paper-with-me

홈 › Papers

EP-GAN: Unsupervised Federated Learning with Expectation-Propagation Prior GAN

2021-09-29 · Xueyang Wu, Hengguan Huang, Hao Wang, Ye Wang, Qian Xu

Generative Adversarial Networks (GANs) are overwhelming in unsupervised learning tasks due to their expressive power in modeling fine-grained data distributions. However, it is challenging for GANs to model distributions of separate non-i.i.d. data partitions as it usually adopts an over-general prior, limiting its capability in capturing the latent structure of multiple data partitions and thus leading to mode collapse. In this paper, we present a new Bayesian GAN, dubbed expectation propagation prior GAN (EP-GAN), which addresses the above challenge of modeling non-i.i.d. federated data through imposing a partition-invariant prior distribution on a Bayesian GAN. Furthermore, unlike most existing algorithms for deep-learning-based EP inference that require numerical quadrature, here we propose a closed-form solution for each update step of EP, leading to a more efficient solution for federated data modeling. Experiments on both synthetic extremely non-i.i.d. image data partitions and realistic non-i.i.d. speech recognition tasks demonstrate that our framework effectively alleviates the performance deterioration caused by non-i.i.d. data.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach

2023-02-08 · Han Guo, Philip Greengard, Hongyi Wang, Andrew Gelman 외

The canonical formulation of federated learning treats it as a distributed optimization problem where the model parameters are optimized against a global loss function that decomposes across client loss functions. A rece…

Distributed OptimizationFederated LearningVariational Inference

Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation

2022-10-02 · Xinhang Liu, Jiaben Chen, Huai Yu, Yu-Wing Tai 외

We present radiance field propagation (RFP), a novel approach to segmenting objects in 3D during reconstruction given only unlabeled multi-view images of a scene. RFP is derived from emerging neural radiance field-based …

3D Object EditingNeRFObjectScene Segmentation+2

An Expectation-Maximization Perspective on Federated Learning

2021-11-19 · Christos Louizos, Matthias Reisser, Joseph Soriaga, Max Welling

Federated learning describes the distributed training of models across multiple clients while keeping the data private on-device. In this work, we view the server-orchestrated federated learning process as a hierarchical…

Federated Learning

Federated Averaging as Expectation Maximization

2021-01-01 · Christos Louizos, Matthias Reisser, Joseph Soriaga, Max Welling

Federated averaging (FedAvg), despite its simplicity, has been the main approach in training neural networks in the federated learning setting. In this work, we show that the algorithmic choices of the FedAvg algorithm c…

Federated Learning

Fast Scalable Image Restoration using Total Variation Priors and Expectation Propagation

2021-10-04 · Dan Yao, Stephen McLaughlin, Yoann Altmann

This paper presents a scalable approximate Bayesian method for image restoration using total variation (TV) priors. In contrast to most optimization methods based on maximum a posteriori estimation, we use the expectatio…

Compressive SensingDenoisingImage Restoration