ICML 2024 accepted papers on Federated learning and privacy
100 of the 2,610 papers accepted at ICML 2024 (3.8%) are on Federated learning and privacy, compared with 4.8% at ICML 2023. They fall into 4 topics.
See ICML 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Differential privacy · 40 papers
- Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining (9 citations)
- Differentially Private Bias-Term Fine-tuning of Foundation Models (5 citations)
- CuTS: Customizable Tabular Synthetic Data Generation (4 citations)
- Differentially Private Representation Learning via Image Captioning (3 citations)
- Differentially Private Synthetic Data via Foundation Model APIs 2: Text (2 citations)
- A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization (1 citation)
- Auditing Private Prediction (1 citation)
- Delving into Differentially Private Transformer (1 citation)
- Differentially Private Post-Processing for Fair Regression (1 citation)
- Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent (1 citation)
- Shifted Interpolation for Differential Privacy (1 citation)
- Better Locally Private Sparse Estimation Given Multiple Samples Per User
and 28 more in the interactive map.
Personalized and heterogeneous FL · 28 papers
- FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models (7 citations)
- Federated Neuro-Symbolic Learning (3 citations)
- FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering (2 citations)
- MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis (2 citations)
- Accelerating Heterogeneous Federated Learning with Closed-form Classifiers (1 citation)
- Harmonizing Generalization and Personalization in Federated Prompt Learning (1 citation)
- Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization (1 citation)
- Balancing Similarity and Complementarity for Federated Learning
- Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
- Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning
- FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler
- Federated Representation Learning in the Under-Parameterized Regime
and 16 more in the interactive map.
Communication-efficient FL · 19 papers
- Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes (7 citations)
- Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often! (2 citations)
- FADAS: Towards Federated Adaptive Asynchronous Optimization (1 citation)
- PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs (1 citation)
- A New Theoretical Perspective on Data Heterogeneity in Federated Optimization
- Achieving Lossless Gradient Sparsification via Mapping to Alternative Space in Federated Learning
- Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
- Decomposable Submodular Maximization in Federated Setting
- FedBAT: Communication-Efficient Federated Learning via Learnable Binarization
- Federated Optimization with Doubly Regularized Drift Correction
- Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems
- Pursuing Overall Welfare in Federated Learning through Sequential Decision Making
and 7 more in the interactive map.
Privacy attacks and secure learning · 13 papers
- Split-and-Denoise: Protect large language model inference with local differential privacy (4 citations)
- CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sources (1 citation)
- Privacy Attacks in Decentralized Learning (1 citation)
- Recovering Labels from Local Updates in Federated Learning (1 citation)
- Certifiably Byzantine-Robust Federated Conformal Prediction
- Disparate Impact on Group Accuracy of Linearization for Private Inference
- MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective
- Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
- AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated Learning
- FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
- Privacy-Preserving Embedding via Look-up Table Evaluation with Fully Homomorphic Encryption
- Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain Recommendation
and 1 more in the interactive map.