ICLR

2024

• One-shot Empirical Privacy Estimation for Federated Learning.

• Benchmarking Algorithms for Federated Domain Generalization.

• A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging.

• A Mutual Information Perspective on Federated Contrastive Learning.

• Stochastic Controlled Averaging for Federated Learning with Communication Compression.

• Bayesian Coreset Optimization for Personalized Federated Learning.

• Fair and Efficient Contribution Valuation for Vertical Federated Learning.

• FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization.

• Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning.

• Federated Q-Learning: Linear Regret Speedup with Low Communication Cost.

• Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning.

• Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients.

• Fake It Till Make It: Federated Learning with Consensus-Oriented Generation.

• Communication-Efficient Federated Non-Linear Bandit Optimization.

• Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration.

• Adaptive Federated Learning with Auto-Tuned Clients.

• Improving LoRA in Privacy-preserving Federated Learning.

• Incentivized Truthful Communication for Federated Bandits.

• Federated Wasserstein Distance.

• Incentive-Aware Federated Learning with Training-Time Model Rewards.

• An improved analysis of per-sample and per-update clipping in federated learning.

• PeFLL: Personalized Federated Learning by Learning to Learn.

• Robust Training of Federated Models with Extremely Label Deficiency.

• Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit.

• FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data.

• FedImpro: Measuring and Improving Client Update in Federated Learning.

• FedWon: Triumphing Multi-domain Federated Learning Without Normalization.

• Federated Recommendation with Additive Personalization.

• On Differentially Private Federated Linear Contextual Bandits.

• Federated Text-driven Prompt Generation for Vision-Language Models.

• Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning.

• Federated Causal Discovery from Heterogeneous Data.

• FedInverse: Evaluating Privacy Leakage in Federated Learning.

• FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning.

• FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation.

• Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate.

• Backdoor Federated Learning by Poisoning Backdoor-Critical Layers.

• Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition.

• FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent.

• Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting.

• FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler.

• Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages.

• Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting.

• Accurate Forgetting for Heterogeneous Federated Continual Learning.

• VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks.

• Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning.

• VFLAIR: A Research Library and Benchmark for Vertical Federated Learning.

• Momentum Benefits Non-iid Federated Learning Simply and Provably.

• Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory.

• Effective and Efficient Federated Tree Learning on Hybrid Data.

• FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity.

2023

Notable-top-5%

• Personalized Federated Learning with Feature Alignment and Classifier Collaboration.

• MocoSFL: enabling cross-client collaborative self-supervised learning.

Notable-top-25%

• Single-shot General Hyper-parameter Optimization for Federated Learning.

• Where to Begin? Exploring the Impact of Pre-Training and Initialization in Federated.

• FedExP: Speeding up Federated Averaging via Extrapolation.

• Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection.

• DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity.

Poster

• Machine Unlearning of Federated Clusters.

• Federated Neural Bandits.

• FedFA: Federated Feature Augmentation.

• Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach.

• Better Generative Replay for Continual Federated Learning.

• Federated Learning from Small Datasets.

• Federated Nearest Neighbor Machine Translation.

• Test-Time Robust Personalization for Federated Learning.

• DepthFL : Depthwise Federated Learning for Heterogeneous Clients.

• Towards Addressing Label Skews in One-Shot Federated Learning.

• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning.

• Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation.

• SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication.

• Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses.

• Effective passive membership inference attacks in federated learning against overparameterized models.

• FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification.

• Multimodal Federated Learning via Contrastive Representation Ensemble.

• Faster federated optimization under second-order similarity.

• FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy.

• The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation.

• PerFedMask: Personalized Federated Learning with Optimized Masking Vectors.

• EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data.

• FedDAR: Federated Domain-Aware Representation Learning.

• Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning.

• FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning.

• Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses.

• Efficient Federated Domain Translation.

• On the Importance and Applicability of Pre-Training for Federated Learning.

• Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models.

• A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy.

• Instance-wise Batch Label Restoration via Gradients in Federated Learning.

• Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity.

• Meta Knowledge Condensation for Federated Learning.

• CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning.

• Sparse Random Networks for Communication-Efficient Federated Learning.

• Combating Exacerbated Heterogeneity for Robust Decentralized Models.

• Hyperparameter Optimization through Neural Network Partitioning.

• Does Decentralized Learning with Non-IID Unlabeled Data Benefit from Self Supervision?

• Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top.