Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero, Zohreh Shams, Mateja Jamnik
Abstract
In this paper, we investigate how concept-based models (CMs) respond to out-of-distribution (OOD) inputs. CMs are interpretable neural architectures that first predict a set of high-level *concepts* (e.g., "stripes", "black") and then predict a task label from those concepts. In particular, we study the impact of *concept interventions* (i.e., operations where a human expert corrects a CM’s mispredicted concepts at test time) on CMs' task predictions when inputs are OOD. Our analysis reveals a weakness in current state-of-the-art CMs, which we term *leakage poisoning*, that prevents them from properly improving their accuracy when intervened on for OOD inputs. To address this, we introduce *MixCEM*, a new CM that learns to dynamically exploit leaked information missing from its concepts only when this information is in-distribution. Our results across tasks with and without complete sets of concept annotations demonstrate that MixCEMs outperform strong baselines by significantly improving their accuracy for both in-distribution and OOD samples in the presence and absence of concept interventions.
BibTeX
@inproceedings{
zarlenga2025avoiding,
title={Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts},
author={Mateo Espinosa Zarlenga and Gabriele Dominici and Pietro Barbiero and Zohreh Shams and Mateja Jamnik},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=7mxDGiF01U}
}