NeurIPS 2021 accepted papers on Federated learning and privacy
72 of the 2,508 papers accepted at NeurIPS 2021 (2.9%) are on Federated learning and privacy, compared with 2.1% at NeurIPS 2020. They fall into 4 topics.
See NeurIPS 2021 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 · 37 papers
- Differentially Private Learning with Adaptive Clipping (86 citations)
- Remember What You Want to Forget: Algorithms for Machine Unlearning (64 citations)
- The Skellam Mechanism for Differentially Private Federated Learning (34 citations)
- G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators (19 citations)
- Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization (18 citations)
- Differentially Private Empirical Risk Minimization under the Fairness Lens (12 citations)
- Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods (11 citations)
- Robust and differentially private mean estimation (11 citations)
- Covariance-Aware Private Mean Estimation Without Private Covariance Estimation (10 citations)
- Instance-optimal Mean Estimation Under Differential Privacy (9 citations)
- Antipodes of Label Differential Privacy: PATE and ALIBI (8 citations)
- Fast and Memory Efficient Differentially Private-SGD via JL Projections (8 citations)
and 25 more in the interactive map.
Communication-efficient FL · 17 papers
- Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients (39 citations)
- Sageflow: Robust Federated Learning against Both Stragglers and Adversaries (36 citations)
- Breaking the centralized barrier for cross-device federated learning (30 citations)
- Fast Federated Learning in the Presence of Arbitrary Device Unavailability (24 citations)
- Federated Reconstruction: Partially Local Federated Learning (24 citations)
- Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning (22 citations)
- STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning (20 citations)
- DeepReduce: A Sparse-tensor Communication Framework for Federated Deep Learning (12 citations)
- FedDR – Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization (12 citations)
- Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing (11 citations)
- DRIVE: One-bit Distributed Mean Estimation (9 citations)
- Few-Round Learning for Federated Learning (7 citations)
and 5 more in the interactive map.
Privacy attacks and secure learning · 9 papers
- Evaluating Gradient Inversion Attacks and Defenses in Federated Learning (122 citations)
- CrypTen: Secure Multi-Party Computation Meets Machine Learning (62 citations)
- CAFE: Catastrophic Data Leakage in Vertical Federated Learning (15 citations)
- FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective (15 citations)
- Circa: Stochastic ReLUs for Private Deep Learning (12 citations)
- Revealing and Protecting Labels in Distributed Training (8 citations)
- Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee (7 citations)
- Gradient Inversion with Generative Image Prior (3 citations)
- Wisdom of the Crowd Voting: Truthful Aggregation of Voter Information and Preferences (3 citations)
Personalized and heterogeneous FL · 9 papers
- Federated Multi-Task Learning under a Mixture of Distributions (91 citations)
- FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout (64 citations)
- PartialFed: Cross-Domain Personalized Federated Learning via Partial Initialization (48 citations)
- No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data (39 citations)
- Parameterized Knowledge Transfer for Personalized Federated Learning (25 citations)
- Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis (24 citations)
- Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning (19 citations)
- Personalized Federated Learning With Gaussian Processes (11 citations)
- QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning (5 citations)
