NeurIPS 2020 accepted papers on Federated learning and privacy
39 of the 1,901 papers accepted at NeurIPS 2020 (2.1%) are on Federated learning and privacy, compared with 2.0% at NeurIPS 2019. They fall into 4 topics.
See NeurIPS 2020 in the interactive map
Submitting to NeurIPS? 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 · 22 papers
- Auditing Differentially Private Machine Learning: How Private is Private SGD? (73 citations)
- Understanding Gradient Clipping in Private SGD: A Geometric Perspective (60 citations)
- GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators (56 citations)
- Differentially-Private Federated Linear Bandits (40 citations)
- CoinPress: Practical Private Mean and Covariance Estimation (25 citations)
- Locally private non-asymptotic testing of discrete distributions is faster using interactive mechanisms (21 citations)
- Permute-and-Flip: A new mechanism for differentially private selection (20 citations)
- Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms (17 citations)
- Differentially Private Clustering: Tight Approximation Ratios (16 citations)
- Learning discrete distributions: user vs item-level privacy (16 citations)
- The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space (15 citations)
- Learning from Mixtures of Private and Public Populations (12 citations)
and 10 more in the interactive map.
Communication-efficient FL · 9 papers
- Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization (565 citations)
- Personalized Federated Learning with Moreau Envelopes (213 citations)
- Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge (187 citations)
- Lower Bounds and Optimal Algorithms for Personalized Federated Learning (89 citations)
- Throughput-Optimal Topology Design for Cross-Silo Federated Learning (47 citations)
- Breaking the Communication-Privacy-Accuracy Trilemma (31 citations)
- Distributed Distillation for On-Device Learning (29 citations)
- An Efficient Framework for Clustered Federated Learning
- Federated Bayesian Optimization via Thompson Sampling
Privacy attacks and secure learning · 5 papers
- Inverting Gradients - How easy is it to break privacy in federated learning? (206 citations)
- CryptoNAS: Private Inference on a ReLU Budget (37 citations)
- A Scalable Approach for Privacy-Preserving Collaborative Machine Learning (29 citations)
- Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data (22 citations)
- Falcon: Fast Spectral Inference on Encrypted Data
