SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.09069 · 2024

On the Robustness of Global Feature Effect Explanations

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 4 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
hbaniecki/robust-feature-effects canonical 4 of 4
FunctionStatusWhere it lives
check_early_stopping Ran hbaniecki/robust-feature-effects/src/utils.py
code served (permissive licence) · get_code("6d5caa9f8bb4b5f7")
distance_values Ran hbaniecki/robust-feature-effects/src/loss.py
code served (permissive licence) · get_code("3b200194bc918ad6")
loss Ran hbaniecki/robust-feature-effects/src/loss.py
code served (permissive licence) · get_code("831e0df4b6f765d1")
loss_pop Ran hbaniecki/robust-feature-effects/src/loss.py
code served (permissive licence) · get_code("70b16a7fc8254617")

Repositories linked to this paper

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

Abstract

We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model debugging and scientific discovery in applied sciences. However, how vulnerable they are to data and model perturbations remains an open research question. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects. Our experimental results with synthetic and real-world datasets quantify the gap between the best and worst-case scenarios of (mis)interpreting machine learning predictions globally.

For agents

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

get_harvested_code_for_paper("2406.09069")
get_code_for_paper("2406.09069")
have("2406.09069")

Connect an agent — have() is free.