19 citations · 49 across the 11 of their papers we have counts for
6 papers · 1 filter
DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators
Tejumade Afonja, Hui-Po Wang, Raouf Kerkouche +1
Generating tabular data under differential privacy (DP) protection ensures theoretical privacy guarantees but poses challenges for training machine learning models, primarily due t…
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
Hui-Po Wang, Mario Fritz
Despite the widespread use of statistical prior models in various fields, such models for neural network gradients have long been overlooked. The inherent challenge stems from thei…
FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations
Hui-Po Wang, Dingfan Chen, Raouf Kerkouche +1
Conventional gradient-sharing approaches for federated learning (FL), such as FedAvg, rely on aggregation of local models and often face performance degradation under differential…
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
Hui-Po Wang, Sebastian U. Stich, Yang He +1
Federated learning is a powerful distributed learning scheme that allows numerous edge devices to collaboratively train a model without sharing their data. However, training is res…
CosSGD: Communication-Efficient Federated Learning with a Simple Cosine-Based Quantization
Yang He, Hui-Po Wang, Maximilian Zenk +1
Federated learning is a promising framework to mitigate data privacy and computation concerns. However, the communication cost between the server and clients has become the major b…
Learning Priors for Adversarial Autoencoders
Hui-Po Wang, Wen-Hsiao Peng, Wei-Jan Ko
Most deep latent factor models choose simple priors for simplicity, tractability or not knowing what prior to use. Recent studies show that the choice of the prior may have a profo…