Prototype Guided Federated Learning of Visual Feature Representations
Federated Learning (FL) is a framework which enables distributed model training using a large corpus of decentralized training data. Existing methods aggregate models disregarding their internal representations, which are crucial for training models in vision tasks. System and statistical heterogeneity (e.g., highly imbalanced and non-i.i.d. data) further harm model training. To this end, we introduce a method, called FedProto, which computes client deviations using margins of prototypical representations learned on distributed data, and applies them to drive federated optimization via an attention mechanism. In addition, we propose three methods to analyse statistical properties of feature representations learned in FL, in order to elucidate the relationship between accuracy, margins and feature discrepancy of FL models. In experimental analyses, FedProto demonstrates state-of-the-art accuracy and convergence rate across image classification and semantic segmentation benchmarks by enabling maximum margin training of FL models. Moreover, FedProto reduces uncertainty of predictions of FL models compared to the baseline. To our knowledge, this is the first work evaluating FL models in dense prediction tasks, such as semantic segmentation.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated Learningimage-classificationImage ClassificationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning
Existing federated learning methods have effectively dealt with decentralized learning in scenarios involving data privacy and non-IID data. However, in real-world situations, each client dynamically learns new classes, …
class-incremental learningClass Incremental LearningFederated LearningIncremental LearningRobust Federated Learning on Edge Devices with Domain Heterogeneity
Federated Learning (FL) allows collaborative training while ensuring data privacy across distributed edge devices, making it a popular solution for privacy-sensitive applications. However, FL faces significant challenges…
Contrastive LearningDiversityFederated LearningFederated Learning from Pre-Trained Models: A Contrastive Learning Approach
Federated Learning (FL) is a machine learning paradigm that allows decentralized clients to learn collaboratively without sharing their private data. However, excessive computation and communication demands pose challeng…
Contrastive LearningFederated LearningClosing the Alignment-Maturity Gap in Federated Prototype Learning
Learning discriminative visual representations from distributed, heterogeneous data is a fundamental challenge in Federated Learning (FL). Prototype-based methods address statistical heterogeneity by sharing class-level …
Representation LearningFederated LearningDivide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation
Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt t…
Representation LearningFederated Learning