Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling
Not on the map. Why?
Abstract (arXiv)
Federated Multi-Task Learning (FMTL) enables multiple clients performing heterogeneous tasks without exchanging their local data, offering broad potential for privacy preserving multi-task collaboration. However, most existing methods focus on building personalized models for each client and unable to support the aggregation of multiple heterogeneous tasks into a unified model. As a result, in real-world scenarios where task objectives, label spaces, and optimization paths vary significantly, conventional FMTL methods struggle to achieve effective joint training. To address this challenge, we propose FedDEA (Federated Decoupled Aggregation), an update-structure-aware aggregation method specifically designed for multi-task model integration. Our method dynamically identifies task-relevant dimensions based on the response strength of local updates and enhances their optimization effectiveness through rescaling. This mechanism effectively suppresses cross-task interference and enables task-level decoupled aggregation within a unified global model. FedDEA does not rely on task labels or architectural modifications, making it broadly applicable and deployment-friendly. Experimental results demonstrate that it can be easily integrated into various mainstream federated optimization algorithms and consistently delivers significant overall performance improvements on widely used NYUD-V2 and PASCAL-Context. These results validate the robustness and generalization capabilities of FedDEA under highly heterogeneous task settings.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 52 references that are in the map. First posted on arXiv 30 May 2025.
Builds on
34 of 52 references.
References · 34
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2020Gradient Surgery for Multi-Task Learningcited by 1,256
- 2022Editing Models with Task Arithmeticcited by 1,120
- 2020Adaptive Federated Optimizationcited by 1,046
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
- 2017A Survey on Multi-Task Learningcited by 840
- 2021Model-Contrastive Federated Learningcited by 766
22 more
- 2017Federated Multi-Task Learningcited by 672
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2021Federated Learning Based on Dynamic Regularizationcited by 562
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
- 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
- 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
- 2017Multi-task Self-Supervised Visual Learningcited by 200
- 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
- 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
- 2019Attentive Single-Tasking of Multiple Taskscited by 148
- 2021Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learningcited by 111
- 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
- 2021Multi-Task Learning in Natural Language Processing: An Overviewcited by 62
- 2020Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computingcited by 52
- 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 30
- 2024Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Erascited by 26
- 2022Communication-Efficient Federated Learning with Accelerated Client Gradientcited by 24
- 2022FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentationcited by 24
- 2021Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligencecited by 18
- 2023FedHCA2: Towards Hetero-Client Federated Multi-Task Learningcited by 17
Built on by
Citing papers per year: 2026: 1.
1 paper.