Federated learning for unpaired multimodal data through a homogeneous transformer model

• URL: http://arxiv.org/abs/2601.17986v1
• Date: Sun, 25 Jan 2026 20:30:21 GMT
• Title: Federated learning for unpaired multimodal data through a homogeneous transformer model
• Abstract summary: This paper establishes the mathematical backbone for federated unpaired foundation models.<n>It enables a global model to learn a unified representation of the world from fragmented, disjoint, and private data silos.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Training of multimodal foundation models is currently restricted to centralized data centers containing massive, aligned datasets (e.g., image-text pairs). However, in realistic federated environments, data is often unpaired and fragmented across disjoint nodes; one node may hold sensor data, while another holds textual logs. These datasets are strictly private and share no common samples. Current federated learning (FL) methods fail in this regime, as they assume local clients possess aligned pairs or require sharing raw feature embeddings, which violates data sovereignty. We propose a novel framework to train a global multimodal transformer across decentralized nodes with disjoint modalities. We introduce a small public anchor set to align disjoint private manifolds. Using Gram matrices calculated from these public anchors, we enforce semantic alignment across modalities through centered kernel alignment without ever transmitting private samples, offering a mathematically superior privacy guarantee compared to prototype sharing. Further, we introduce a subspace-stabilized fine-tuning method to handle FL with huge transformer models. We strictly decouple domain-specific magnitude shifts from semantic direction, ensuring that nodes with varying sensor characteristics align geometrically to the global consensus. Lastly, we propose precision weighted averaging, where efficiently obtained uncertainty estimates are used to downweight uncertain nodes. This paper establishes the mathematical backbone for federated unpaired foundation models, enabling a global model to learn a unified representation of the world from fragmented, disjoint, and private data silos without requiring centralized storage or paired samples.

Related papers

• SCOPE: Semantic Coreset with Orthogonal Projection Embeddings for Federated learning [0.7799711162530713]
  Current ML approaches either require impractical data aggregation or fail due to class imbalance.<n>We introduce SCOPE, a coreset framework for federated data that filters anomalies and adaptively prunes redundant data to long-tail skew.<n>SCOPE yields competitive global accuracy and robust convergence, all while achieving exceptional efficiency with a 128x to 512x reduction in uplink bandwidth.
  arXiv  Detail & Related papers  (2026-03-13T13:24:12Z)
• Federated Learning Meets LLMs: Feature Extraction From Heterogeneous Clients [0.0]
  Federated learning (FL) enables collaborative model training without sharing raw data.<n>We propose FedLLM-Align, a framework that leverages pre-trained large language models (LLMs) as universal feature extractors.<n>We evaluate FedLLM-Align on coronary heart disease prediction using partitioned datasets with simulated schema divergence.
  arXiv  Detail & Related papers  (2025-09-29T14:06:52Z)
• Federated Flow Matching [7.888172595458005]
  We introduce Federated Flow Matching (FFM), a framework for training flow matching models under privacy constraints.<n>Experiments on synthetic and image datasets show that FFM enables privacy-preserving training while enhancing both the flow straightness and sample quality in federated settings.
  arXiv  Detail & Related papers  (2025-09-25T14:45:02Z)
• Perfectly-Private Analog Secure Aggregation in Federated Learning [51.61616734974475]
  In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model.<n>In this paper, a novel secure parameter aggregation method is proposed that employs the torus rather than a finite field.
  arXiv  Detail & Related papers  (2025-09-10T15:22:40Z)
• OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction [10.326927761316986]
  Federated clustering aims to discover global cluster structures across decentralized clients without sharing raw data.<n>There are two critical challenges: (1) privacy leakage during collaboration, and (2) robustness degradation due to aggregation of proxy information.<n>We propose Omni Federated Clustering, a unified and model-agnostic framework.
  arXiv  Detail & Related papers  (2025-05-19T13:04:59Z)
• Deep Domain Isolation and Sample Clustered Federated Learning for Semantic Segmentation [2.515027627030043]
  In this paper, we explore for the first time the effect of covariate shifts between participants' data in 2D segmentation tasks. We develop Deep Domain Isolation (DDI) to isolate image domains directly in the gradient space of the model. We leverage this clustering algorithm through a Sample Clustered Federated Learning (SCFL) framework.
  arXiv  Detail & Related papers  (2024-10-04T12:43:07Z)
• PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
  We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
  arXiv  Detail & Related papers  (2024-06-04T13:51:08Z)
• Decentralized Directed Collaboration for Personalized Federated Learning [39.29794569421094]
  We concentrate on the Decentralized Personalized Learning (DPFL) that performs distributed training model computation. We propose a directed collaboration framework by incorporating textbfDecentralized textbfFederated textbfPartial textbfGradient textbfPedGP.
  arXiv  Detail & Related papers  (2024-05-28T06:52:19Z)
• Fed-MIWAE: Federated Imputation of Incomplete Data via Deep Generative Models [5.373862368597948]
  Federated learning allows for the training of machine learning models on multiple local datasets without requiring explicit data exchange. Data pre-processing, including strategies for handling missing data, remains a major bottleneck in real-world federated learning deployment. We propose Fed-MIWAE, a deep latent variable model for missing data imputation based on variational autoencoders.
  arXiv  Detail & Related papers  (2023-04-17T08:14:08Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning [112.69497636932955]
  Federated learning aims to train models across different clients without the sharing of data for privacy considerations. We study how data heterogeneity affects the representations of the globally aggregated models. We propose sc FedDecorr, a novel method that can effectively mitigate dimensional collapse in federated learning.
  arXiv  Detail & Related papers  (2022-10-01T09:04:17Z)
• FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data [69.0785021613868]
  Federated learning is a distributed machine learning approach which enables a shared server model to learn by aggregating the locally-computed parameter updates with the training data from spatially-distributed client silos. We propose the Federated Invariant Learning Consistency (FedILC) approach, which leverages the gradient covariance and the geometric mean of Hessians to capture both inter-silo and intra-silo consistencies. This is relevant to various fields such as medical healthcare, computer vision, and the Internet of Things (IoT)
  arXiv  Detail & Related papers  (2022-05-19T03:32:03Z)
• FedMix: Approximation of Mixup under Mean Augmented Federated Learning [60.503258658382]
  Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device. Current state-of-the-art algorithms suffer from performance degradation as the heterogeneity of local data across clients increases. We propose a new augmentation algorithm, named FedMix, which is inspired by a phenomenal yet simple data augmentation method, Mixup.
  arXiv  Detail & Related papers  (2021-07-01T06:14:51Z)

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.