paper-with-me

Papers

Experimenting with Normalization Layers in Federated Learning on non-IID scenarios

2023-03-19 · Bruno Casella, Roberto Esposito, Antonio Sciarappa, Carlo Cavazzoni, Marco Aldinucci

Training Deep Learning (DL) models require large, high-quality datasets, often assembled with data from different institutions. Federated Learning (FL) has been emerging as a method for privacy-preserving pooling of datasets employing collaborative training from different institutions by iteratively globally aggregating locally trained models. One critical performance challenge of FL is operating on datasets not independently and identically distributed (non-IID) among the federation participants. Even though this fragility cannot be eliminated, it can be debunked by a suitable optimization of two hyper-parameters: layer normalization methods and collaboration frequency selection. In this work, we benchmark five different normalization layers for training Neural Networks (NNs), two families of non-IID data skew, and two datasets. Results show that Batch Normalization, widely employed for centralized DL, is not the best choice for FL, whereas Group and Layer Normalization consistently outperform Batch Normalization. Similarly, frequent model aggregation decreases convergence speed and mode quality.

📄 PDF Abstract BibTeX arXiv:2303.10630

Code (1)

alpha-unito/benchmarking-normalization-layers-in-federated-learning-for-image-classification-tasks-on-non-iid 공식 구현 tf

Tasks

Federated LearningPrivacy Preserving

Methods 이 논문이 사용한 방법론

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Backward Gradient Normalization in Deep Neural Networks

2021-06-17 · Alejandro Cabana, Luis F. Lago-Fernández

We introduce a new technique for gradient normalization during neural network training. The gradients are rescaled during the backward pass using normalization layers introduced at certain points within the network archi…

Optimizing Federated Learning for Medical Image Classification on Distributed Non-iid Datasets with Partial Labels

2023-03-10 · Pranav Kulkarni, Adway Kanhere, Paul H. Yi, Vishwa S. Parekh

Numerous large-scale chest x-ray datasets have spearheaded expert-level detection of abnormalities using deep learning. However, these datasets focus on detecting a subset of disease labels that could be present, thus ma…

Federated Learningimage-classificationImage ClassificationMedical Image Classification+1

FedWon: Triumphing Multi-domain Federated Learning Without Normalization

2023-06-09 · Weiming Zhuang, Lingjuan Lyu

Federated learning (FL) enhances data privacy with collaborative in-situ training on decentralized clients. Nevertheless, FL encounters challenges due to non-independent and identically distributed (non-i.i.d) data, lead…

Domain GeneralizationFederated Learning

Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training

2021-10-08 · Lillian Zhou, Dhruv Guliani, Andreas Kabel, Giovanni Motta 외

Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers. Applying these approaches to Automatic Speech Recognitio…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Federated Learningspeech-recognition+1

Rethinking Normalization Methods in Federated Learning

2022-10-07 · Zhixu Du, Jingwei Sun, Ang Li, Pin-Yu Chen 외

Federated learning (FL) is a popular distributed learning framework that can reduce privacy risks by not explicitly sharing private data. In this work, we explicitly uncover external covariate shift problem in FL, which …

Federated Learning