A Practical Privacy-preserving Method in Federated Deep Learning

23 Feb 2020 • Yan Feng • Xue Yang • Weijun Fang • Shu-Tao Xia • Xiaohu Tang • Jun Shao • Tao Xiong

Although federated learning improves privacy of training data by exchanging model updates rather than raw data, many research results show that sharing the model updates may still involve risks. To alleviate this problem, many privacy-preserving techniques have been introduced to federated learning... (read more)

PDF Abstract

Results from the Paper

Add Remove

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Dense Connections	Feedforward Networks
Residual Connection	Skip Connections
Batch Normalization	Normalization
1x1 Convolution	Convolutions
Global Average Pooling	Pooling Operations
Kaiming Initialization	Initialization
Dropout	Regularization
Concatenated Skip Connection	Skip Connections
ReLU	Activation Functions
Max Pooling	Pooling Operations
Softmax	Output Functions
Residual Block	Skip Connection Blocks
Average Pooling	Pooling Operations
Bottleneck Residual Block	Skip Connection Blocks
ResNet	Convolutional Neural Networks
Dense Block	Image Model Blocks
Convolution	Convolutions
DenseNet	Convolutional Neural Networks

METHOD

TYPE

Dense Connections