ICML 2019 accepted papers on Federated learning and privacy
18 of the 774 papers accepted at ICML 2019 (2.3%) are on Federated learning and privacy, compared with 1.3% at ICML 2018. They fall into 4 topics.
See ICML 2019 in the interactive map
Submitting to ICML? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Differential privacy · 12 papers
- On Sparse Linear Regression in the Local Differential Privacy Model (44 citations)
- Graphical-model based estimation and inference for differential privacy (34 citations)
- Bounding User Contributions: A Bias-Variance Trade-off in Differential Privacy (33 citations)
- Differentially Private Empirical Risk Minimization with Non-convex Loss Functions (32 citations)
- Communication Complexity in Locally Private Distribution Estimation and Heavy Hitters (25 citations)
- Poission Subsampled Rényi Differential Privacy (20 citations)
- Differentially Private Fair Learning (18 citations)
- Locally Private Bayesian Inference for Count Models (14 citations)
- Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA (10 citations)
- Formal Privacy for Functional Data with Gaussian Perturbations (7 citations)
- Differentially Private Learning of Geometric Concepts
- Sublinear Space Private Algorithms Under the Sliding Window Model
Communication-efficient FL · 3 papers
- Agnostic Federated Learning (403 citations)
- Distributed Learning over Unreliable Networks (20 citations)
- Communication-Constrained Inference and the Role of Shared Randomness (2 citations)
Personalized and heterogeneous FL · 2 papers
Privacy attacks and secure learning · 1 paper
- Low Latency Privacy Preserving Inference (52 citations)
