This repo is a collection of heterogeneous federated learning, including traditional federated learning and personalized federated learning.
- Test-Time Robust Personalization for Federated Learning[ICLR]
- EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data[ICLR]
- Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning[ICLR]
- PerFedMask: Personalized Federated Learning with Optimized Masking Vectors[ICLR]
- Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning[ICLR]
- Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses[ICLR]
- Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection[ICLR]
- Towards Addressing Label Skews in One-Shot Federated Learning[ICLR]
- Personalized Federated Learning with Feature Alignment and Classifier Collaboration[ICLR]
- FedFA: Federated Feature Augmentation[ICLR]
- Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity[ICLR]
- Multimodal Federated Learning via Contrastive Representation Ensemble[ICLR]
- The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation[ICLR]
- On the Importance and Applicability of Pre-Training for Federated Learning [ICLR]
- FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings[NeurIPS]
- Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning [ICML]
- Federated Learning with Label Distribution Skew via Logits Calibration [ICML]
- Multi-Level Branched Regularization for Federated Learning [ICML]
- Neural Tangent Kernel Empowered Federated Learning [ICML]
- Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring [ICML]
- CalFAT: Calibrated Federated Adversarial Training with Label Skewness[NeurIPS]
- Subspace Recovery from Heterogeneous Data with Non-isotropic Noise[NeurIPS]
- Global Convergence of Federated Learning for Mixed Regression[NeurIPS]
- TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels[NeurIPS]
- Preservation of the Global Knowledge by Not-True Distillation in Federated Learning[NeurIPS]
- DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing[NeurIPS]
- An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects[NeurIPS]
- AN AGNOSTIC APPROACH TO FEDERATED LEARNING WITH CLASS IMBALANCE[ICLR]
- FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction[CVPR]
- FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning[CVPR]
- Learn from Others and Be Yourself in Heterogeneous Federated Learning[CVPR]
- Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning[CVPR]
- Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning[CVPR]
- FedCorr: Multi-Stage Federated Learning for Label Noise Correction[CVPR]
- Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning[CVPR]
- Federated Learning with Position-Aware [CVPR]
- SphereFed: Hyperspherical Federated Learning[ECCV]
- Addressing Heterogeneity in Federated Learning via Distributional Transformation[ECCV]
- FedX: Unsupervised Federated Learning with Cross Knowledge Distillation[ECCV]
- HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images[AAAI]
- Is Your Data Relevant?: Dynamic Selection of Relevant Data for Federated Learning[[AAAI]](Is Your Data Relevant?: Dynamic Selection of Relevant Data for Federated Learning)
- edSoft: Soft Clustered Federated Learning with Proximal Local Updating[AAAI]
- Seizing Critical Learning Periods in Federated Learning[AAAI]
- Class-Wise Adaptive Self Distillation for Federated Learning on Non-IID Data (Student Abstract)[AAAI]
- Implicit Gradient Alignment in Distributed and Federated Learning[AAAI]
- Contribution-Aware Federated Learning for Smart Healthcare[AAAI]
- Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning[IJCAI]
- Private Semi-Supervised Federated Learning[IJCAI]
- Adapt to Adaptation: Learning Personalization for Cross-Silo Federated[IJCAI]
- Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features[IJCAI] *
-
Data-Free Knowledge Distillation for Heterogeneous Federated Learning[ICML]
-
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data[NeurIPS]
-
Breaking the centralized barrier for cross-device federated learning[NeurIPS]
-
Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients[NeurIPS]
-
Robust Federated Learning: The Case of Affine Distribution Shifts[NeurIPS]
-
FedBN: Federated Learning on Non-IID Features via Local Batch Normalization[ICLR]
-
FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning[ICLR]
-
Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning[ICLR]
-
FedMix: Approximation of Mixup under Mean Augmented Federated Learning[ICLR]
-
Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment[CVPR]
-
Model-Contrastive Federated Learning[CVPR]
-
Ensemble Attention Distillation for Privacy-Preserving Federated Learning[ICCV]
-
Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment[ICCV]
- SCAFFOLD: Stochastic Controlled Averaging for Federated Learning[ICML]
- Federated Learning with Only Positive Labels[ICML]
- An Efficient Framework for Clustered Federated Learning[NeurIPS]
- Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge[NeurIPS]
- Federated Learning with Matched Averaging[ICLR]
- Federated Multi-Task Learning[NeurIPS]
- Communication-Efficient Learning of Deep Networks from Decentralized Data[AISTATS][[FedAvg]]
- pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning[NeurIPS]
- Personalized Federated Learning via Variational Bayesian Inference [ICML]
- Personalized Federated Learning through Local Memorization[ICML]
- FedPop: A Bayesian Approach for Personalised Federated Learning[NeurIPS]
- Personalized Online Federated Learning with Multiple Kernels[NeurIPS]
- Factorized-FL: Personalized Federated Learning with Parameter Factorization & Similarity Matching[NeurIPS]
- ON BRIDGING GENERIC AND PERSONALIZED FEDERATED LEARNING FOR IMAGE CLASSIFICATION[ICLR]
- CD2-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning[CVPR]
- Layer-wised Model Aggregation for Personalized Federated Learning[CVPR]
- FedLTN: Federated Learning for Sparse and Personalized Lottery Ticket Networks[ECCV]
- Improving Generalization in Federated Learning by Seeking Flat Minima[ECCV]
- AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation[ECCV]
- Personalized Federated Learning using Hypernetworks[ICML]
- Exploiting Shared Representations for Personalized Federated Learning[ICML]
- PartialFed: Cross-Domain Personalized Federated Learning via Partial Initialization[NeurIPS]
- Personalized Federated Learning with Gaussian Processes[NeurIPS]
- QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning[NeurIPS]
- Federated Multi-Task Learning under a Mixture of Distributions[NeurIPS]
- Parameterized Knowledge Transfer for Personalized Federated Learning[NeurIPS]
- Exploiting Shared Representations for Personalized Federated Learning[ICML]
- Personalized Federated Learning with First Order Model Optimization[ICLR]
- Architecture Agnostic Federated Learning for Neural Networks[ICML]
- Adaptive Personalized Federated Learning[ICML]
- Personalized Federated Learning with Moreau Envelopes[NeurIPS]
- Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach[NeurIPS]
- Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization [ICML]
- Resource-Adaptive Federated Learning with All-In-One Neural Composition[NeurIPS]
- FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction[NeurIPS]
- FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout[NeurIPS]
- Ensemble Distillation for Robust Model Fusion in Federated Learning[NeurIPS]
- EFFICIENT SPLIT-MIX FEDERATED LEARNING FOR ONDEMAND AND IN-SITU CUSTOMIZATION [ICLR]
- ZEROFL: EFFICIENT ON-DEVICE TRAINING FOR FEDERATED LEARNING WITH LOCAL SPARSITY[ICLR]
- HYBRID LOCAL SGD FOR FEDERATED LEARNING WITH HETEROGENEOUS COMMUNICATIONS[ICLR]
- Robust Federated Learning with Noisy and Heterogeneous Clients[CVPR]
- HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients[ICLR]