Provably Better Explanations with Optimized Aggregation of Feature Attributions

Volker Tresp, Florian Buettner, Jindong Gu, Thomas Decker, Ananta Bhattarai

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 1 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.

Repositories linked to this paper

• thomdeck/aggopt

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

Abstract

Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often produce inconsistent and unstable results, putting their overall reliability into question. In this work, we aim to systematically improve the quality of feature attributions by combining multiple explanations across distinct methods or their variations. For this purpose, we propose a novel approach to derive optimal convex combinations of feature attributions that yield provable improvements of desired quality criteria such as robustness or faithfulness to the model behavior. Through extensive experiments involving various model architectures and popular feature attribution techniques, we demonstrate that our combination strategy consistently outperforms individual methods and existing baselines.

For agents

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

get_harvested_code_for_paper("2406.05090")
get_code_for_paper("2406.05090")
have("2406.05090")

Connect an agent — have() is free.