DeepLIFT  –

GitHub Support CommunityModel interpretability

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.

Official website

Tutorial and documentation

Enter your contact information to continue reading