Uncertainty-Aware Label Refinement on Hypergraphs for Personalized Federated Facial Expression Recognition
Not on the map. Why?
Abstract (arXiv)
Most facial expression recognition (FER) models are trained on large-scale expression data with centralized learning. Unfortunately, collecting a large amount of centralized expression data is difficult in practice due to privacy concerns of facial images. In this paper, we investigate FER under the framework of personalized federated learning, which is a valuable and practical decentralized setting for real-world applications. To this end, we develop a novel uncertainty-Aware label refineMent on hYpergraphs (AMY) method. For local training, each local model consists of a backbone, an uncertainty estimation (UE) block, and an expression classification (EC) block. In the UE block, we leverage a hypergraph to model complex high-order relationships between expression samples and incorporate these relationships into uncertainty features. A personalized uncertainty estimator is then introduced to estimate reliable uncertainty weights of samples in the local client. In the EC block, we perform label propagation on the hypergraph, obtaining high-quality refined labels for retraining an expression classifier. Based on the above, we effectively alleviate heterogeneous sample uncertainty across clients and learn a robust personalized FER model in each client. Experimental results on two challenging real-world facial expression databases show that our proposed method consistently outperforms several state-of-the-art methods. This indicates the superiority of hypergraph modeling for uncertainty estimation and label refinement on the personalized federated FER task. The source code will be released at https://github.com/mobei1006/AMY.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 50 references that are in the map. First posted on arXiv 3 Jan 2025.
Builds on
26 of 50 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2020Personalized Federated Learning with Moreau Envelopescited by 618
- 2019Federated Learning with Personalization Layerscited by 541
- 2018Hypergraph Neural Networkscited by 488
- 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
- 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
- 2021A Field Guide to Federated Optimizationcited by 315
- 2019Label Propagation for Deep Semi-supervised Learningcited by 289
14 more
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
- 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
- 2016Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distributioncited by 158
- 2020Suppressing Uncertainties for Large-Scale Facial Expression Recognitioncited by 157
- 2020Survey of Personalization Techniques for Federated Learningcited by 145
- 2021Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognitioncited by 89
- 2021Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognitioncited by 49
- 2015Going Deeper in Facial Expression Recognition using Deep Neural Networkscited by 43
- 2017Island Loss for Learning Discriminative Features in Facial Expression Recognitioncited by 35
- 2021Federated Learning for Face Recognition with Gradient Correctioncited by 24
- 2021FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognitioncited by 16
- 2022Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edgescited by 12
- 2022Mid-level Representation Enhancement and Graph Embedded Uncertainty Suppressing for Facial Expression Recognitioncited by 6
- 2023FedREP: A Byzantine-Robust, Communication-Efficient and Privacy-Preserving Framework for Federated Learningcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.