Privacy papers in ICML 2021

2 minute read

Published: June 06, 2021

I have curated and am beginning to read ICML ‘21 papers related to privacy and federated learning. The list will be constantly updated with the paper summaries. Stay tuned!
Note that I wrote a simple script to scrape the links to the paper and the links may not be accurate.

Title	Summary
Differentially Private Quantiles
Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix
Large Scale Private Learning via Low-rank Reparametrization
Differentially Private Densest Subgraph Detection
PAPRIKA: Private Online False Discovery Rate Control
FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Analysis
Personalized Federated Learning using Hypernetworks
Federated Composite Optimization
Exploiting Shared Representations for Personalized Federated Learning
Oneshot Differentially Private Top-k Selection
Data-Free Knowledge Distillation for Heterogeneous Federated Learning
Privacy-Preserving Video Classification with Convolutional Neural Networks
Federated Continual Learning with Weighted Inter-client Transfer
Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity
Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning
Differentially Private Query Release Through Adaptive Projection
A Framework for Private Matrix Analysis in Sliding Window Model
Federated Learning of User Verification Models Without Sharing Embeddings
Differentially Private Aggregation in the Shuffle Model: Almost Central Accuracy in Almost a Single Message
Locally Private k-Means in One Round
[Differentially-Private Clustering of Easy Instances]
Differentially Private Sliced Wasserstein Distance	privatize sliced W. distance by utilizing random projection techniques plus gaussian noises. Applied to domain adaptation and gen. models. Showed that generating faces is feasible
Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning
Ditto: Fair and Robust Federated Learning Through Personalization	simple regularization between the global and local terms
Differentially Private Correlation Clustering
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
Private Alternating Least Squares: (Nearly) Optimal Privacy/Utility Trade-off for Matrix Completion
Lossless Compression of Efficient Private Local Randomizers
Differentially Private Bayesian Inference for Generalized Linear Models
Heterogeneity for the Win: One-Shot Federated Clustering
Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry
Practical and Private (Deep) Learning without Sampling or Shuffling
DeepReDuce: ReLU Reduction for Fast Private Inference
Privacy-Preserving Feature Selection with Secure Multiparty Computation
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
Debiasing Model Updates for Improving Personalized Federated Training
Leveraging Public Data for Practical Private Query Release
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
Learner-Private Online Convex Optimization
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Federated Learning under Arbitrary Communication Patterns
Private Adaptive Gradient Methods for Convex Optimization

Seng Pei Liew

Privacy papers in ICML 2021

You May Also Enjoy

ICLR 2023 privacy/FL papers

ICML 2022 privacy papers

Awesome list of DP resources

Privacy papers in ICLR 2021