Boosting Multimodal Federated Learning via Chained Modality Optimization

• URL: http://arxiv.org/abs/2606.01856v1
• Date: Mon, 01 Jun 2026 08:07:09 GMT
• Title: Boosting Multimodal Federated Learning via Chained Modality Optimization
• Abstract summary: Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative learning across decentralized clients with heterogeneous data and modality availability.<n>To address this, we propose FedMChain, a balanced MMFL framework that structures federated multimodal training as a chain of modality-wise phases.<n>This phase-wise design gives each modality a dedicated local optimization window on multimodal clients to mitigate modality competition, and further promotes cross-modal complementarity via an error-compensated regularizer.
• Score: 69.53075328069504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative learning across decentralized clients with heterogeneous data and modality availability. However, most existing MMFL methods cast multimodal training as a joint optimization problem, overlooking a key bottleneck: modality competition, where dominant modalities suppress weaker ones and lead to suboptimal global models. To address this, we propose FedMChain, a balanced MMFL framework that structures federated multimodal training as a chain of modality-wise phases. This phase-wise design gives each modality a dedicated local optimization window on multimodal clients to mitigate modality competition, and further promotes cross-modal complementarity via an error-compensated regularizer. On the server side, we employ a sparse sign-guided aggregation strategy that leverages directional sign agreement for robust intra-modality aggregation, avoids destructive averaging, and supports less frequent synchronization to reduce communication overhead. Extensive experiments on multimodal benchmarks demonstrate that FedMChain consistently improves predictive performance while requiring less frequent communication than baselines.

Related papers

• FedTaste: Topology-Aware Structural Transfer for Multimodal Federated Learning with Missing Modalities [7.015345209610299]
  FedTaste is a parameter-efficient framework for topology-aware structural transfer in Multimodal Federated Learning.<n>To adapt clients with missing modalities, we introduce Modality-Adaptive Structural Prompts.<n>In this way, FedTaste avoids explicit modality imputation while preserving shared semantic structure across clients.
  arXiv  Detail & Related papers  (2026-07-25T15:11:58Z)
• Balancing Multimodal Learning through Label Space Reshaping [21.889831594837677]
  We argue that the discrepancy of learning pace arises from differences in the mapping difficulty between modality-specific feature space and the shared label space.<n>We propose Balanced Multimodal Label Reshaping (BMLR), the first method that promotes multimodal balance from the label-side design.
  arXiv  Detail & Related papers  (2026-05-22T08:22:31Z)
• Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models [67.45032003041399]
  We propose a novel Multi-Paradigm Collaborative Attack (MPCAttack) framework to boost the transferability of adversarial examples against MLLMs.<n>MPCO adaptively balances the importance of different paradigm representations and guides the global optimisation.<n>Our solution consistently outperforms state-of-the-art methods in both targeted and untargeted attacks on open-source and closed-source MLLMs.
  arXiv  Detail & Related papers  (2026-03-05T06:01:26Z)
• Modality-Balanced Collaborative Distillation for Multi-Modal Domain Generalization [72.83292830785336]
  Weight Averaging (WA) has emerged as a powerful technique for enhancing generalization by promoting convergence to a flat loss landscape.<n>We propose MBCD, a unified collaborative distillation framework that retains WA's flatness-inducing advantages while overcoming its shortcomings in multi-modal contexts.
  arXiv  Detail & Related papers  (2025-11-25T12:38:28Z)
• BlendFL: Blended Federated Learning for Handling Multimodal Data Heterogeneity [44.03774830953328]
  BlendFL is a novel FL framework that seamlessly blends the principles of horizontal and vertical FL in a synchronized and non-restrictive fashion.<n> BlendFL features a decentralized inference mechanism, empowering clients to run collaboratively trained local models.<n>We trained and evaluated BlendFL and other state-of-the-art baselines on three classification tasks using a large-scale real-world multimodal medical dataset.
  arXiv  Detail & Related papers  (2025-10-15T08:10:42Z)
• Improving Multimodal Learning Balance and Sufficiency through Data Remixing [14.282792733217653]
  Methods for enforcing the weak modality fail to achieve unimodal sufficiency and multimodal balance.<n>We propose multimodal Data Remixing, including decoupling multimodal data and filtering hard samples for each modality to mitigate modality imbalance.<n>Our method can be seamlessly integrated with existing approaches, improving accuracy by approximately 6.50%$uparrow$ on CREMAD and 3.41%$uparrow$ on Kinetic-Sounds.
  arXiv  Detail & Related papers  (2025-06-13T08:01:29Z)
• MMiC: Mitigating Modality Incompleteness in Clustered Federated Learning [29.049226511777736]
  We present MMiC, a framework for Mitigating Modality incompleteness in Multimodal Federated Learning (MFL)<n> MMiC replaces partial parameters within client models inside clusters to mitigate the impact of missing modalities.<n>It also leverages the Banzhaf Power Index to optimize client selection under these conditions.
  arXiv  Detail & Related papers  (2025-05-11T09:12:36Z)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modality [28.90486547668949]
  Multimodal Federated Cross Prototype Learning (MFCPL) is a novel approach for MFL under severely missing modalities.<n>MFCPL provides diverse modality knowledge in modality-shared level with the cross-modal regularization and modality-specific level with cross-modal contrastive mechanism.<n>Our approach introduces the cross-modal alignment to provide regularization for modality-specific features, thereby enhancing the overall performance.
  arXiv  Detail & Related papers  (2024-01-25T02:25:23Z)
• Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection [19.284989473603627]
  We propose a novel Balanced Modality Selection framework for multi-modal learning (MFL) We show that local training with a certain single modality may contribute more to the global model than training with all local modalities. Our experiments on audio-visual, colored-gray, and front-back datasets showcase the superiority of BMSFed over baselines.
  arXiv  Detail & Related papers  (2023-12-31T05:37:27Z)
• FedMFS: Federated Multimodal Fusion Learning with Selective Modality Communication [11.254610576923204]
  We propose Federated Multimodal Fusion learning with Selective modality communication (FedMFS) Key idea is the introduction of a modality selection criterion for each device, which weighs (i) the impact of the modality, gauged by Shapley value analysis, against (ii) the modality model size as a gauge for communication overhead. Experiments on the real-world ActionSense dataset demonstrate the ability of FedMFS to achieve comparable accuracy to several baselines while reducing the communication overhead by over 4x.
  arXiv  Detail & Related papers  (2023-10-10T22:23:27Z)
• FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning [87.08902493524556]
  Federated learning(FL) has recently attracted increasing attention from academia and industry. We propose FedDM to build the global training objective from multiple local surrogate functions. In detail, we construct synthetic sets of data on each client to locally match the loss landscape from original data.
  arXiv  Detail & Related papers  (2022-07-20T04:55:18Z)
• Low-Latency Federated Learning over Wireless Channels with Differential Privacy [142.5983499872664]
  In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement.
  arXiv  Detail & Related papers  (2021-06-20T13:51:18Z)

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.