Federated style aware transformer aggregation of representations
Personalized Federated Learning (PFL) faces persistent challenges, including domain heterogeneity from diverse client data, data imbalance due to skewed participation, and strict communication constraints. Traditional federated learning often lacks personalization, as a single global model cannot capture client-specific characteristics, leading to biased predictions and poor generalization, especially for clients with highly divergent data distributions. To address these issues, we propose FedSTAR, a style-aware federated learning framework that disentangles client-specific style factors from shared content representations. FedSTAR aggregates class-wise prototypes using a Transformer-based attention mechanism, allowing the server to adaptively weight client contributions while preserving personalization. Furthermore, by exchanging compact prototypes and style vectors instead of full model parameters, FedSTAR significantly reduces communication overhead. Experimental results demonstrate that combining content-style disentanglement with attention-driven prototype aggregation improves personalization and robustness in heterogeneous environments without increasing communication cost.
Code (0)
등록된 구현이 없습니다.
Tasks
Personalized Federated LearningSimilar Papers 제목 키워드 기반
Federated Cross-Modal Style-Aware Prompt Generation
Prompt learning has propelled vision-language models like CLIP to excel in diverse tasks, making them ideal for federated learning due to computational efficiency. However, conventional approaches that rely solely on fin…
Computational EfficiencyImage ClassificationFederated LearningBeyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA
Federated LoRA enables parameter-efficient adaptation of large language models under decentralized data and limited client resources.However, directly averaging LoRA factors is representation-dependent: the same intrinsi…
L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning
The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system c…
Federated LearningRepresentation LearningSelf-Supervised LearningFedBPrompt: Federated Domain Generalization Person Re-Identification via Body Distribution Aware Visual Prompts
Federated Domain Generalization for Person Re-Identification (FedDG-ReID) learns domain-invariant representations from decentralized data. While Vision Transformer (ViT) is widely adopted, its global attention often fail…
Person Re-IdentificationDomain GeneralizationFedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs
Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or optimization process that produces each client update. A malicious client …
Federated Learning