FML-DGCN: Federated Multi-Label Learning Based on Dynamic Graph Convolutional Networks
- 22 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. PP (4) , 1-15
Abstract
Federated multilabel learning enables the collaborative training of multilabel classification models while preserving client privacy. Existing federated multilabel learning methods either fail to effectively capture label correlations, which significantly affects model performance in scenarios where labels are interdependent, or increase the risk of client privacy leakage due to the transmission of unnecessary client data. To this end, we propose FML-DGCN, a federated multi-label learning approach based on dynamic graph convolutional networks. In the local training phase, a dynamic graph convolutional module is designed and employed to generate label representations specific to the input image, with parameters efficiently optimized by our designed correlation alignment loss. Within the module, we employ a fully connected layer-based network to merge static label embeddings and image features for computing dynamic label graphs, instead of leveraging complex attention-based networks, making it suitable for federated learning environments with limited computing resources. In the federated aggregation phase, clients transmit only model parameters, without sharing any additional information such as scene knowledge, thus lowering the risk of client privacy leakage. Experimental results on four typical multilabel image classification datasets demonstrate the superiority of our approach.Keywords
Funding Information
- National Natural Science Foundation of China (62576121)
This publication has 43 references indexed in Scilit:
- Evaluation of domain shift sources and generalisability in AI-based prostate MRI autocontouring for radiotherapyPhysica Medica, 2025
- Analysing Satellite Imagery Classification under Spatial Domain Shift across Geographic RegionsInternational Journal of Computer Vision, 2025
- Grounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection2024
- Handling imbalanced medical datasets: review of a decade of researchArtificial Intelligence Review, 2024
- Exploring Plain Vision Transformer Backbones for Object Detection2022
- Label-representative graph convolutional network for multi-label text classificationApplied Intelligence, 2022
- Attention-Driven Dynamic Graph Convolutional Network for Multi-label Image Recognition2020
- Efficient Machine Learning for Big Data: A ReviewBig Data Research, 2015
- Microsoft COCO: Common Objects in Context2014
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009