FedSC: Federated Learning with Semantic-Aware Collaboration
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) aims to train models collaboratively across clients without sharing data for privacy-preserving. However, one major challenge is the data heterogeneity issue, which refers to the biased labeling preferences at multiple clients. A number of existing FL methods attempt to tackle data heterogeneity locally (e.g., regularizing local models) or globally (e.g., fine-tuning global model), often neglecting inherent semantic information contained in each client. To explore the possibility of using intra-client semantically meaningful knowledge in handling data heterogeneity, in this paper, we propose Federated Learning with Semantic-Aware Collaboration (FedSC) to capture client-specific and class-relevant knowledge across heterogeneous clients. The core idea of FedSC is to construct relational prototypes and consistent prototypes at semantic-level, aiming to provide fruitful class underlying knowledge and stable convergence signals in a prototype-wise collaborative way. On the one hand, FedSC introduces an inter-contrastive learning strategy to bring instance-level embeddings closer to relational prototypes with the same semantics and away from distinct classes. On the other hand, FedSC devises consistent prototypes via a discrepancy aggregation manner, as a regularization penalty to constrain the optimization region of the local model. Moreover, a theoretical analysis for FedSC is provided to ensure a convergence guarantee. Experimental results on various challenging scenarios demonstrate the effectiveness of FedSC and the efficiency of crucial components.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 52 of its 70 references that are in the map. First posted on arXiv 26 Jun 2025.
Builds on
52 of 70 references.
References · 52
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
- 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
38 more
- 2021Model-Contrastive Federated Learningcited by 766
- 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
- 2020Federated Learning with Matched Averagingcited by 564
- 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
- 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
- 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
- 2021Federated Learning on Non-IID Data: A Surveycited by 346
- 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
- 2020Contrastive Clusteringcited by 265
- 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
- 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
- 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
- 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
- 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
- 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
- 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
- 2018Robust Classification with Convolutional Prototype Learningcited by 123
- 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
- 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
- 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
- 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
- 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
- 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 67
- 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 67
- 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
- 2023Cluster-guided Contrastive Graph Clustering Networkcited by 60
- 2023Online Prototype Learning for Online Continual Learningcited by 53
- 2017The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classificationcited by 50
- 2021Federated Multi-Target Domain Adaptationcited by 44
- 2022On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyondcited by 38
- 2024Relaxed Contrastive Learning for Federated Learningcited by 32
- 2022FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentationcited by 24
- 2023Boosting Few-shot Action Recognition with Graph-guided Hybrid Matchingcited by 24
- 2022Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrievalcited by 20
- 2021Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identificationcited by 19
- 2022Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defensecited by 16
- 2021A Closer Look at Prototype Classifier for Few-shot Image Classificationcited by 15
50 most cited of 52 All 52 (JSON)
Built on by
Citing papers per year: 2026: 3.
3 papers.