mlsanityData to 7 Oct 2026

FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularization

arXiv 2410.03070 ↗First posted 4 Oct 2024cs.LG cs.MMcited by 16

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a method for training machine learning models using distributed data sources. It ensures privacy by allowing clients to collaboratively learn a shared global model while storing their data locally. However, a significant challenge arises when dealing with missing modalities in clients' datasets, where certain features or modalities are unavailable or incomplete, leading to heterogeneous data distribution. While previous studies have addressed the issue of complete-modality missing, they fail to tackle partial-modality missing on account of severe heterogeneity among clients at an instance level, where the pattern of missing data can vary significantly from one sample to another. To tackle this challenge, this study proposes a novel framework named FedMAC, designed to address multi-modality missing under conditions of partial-modality missing in FL. Additionally, to avoid trivial aggregation of multi-modal features, we introduce contrastive-based regularization to impose additional constraints on the latent representation space. The experimental results demonstrate the effectiveness of FedMAC across various client configurations with statistical heterogeneity, outperforming baseline methods by up to 26% in severe missing scenarios, highlighting its potential as a solution for the challenge of partially missing modalities in federated systems. Our source code is provided at https://github.com/nmduonggg/PEPSY

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 14 of its 26 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

14 of 26 references.

References · 14

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  3. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  4. 2016An overview of gradient descent optimization algorithmscited by 1,021
  5. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  6. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  7. 2022Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learningcited by 81
  8. 2020Deep Partial Multi-View Learningcited by 71
  9. 2023FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learningcited by 59
  10. 2022Geometric Multimodal Contrastive Representation Learningcited by 40
  11. 2024FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathologycited by 17
  12. 2022FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learningcited by 7
2 more
  1. 2023CADIS: Handling Cluster-skewed Non-IID Data in Federated Learning with Clustered Aggregation and Knowledge DIStilled Regularizationcited by 5
  2. 2022Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer Learningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 14.

16 papers.

Sort:

By area:

  1. 2026MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learningcited by 11
  2. 2025Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Datacited by 7
  3. 2026Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Datacited by 3
  4. 2026STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learningcited by 3
  5. 2026PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learningcited by 3
  6. 2025ClusMFL: A Cluster-Enhanced Framework for Modality-Incomplete Multimodal Federated Learning in Brain Imaging Analysiscited by 2
  7. 2026Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneitycited by 1
  8. 2026Federated Imputation under Heterogeneous Feature Spacescited by 1
  9. 2026FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learningcited by 1
  10. 2026Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneitycited by 1
  11. 2026FedUAF: Uncertainty-Aware Fusion with Reliability-Guided Aggregation for Multimodal Federated Sentiment Analysiscited by 0
  12. 2026Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learningcited by 0
4 more
  1. 2026Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approachcited by 0
  2. 2026Multimodal Federated Learning under Dual-Axis Modality Missingnesscited by 0
  3. 2026MedMix: Specialization-Consistent Federated Sparse MoEs under Modality Heterogeneitycited by 0
  4. 2026Fed-ReMasker: Federated Tabular Imputation under Feature-Level Missingnesscited by 0