ICML

2024

• PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs.

• FedMBridge: Bridgeable Multimodal Federated Learning.

• Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization.

• SILVER: Single-loop variance reduction and application to federated learning.

• Accelerating Heterogeneous Federated Learning with Closed-form Classifiers.

• SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding.

• Effective Federated Graph Matching.

• Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!

• A New Theoretical Perspective on Data Heterogeneity in Federated Optimization.

• FADAS: Towards Federated Adaptive Asynchronous Optimization.

• Decomposable Submodular Maximization in Federated Setting.

• Recovering Labels from Local Updates in Federated Learning.

• Pursuing Overall Welfare in Federated Learning through Sequential Decision Making.

• Certifiably Byzantine-Robust Federated Conformal Prediction.

• Adaptive Group Personalization for Federated Mutual Transfer Learning.

• Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization.

• Ranking-based Client Imitation Selection for Efficient Federated Learning.

• Fair Federated Learning via the Proportional Veto Core.

• Federated Continual Learning via Prompt-based Dual Knowledge Transfer.

• A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional Optimization.

• FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error.

• Recurrent Early Exits for Federated Learning with Heterogeneous Clients.

• FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Data.

• Clustered Federated Learning via Gradient-based Partitioning.

• Federated Representation Learning in the Under-Parameterized Regime.

• Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning.

• Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments.

• Byzantine Resilient and Fast Federated Few-Shot Learning.

• Federated Neuro-Symbolic Learning.

• Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems.

• Improved Modelling of Federated Datasets using Mixtures-of-Dirichlet-Multinomials.

• Federated Combinatorial Multi-Agent Multi-Armed Bandits.

• FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models.

• Enhancing Storage and Computational Efficiency in Federated Multimodal Learning for Large-Scale Models.

• Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning.

• Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective.

• A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC Maximization.

• Balancing Similarity and Complementarity for Federated Learning.

• Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates.

• FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler.

• AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning.

• Rethinking the Flat Minima Searching in Federated Learning.

• FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering.

• Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices.

• Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning.

• Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms.

• Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses.

• Accelerating Federated Learning with Quick Distributed Mean Estimation.

• Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients.

• Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation.

• Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors.

• Self-Driven Entropy Aggregation for Byzantine-Robust Heterogeneous Federated Learning.

• COALA: A Practical and Vision-Centric Federated Learning Platform.

• FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees.

• Federated Optimization with Doubly Regularized Drift Correction.

• FedBAT: Communication-Efficient Federated Learning via Learnable Binarization.

• Harmonizing Generalization and Personalization in Federated Prompt Learning.

• Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes.

• Federated Self-Explaining GNNs with Anti-shortcut Augmentations.

• MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis.

2023

• Personalized Subgraph Federated Learning.

• Optimizing the Collaboration Structure in Cross-Silo Federated Learning.

• LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning.

• Fast Federated Machine Unlearning with Nonlinear Functional Theory.

• GuardHFL: Privacy Guardian for Heterogeneous Federated Learning.

• Efficient Personalized Federated Learning via Sparse Model-Adaptation.

• On the Convergence of Federated Averaging with Cyclic Client Participation.

• From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning.

• Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning.

• DoCoFL: Downlink Compression for Cross-Device Federated Learning.

• Federated Heavy Hitter Recovery under Linear Sketching.

• Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design.

• Out-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships.

• FeDXL: Provable Federated Learning for Deep X-Risk Optimization.

• FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction.

• Achieving Linear Speedup in Non-IID Federated Bilevel Learning.

• Federated Linear Contextual Bandits with User-level Differential Privacy.

• One-Shot Federated Conformal Prediction.

• Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis.

• Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial Participation.

• Revisiting Weighted Aggregation in Federated Learning with Neural Networks.

• Federated Adversarial Learning: A Framework with Convergence Analysis.

• FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models.

• Federated Conformal Predictors for Distributed Uncertainty Quantification.

• Vertical Federated Graph Neural Network for Recommender System.

• SRATTA: Sample Re-ATTribution Attack of Secure Aggregation in Federated Learning.

• Flash: Concept Drift Adaptation in Federated Learning.

• Secure Federated Correlation Test and Entropy Estimation.

• Towards Understanding Ensemble Distillation in Federated Learning.

• Federated Online and Bandit Convex Optimization.

• Conformal Prediction for Federated Uncertainty Quantification Under Label Shift.

• Improving the Model Consistency of Decentralized Federated Learning.

• Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape.

• Private Federated Learning with Autotuned Compression.

• TabLeak: Tabular Data Leakage in Federated Learning.

• FedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization.

• The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond.

• Anchor Sampling for Federated Learning with Partial Client Participation.

• Personalized Federated Learning under Mixture of Distributions.

• Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation.

• Personalized Federated Learning with Inferred Collaboration Graphs.

• FedDisco: Federated Learning with Discrepancy-Aware Collaboration.

• Doubly Adversarial Federated Bandits.

• FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information Regularization.

• Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction.

• No One Idles: Efficient Heterogeneous Federated Learning with Parallel Edge and Server Computation.

• Towards Unbiased Training in Federated Open-world Semi-supervised Learning.

• LeadFL: Client Self-Defense against Model Poisoning in Federated Learning.

• Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning.

2022

• Fast Composite Optimization and Statistical Recovery in Federated Learning.

• Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning.

• The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning.

• The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation.

• DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training.

• FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning.

• DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning.

• Accelerated Federated Learning with Decoupled Adaptive Optimization.

• Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling.

• Multi-Level Branched Regularization for Federated Learning.

• FedScale: Benchmarking Model and System Performance of Federated Learning at Scale.

• Federated Learning with Positive and Unlabeled Data.

• Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning.

• Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering.

• Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring.

• Architecture Agnostic Federated Learning for Neural Networks.

• Personalized Federated Learning through Local Memorization.

• Proximal and Federated Random Reshuffling.

• Federated Learning with Partial Model Personalization.

• Generalized Federated Learning via Sharpness Aware Minimization.

• FedNL: Making Newton-Type Methods Applicable to Federated Learning.

• Federated Minimax Optimization: Improved Convergence Analyses and Algorithms.

• Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning.

• FedNest: Federated Bilevel, Minimax, and Compositional Optimization.

• EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning.

• Communication-Efficient Adaptive Federated Learning.

• ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training.

• Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification.

• Anarchic Federated Learning.

• QSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning.

• Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization.

• Neural Tangent Kernel Empowered Federated Learning.

• Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy.

• Personalized Federated Learning via Variational Bayesian Inference.

• Federated Learning with Label Distribution Skew via Logits Calibration.

• Neurotoxin: Durable Backdoors in Federated Learning.

• Resilient and Communication Efficient Learning for Heterogeneous Federated Systems.

2021

• Debiasing Model Updates for Improving Personalized Federated Training.

• Federated Learning under Arbitrary Communication Patterns.

• One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning.

• Exploiting Shared Representations for Personalized Federated Learning.

• Heterogeneity for the Win: One-Shot Federated Clustering.

• Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning.

• Federated Learning of User Verification Models Without Sharing Embeddings.

• FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis.

• The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation.

• Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix.

• Ditto: Fair and Robust Federated Learning Through Personalization.

• Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning.

• Personalized Federated Learning using Hypernetworks.

• CRFL: Certifiably Robust Federated Learning against Backdoor Attacks.

• Federated Continual Learning with Weighted Inter-client Transfer.

• Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity.

• Federated Composite Optimization.

• Data-Free Knowledge Distillation for Heterogeneous Federated Learning.