This version of DeepLIFT has been tested with Keras 2.2.4 & tensorflow 1.14.0. See this FAQ question for information on other implementations of DeepLIFT that may work with different versions of tensorflow/pytorch, as well as a wider range of architectures. See the tags for older versions.
This repository implements the methods in “Learning Important Features Through Propagating Activation Differences” by Shrikumar, Greenside & Kundaje, as well as other commonly-used methods such as gradients, gradient-times-input (equivalent to a version of Layerwise Relevance Propagation for ReLU networks), guided backprop and integrated gradients.
(1) DeepExplain uses standard gradient backpropagation for elementwise operations (such as those present in LSTMs/GRUs/Attention).
(2) DeepExplain (by Ancona et al.) does not support the dynamic reference that is demonstrated in the DeepLIFT repo (i.e. the case where a different reference is generated according to the properties of the input example, such as the ‘dinucleotide shuffled’ references used in genomics).
(3) DeepSHAP/DeepExplainer is implemented such that multiple references can be used for a single example, and the final attributions are averaged over each reference.
1275 Av. des Canadiens-de-Montréal,
Montréal, QC H3B 0G4
Canada
312 Arizona Ave,
Santa Monica, CA 90401,
USA
Gate Avenue Zone D at DIFC – Sheikh Zayed Road
Dubai, United Arab Emirates
1 Al Corniche St, Burj Doha, level 21,
Doha, Qatar
© Copyright 2022. All rights reserved by Rocket Science Development
