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 can potentially offer data privacy guarantees while also advancing the quality and robustness of the learned visual representations without needing to move data around. However, client bias and divergence during FL aggregation caused by data heterogeneity limits the performance of learned visual representations on downstream tasks. In this paper, we propose a new aggregation strategy termed Layer-wise Divergence Aware Weight Aggregation (L-DAWA) to mitigate the influence of client bias and divergence during FL aggregation. The proposed method aggregates weights at the layer-level according to the measure of angular divergence between the clients' model and the global model. Extensive experiments with cross-silo and cross-device settings on CIFAR-10/100 and Tiny ImageNet datasets demonstrate that our methods are effective and obtain new SOTA performance on both contrastive and non-contrastive SSL approaches.
Code (1)
Tasks
Federated LearningRepresentation LearningSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses
Adversarial robustness evaluation faces a critical challenge as new defense paradigms emerge that can exploit limitations in existing assessment methods. This paper reveals that Dummy Classes-based defenses, which introd…
Adversarial RobustnessOn the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond
Federated averaging (FedAvg) is the most fundamental algorithm in Federated learning (FL). Previous theoretical results assert that FedAvg convergence and generalization degenerate under heterogeneous clients. However, r…
DiversityFederated LearningDreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning
World Action Models (WAMs) offer a promising approach to embodied intelligence, yet existing methods rely heavily on video prediction as action priors and lack adaptive multimodal reasoning, limiting their effectiveness …
Multimodal ReasoningVisual ReasoningVideo PredictionRandom Surfing Revisited: Generalizing PageRank's Teleportation Model
We revisit the Random Surfer model, focusing on its--often overlooked--Teleportation component, and we introduce NCDawareRank; a novel ranking framework designed to exploit network meta-information as well as aspects of …
modelFedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors
Federated Learning (FL) has emerged as a promising framework for distributed machine learning, enabling collaborative model training without sharing local data, thereby preserving privacy and enhancing security. However,…
Federated Learningglobal-optimization