SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.11420 · 2019

Do Not Trust Additive Explanations

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
jettify/ibreakdown reimplementation 3 of 4
FunctionStatusWhere it lives
build_model Ran jettify/ibreakdown/examples/titanic.py
code served (permissive licence) · get_code("0ce6e2db08e2510d")
idx_to_name Ran jettify/ibreakdown/ibreakdown/iexplainer.py
code served (permissive licence) · get_code("3603a44f23d9614a")
train_model Ran jettify/ibreakdown/examples/titanic.py
code served (permissive licence) · get_code("7bd468778004d05a")
read_dataset Not yet run jettify/ibreakdown/examples/titanic.py
code served (permissive licence) · get_code("65b1e64dcb6aecd7")

Repositories linked to this paper

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

Abstract

Explainable Artificial Intelligence (XAI)has received a great deal of attention recently. Explainability is being presented as a remedy for the distrust of complex and opaque models. Model agnostic methods such as LIME, SHAP, or Break Down promise instance-level interpretability for any complex machine learning model. But how faithful are these additive explanations? Can we rely on additive explanations for non-additive models? In this paper, we (1) examine the behavior of the most popular instance-level explanations under the presence of interactions, (2) introduce a new method that detects interactions for instance-level explanations, (3) perform a large scale benchmark to see how frequently additive explanations may be misleading.

For agents

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

get_harvested_code_for_paper("1903.11420")
get_code_for_paper("1903.11420")
have("1903.11420")

Connect an agent — have() is free.