FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy (2023-07-01T00:00:00.000000Z)

TL;DR

The Federated Conditional Policy (FedCP) method is proposed, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively.

Abstract

Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones, etc. Most existing pFL methods focus on exploiting the global information and personalized information in the client-level model parameters while neglecting that data is the source of these two kinds of information. To address this, we propose the Federated Conditional Policy (FedCP) method, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively. FedCP is more fine-grained to consider personalization in a sample-specific manner than existing pFL methods. Extensive experiments in computer vision and natural language processing domains show that FedCP outperforms eleven state-of-the-art methods by up to 6.69%. Furthermore, FedCP maintains its superiority when some clients accidentally drop out, which frequently happens in mobile settings. Our code is public at https://github.com/TsingZ0/FedCP.

Authors

Jianqing Zhang

2 papers

Yang Hua

2 papers

Hao Wang

2 papers

TL;DR

Abstract

Authors

References60 items

FedDisco: Federated Learning with Discrepancy-Aware Collaboration

FedALA: Adaptive Local Aggregation for Personalized Federated Learning

LightFR: Lightweight Federated Recommendation with Privacy-preserving Matrix Factorization

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

Connecting Low-Loss Subspace for Personalized Federated Learning

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

Federated Learning for Internet of Things: A Comprehensive Survey

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

Exploiting Shared Representations for Personalized Federated Learning

Personalized Federated Learning with First Order Model Optimization

Ditto: Fair and Robust Federated Learning Through Personalization

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization

Personalized Cross-Silo Federated Learning on Non-IID Data

Ensemble Distillation for Robust Model Fusion in Federated Learning

Personalized Federated Learning with Moreau Envelopes

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

Advances and Open Problems in Federated Learning

Federated Learning with Personalization Layers

PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation

Federated Learning: Challenges, Methods, and Future Directions

Deep Leakage from Gradients

Federated Machine Learning

Federated Optimization in Heterogeneous Networks

SpotTune: Transfer Learning Through Adaptive Fine-Tuning

A Guide to the California Consumer Privacy Act of 2018

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

Group Normalization

Convolutional Networks with Adaptive Inference Graphs

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

Convergence Analysis of Two-layer Neural Networks with ReLU Activation

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

Categorical Reparameterization with Gumbel-Softmax

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

Reconstruction Attacks Against Mobile-Based Continuous Authentication Systems in the Cloud

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

Distilling the Knowledge in a Neural Network

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Improving the Fisher Kernel for Large-Scale Image Classification

A Kernel Method for the Two-Sample-Problem

Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution

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

Federated Recommendation Systems

FederatedMachine Learning: Concept and Applications

Deep Learning

REGULATION (EU) 2019/518 OF THE EUROPEAN PARLIAMENT AND OF THE COUNCIL

Machine learning - a probabilistic perspective

Learning Multiple Layers of Features from Tiny Images

Gradient-based learning applied to document recognition

EuropeanConferenceonMachineLearningandPrinciplesandPracticeofKnowledgeDiscoveryinDatabases

Field of Study

Journal Information

Name

Venue Information

Name

Type

URL

Alternate Names