MMiC: Mitigating Modality Incompleteness in Clustered Federated Learning
Not on the map. Why?
Abstract (arXiv)
In the era of big data, data mining has become indispensable for uncovering hidden patterns and insights from vast and complex datasets. The integration of multimodal data sources further enhances its potential. Multimodal Federated Learning (MFL) is a distributed approach that enhances the efficiency and quality of multimodal learning, ensuring collaborative work and privacy protection. However, missing modalities pose a significant challenge in MFL, often due to data quality issues or privacy policies across the clients. In this work, we present MMiC, a framework for Mitigating Modality incompleteness in MFL within the Clusters. MMiC replaces partial parameters within client models inside clusters to mitigate the impact of missing modalities. Furthermore, it leverages the Banzhaf Power Index to optimize client selection under these conditions. Finally, MMiC employs an innovative approach to dynamically control global aggregation by utilizing Markovitz Portfolio Optimization. Extensive experiments demonstrate that MMiC consistently outperforms existing federated learning architectures in both global and personalized performance on multimodal datasets with missing modalities, confirming the effectiveness of our proposed solution. Our code is available at https://github.com/gotobcn8/MMiC.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 62 references that are in the map. First posted on arXiv 11 May 2025.
Builds on
28 of 62 references.
References · 28
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2020Adaptive Federated Optimizationcited by 1,046
- 2017Federated Multi-Task Learningcited by 672
- 2020An Efficient Framework for Clustered Federated Learningcited by 511
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
- 2021Towards Personalized Federated Learningcited by 464
- 2018Stacked Cross Attention for Image-Text Matchingcited by 416
- 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
16 more
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
- 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
- 2023PMET: Precise Model Editing in a Transformercited by 173
- 2019Robust Federated Learning in a Heterogeneous Environmentcited by 90
- 2021Heterogeneity for the Win: One-Shot Federated Clusteringcited by 87
- 2023Multimodal Federated Learning via Contrastive Representation Ensemblecited by 86
- 2020Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Frameworkcited by 59
- 2023FedMultimodal: A Benchmark For Multimodal Federated Learningcited by 51
- 2021FedSoft: Soft Clustered Federated Learning with Proximal Local Updatingcited by 46
- 2022Geometric Multimodal Contrastive Representation Learningcited by 40
- 2022Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspacescited by 36
- 2020Analysis of Social Media Data using Multimodal Deep Learning for Disaster Responsecited by 23
- 2023Multimodal Federated Learning with Missing Modality via Prototype Mask and Contrastcited by 17
- 2024CrisisKAN: Knowledge-infused and Explainable Multimodal Attention Network for Crisis Event Classificationcited by 6
- 2024Open-Vocabulary Federated Learning with Multimodal Prototypingcited by 4
- 2014Human Activity Recognition using Smartphonecited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.