Seng Pei Liew

Seng Pei Liew

Research Scientist
Machine Learning
Physics

ICLR 2023 privacy/FL papers

3 minute read

Published:

I have curated and am beginning to read ICLR ‘23 papers related to privacy and federated learning. The list will be constantly updated with the paper summaries. Stay tuned!

TitleSummary
Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning 
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning 
On the Importance and Applicability of Pre-Training for Federated Learning 
The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation 
Bias Propagation in Federated Learning 
Federated Neural Bandits 
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models 
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation 
FedExP: Speeding Up Federated Averaging via Extrapolation 
A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy 
Federated Learning from Small Datasets 
Effective passive membership inference attacks in federated learning against overparameterized models 
Hyperparameter Optimization through Neural Network Partitioning 
EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data 
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning 
Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach 
Machine Unlearning of Federated Clusters 
Federated Nearest Neighbor Machine Translation 
Faster federated optimization under second-order similarity 
PerFedMask: Personalized Federated Learning with Optimized Masking Vectors 
Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning 
FedFA: Federated Feature Augmentation 
Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision? 
Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses 
Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection 
Better Generative Replay for Continual Federated Learning 
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication 
Personalized Federated Learning with Feature Alignment and Classifier Collaboration 
FedDAR: Federated Domain-Aware Representation Learning 
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning 
FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy 
Instance-wise Batch Label Restoration via Gradients in Federated Learning 
DepthFL : Depthwise Federated Learning for Heterogeneous Clients 
Multimodal Federated Learning via Contrastive Representation Ensemble 
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification 
Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses 
Sparse Random Networks for Communication-Efficient Federated Learning 
Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity 
Single-shot General Hyper-parameter Optimization for Federated Learning 
Test-Time Robust Personalization for Federated Learning 
Towards Addressing Label Skews in One-Shot Federated Learning 
MocoSFL: enabling cross-client collaborative self-supervised learning 
Individual Privacy Accounting with Gaussian Differential Privacy 
Regression with Label Differential Privacy 
Synthetic Data Generation of Many-to-Many Datasets via Random Graph Generation 
Differentially Private Adaptive Optimization with Delayed Preconditioners 
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping 
Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms 
Distributed Differential Privacy in Multi-Armed Bandits 
Differentially Private $L_2$-Heavy Hitters in the Sliding Window Model 
Efficient Model Updates for Approximate Unlearning of Graph-Structured Data 
Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference 
MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPC 
Disparate Impact in Differential Privacy from Gradient Misalignment 
Easy Differentially Private Linear Regression 
Stochastic Differentially Private and Fair Learning 

You May Also Enjoy

ICML 2022 privacy papers

1 minute read

Published:

I have curated and am beginning to read ICML ‘22 papers related to privacy and federated learning. The list will be constantly updated with the paper summaries. Stay tuned!

Awesome list of DP resources

less than 1 minute read

Published:

I am curating a list of resources for learning subjects related to differential privacy, federated learning and machine learning (subject to my preferences).

Privacy papers in ICML 2021

2 minute read

Published:

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.

Privacy papers in ICLR 2021

1 minute read

Published:

I have curated and am beginning to read ICLR ‘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.