GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning (2023-08-20T00:00:00.000000Z)

TL;DR

This work proposes a new pFL method, named GPFL, to simultaneously learn global and personalized feature information on each client and shows the superiority of GPFL over ten state-of-the-art methods regarding effectiveness, scalability, fairness, stability, and privacy.

Abstract

Federated Learning (FL) is popular for its privacy-preserving and collaborative learning capabilities. Recently, personalized FL (pFL) has received attention for its ability to address statistical heterogeneity and achieve personalization in FL. However, from the perspective of feature extraction, most existing pFL methods only focus on extracting global or personalized feature information during local training, which fails to meet the collaborative learning and personalization goals of pFL. To address this, we propose a new pFL method, named GPFL, to simultaneously learn global and personalized feature information on each client. We conduct extensive experiments on six datasets in three statistically heterogeneous settings and show the superiority of GPFL over ten state-of-the-art methods regarding effectiveness, scalability, fairness, stability, and privacy. Besides, GPFL mitigates overfitting and outperforms the baselines by up to 8.99% in accuracy.

Authors

Jianqing Zhang

2 papers

Yang Hua

2 papers

Hao Wang

2 papers

TL;DR

Abstract

Authors

References69 items

FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy

Edge-cloud Collaborative Learning with Federated and Centralized Features

Revisiting Weighted Aggregation in Federated Learning with Neural Networks

FedALA: Adaptive Local Aggregation for Personalized Federated Learning

Federated recommenders: methods, challenges and future

MetaFed: Federated Learning Among Federations With Cyclic Knowledge Distillation for Personalized Healthcare

Federated Learning with Partial Model Personalization

Federated Learning for Face Recognition with Gradient Correction

FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning

Federated Learning for Internet of Things: Applications, Challenges, and Opportunities

Parameterized Knowledge Transfer for Personalized Federated Learning

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

FedProto: Federated Prototype Learning across Heterogeneous Clients

Model-Contrastive Federated Learning

TLSAN: Time-aware Long- and Short-term Attention Network for Next-item Recommendation

Personalized Federated Learning using Hypernetworks

Towards Personalized Federated Learning

FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

Exploiting Shared Representations for Personalized Federated Learning

Federated Learning on Non-IID Data Silos: An Experimental Study

Ditto: Fair and Robust Federated Learning Through Personalization

KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization

Ensemble Distillation for Robust Model Fusion in Federated Learning

Secure, privacy-preserving and federated machine learning in medical imaging

Personalized Federated Learning with Moreau Envelopes

Inverting Gradients - How easy is it to break privacy in federated learning?

End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things

Federated Visual Classification with Real-World Data Distribution

A Simple Framework for Contrastive Learning of Visual Representations

FedVision: An Online Visual Object Detection Platform Powered by Federated Learning

Advances and Open Problems in Federated Learning

Federated Learning with Personalization Layers

Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

Deep Leakage from Gradients

Learning Loss for Active Learning

Federated Optimization in Heterogeneous Networks

Moment Matching for Multi-Source Domain Adaptation

Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks

SpotTune: Transfer Learning Through Adaptive Fine-Tuning

Conditional Neural Processes

TADAM: Task dependent adaptive metric for improved few-shot learning

Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels

Federated Meta-Learning with Fast Convergence and Efficient Communication

BlockDrop: Dynamic Inference Paths in Residual Networks

Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets

Attention is All you Need

Convergence Analysis of Two-layer Neural Networks with ReLU Activation

Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution

Improved Deep Metric Learning with Multi-class N-pair Loss Objective

Layer Normalization

Bag of Tricks for Efficient Text Classification

Communication-Efficient Learning of Deep Networks from Decentralized Data

Deep Residual Learning for Image Recognition

Character-level Convolutional Networks for Text Classification

Convolutional Neural Networks for human activity recognition using mobile sensors

Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine

Representation Learning: A Review and New Perspectives

Image Quality Metrics: PSNR vs. SSIM

A Quantitative Measure Of Fairness And Discrimination For Resource Allocation In Shared Computer Systems

On Bridging Generic and Personalized Federated Learning for Image Classification

FedPHP: Federated Personalization with Inherited Private Models

Temporal Meta-Adaptor for Video Object Detection

Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach

Learning Multiple Layers of Features from Tiny Images

Visualizing Data using t-SNE

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type