SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.03623 · 2020

Feature Removal Is a Unifying Principle for Model Explanation Methods

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another. We examine the literature and find that many methods are based on a shared principle of explaining by removing - essentially, measuring the impact of removing sets of features from a model. These methods vary in several respects, so we develop a framework for removal-based explanations that characterizes each method along three dimensions: 1) how the method removes features, 2) what model behavior the method explains, and 3) how the method summarizes each feature's influence. Our framework unifies 26 existing methods, including several of the most widely used approaches (SHAP, LIME, Meaningful Perturbations, permutation tests). Exposing the fundamental similarities between these methods empowers users to reason about which tools to use, and suggests promising directions for ongoing model explainability research.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2011.03623")
get_code_for_paper("2011.03623")
have("2011.03623")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2011.03623.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2011.03623.svg)](https://syntology.ai/paper/2011.03623)

Connect an agent — have() is free.