Linear TreeShap

TL;DR

Linear TreeShap offers a more efficient and straightforward exact algorithm for computing Shapley values in tree-based models, enhancing interpretability and scalability for complex ensembles.

Contribution

It introduces Linear TreeShap, an improved algorithm that simplifies and speeds up Shapley value computation for tree models while maintaining exactness.

Findings

Linear TreeShap reduces computation time compared to previous methods.

It maintains the same memory requirements as TreeShap.

The algorithm is exact and applicable to complex tree ensembles.

Abstract

Decision trees are well-known due to their ease of interpretability. To improve accuracy, we need to grow deep trees or ensembles of trees. These are hard to interpret, offsetting their original benefits. Shapley values have recently become a popular way to explain the predictions of tree-based machine learning models. It provides a linear weighting to features independent of the tree structure. The rise in popularity is mainly due to TreeShap, which solves a general exponential complexity problem in polynomial time. Following extensive adoption in the industry, more efficient algorithms are required. This paper presents a more efficient and straightforward algorithm: Linear TreeShap. Like TreeShap, Linear TreeShap is exact and requires the same amount of memory.