Agglomerative Contextual Decomposition

Introduced by Singh et al. in Hierarchical interpretations for neural network predictions

Agglomerative Contextual Decomposition (ACD) is an interpretability method that produces hierarchical interpretations for a single prediction made by a neural network, by scoring interactions and building them into a tree. Given a prediction from a trained neural network, ACD produces a hierarchical clustering of the input features, along with the contribution of each cluster to the final prediction. This hierarchy is optimized to identify clusters of features that the DNN learned are predictive.

Source: Hierarchical interpretations for neural network predictions

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Clustering	1	33.33%
Feature Importance	1	33.33%
Interpretable Machine Learning	1	33.33%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
Convolution	Convolutions	(optional)
LSTM	Recurrent Neural Networks	(optional)

Categories

Add Remove

Interpretability