Technology Category
Machine Learning: Distributed Machine Learning & Federated LearningSearch and Optimization: Learning to SearchNatural Language Processing: Sentence-level Semantics, Textual Inference, etc.
FedSC: Federated Learning with Semantic-Aware Collaboration
🤖 AI Summary
Data heterogeneity—particularly label distribution skew—severely degrades model performance in federated learning. To address this, we propose FedSC, a semantic-aware collaborative framework that introduces, for the first time, a semantic-level prototype collaboration mechanism: (i) relational prototypes to model inter-class semantic structure, and (ii) consensus prototypes to align locally learned knowledge across clients. FedSC further integrates inter-class contrastive learning with divergence-aware aggregation regularization to enhance generalization and convergence stability. We provide theoretical convergence guarantees and empirically demonstrate significant improvements over state-of-the-art methods across diverse highly heterogeneous benchmarks. Ablation studies validate both the effectiveness of semantic prototype collaboration and the necessity of each designed component.
Technology Category
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
Addressing data heterogeneity in federated learning
Leveraging semantic information for client-specific knowledge
Ensuring stable convergence with prototype collaboration
Innovation
Methods, ideas, or system contributions that make the work stand out.
Constructs relational and consistent semantic-level prototypes
Uses inter-contrastive learning for instance-level embeddings
Regularizes local models via discrepancy aggregation
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
