-preserving protocols. We propose a unified framework, termed VFLow, which considers the VFL problem under communication, computation, privacy, as well as effectiveness and fairness constraints.
  arXiv  Detail & Related papers  (2022-11-23T10:00:06Z)
• FederatedScope: A Comprehensive and Flexible Federated Learning Platform via Message Passing [63.87056362712879]
  We propose a novel and comprehensive federated learning platform, named FederatedScope, which is based on a message-oriented framework. Compared to the procedural framework, the proposed message-oriented framework is more flexible to express heterogeneous message exchange. We conduct a series of experiments on the provided easy-to-use and comprehensive FL benchmarks to validate the correctness and efficiency of FederatedScope.
  arXiv  Detail & Related papers  (2022-04-11T11:24:21Z)
• Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization [107.72786199113183]
  Federated learning (FL) provides a distributed learning framework for multiple participants to collaborate learning without sharing raw data. In this paper, we propose a novel Split-Mix FL strategy for heterogeneous participants that, once training is done, provides in-situ customization of model sizes and robustness.
  arXiv  Detail & Related papers  (2022-03-18T04:58:34Z)
• Vertical Federated Learning: Challenges, Methodologies and Experiments [34.4865409422585]
  vertical learning (VFL) is capable of constructing a hyper ML model by embracing sub-models from different clients. In this paper, we discuss key challenges in VFL with effective solutions, and conduct experiments on real-life datasets.
  arXiv  Detail & Related papers  (2022-02-09T06:56:41Z)
• Multi-Participant Multi-Class Vertical Federated Learning [16.75182305714081]
  We propose the Multi-participant Multi-class Vertical Federated Learning (MMVFL) framework for multi-class VFL problems involving multiple parties. MMVFL enables label sharing from its owner to other VFL participants in a privacypreserving manner. Experiment results on real-world datasets show that MMVFL can effectively share label information among multiple VFL participants and match multi-class classification performance of existing approaches.
  arXiv  Detail & Related papers  (2020-01-30T02:39:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.