Proj CDeepFuzz Paper Reading: SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks

Abstract

本文：SparseProp
Github: https://github.com/IST-DASLab/sparseprop
Task: a back-propagation algo for sparse training data, a fast vectorized implementation on commodity CPUs
特点： general, can apply to arbitrary sparsity and common layer types; the first support for sparse training on commodity hardware

实验：
效果：

1. 验证vectorized implementation加速，能在从头训练或者transfer learning两种场景下

本栏目推荐文章
• Generalised f-Mean Aggregation for Graph Neural Networks
• LocPatcH An efficient long-read hybrid error correction algorithm based on local pHMM
• Graph Condensation for Graph Neural Networks
• 论文精读：ST2Vec：道路网络中的时空轨迹相似性学习（ST2Vec: Spatio_Temporal Trajectory Similarity Learning in Road Networks）
• 论文阅读-Self-supervised and Interpretable Data Cleaning with Sequence Generative Adversarial Networks
• BIgdataAIML-IBM-A neural networks deep dive - An introduction to neural networks and their programming
• Relation Networks for Object Detection
• Local Relation Networks for Image Recognition： LRNet
• Squeeze-and-Excitation Networks：SENet，早期cv中粗糙的注意力
• Fully convolutional networks for semantic segmentation

Backpropagation SparseProp CDeepFuzz Efficient Networksbackpropagation sparseprop cdeepfuzz efficient labeling-free estimation cdeepfuzz efficient cdeepfuzz networks reading testing sparseprop backpropagation backpropagation unsupervised adaptation domain 神经网络backpropagation intuition神经 cdeepfuzz efficient memory-efficient