X-raying Models with A Matrix to Reveal Backdoor Attacks for Federated Learning.

使用LSTM及股票因子数据预测未来收益，使用LRP(layer-wise relevance propagation)增强网络可解释性

Differential private machine learning

联邦学习隐私保护综述

A pytorch implemention of the Explainable AI work 'Contrastive layerwise relevance propagation (CLRP)'

A PyTorch 1.6 implementation of Layer-Wise Relevance Propagation (LRP).

天涯 kkndme 神贴聊房价

torch-optimizer -- collection of optimizers for Pytorch

interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI

Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"

Experiments on AMSGrad

Experiments on AMSGrad -- pytorch version

An optimizer that trains as fast as Adam and as good as SGD.

An optimizer that trains as fast as Adam and as good as SGD.

Some improvements on Adam

Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"

Codes accompanying the paper "LaProp: a Better Way to Combine Momentum with Adaptive Gradient"

Simple Tensorflow implementation of "On the Convergence of Adam and Beyond" (ICLR 2018)

The code for the paper: https://arxiv.org/abs/1806.06317

联邦学习

Algorithms to recover input data from their gradient signal through a neural network

Implementation of dp-based federated learning framework using PyTorch

simple Differential Privacy in PyTorch

Concentrated Differentially Private Gradient Descent with Adaptive per-iteration Privacy Budget

Diffprivlib: The IBM Differential Privacy Library

Differential Privacy Preservation in Deep Learning under Model Attacks

Analytic calibration for differential privacy with Gaussian perturbations