Portrait of Samy Mammeri

Samy Mammeri

Research Intern - Université Laval
Supervisor
Christian Gagné
Research Topics
Deep Learning
Interpretability
Mechanistic Interpretability
Google Scholar

Publications

High-order Component Attribution via Kolmogorov-Arnold Networks
Samy Mammeri
Christian Gagné
Component attribution methods provide insight into how parts of deep learning models, such as convolutional filters and attention heads, inf… (see more)luence model predictions. Despite their successes, existing attribution approaches typically assume component effects are additive and independent, neglecting complex interactions among components. Capturing these relations between components is crucial for a better mechanistic understanding of these models. In this work, we improve component attribution (COAR) by replacing the linear counterfactual estimator with a Kolmogorov–Arnold Network (KAN) surrogate fitted to example‑wise perturbation–response data. Then, a symbolic approximation of the learned KAN lets us compute mixed partial derivatives that captures and makes explicit high‑order component interactions that linear methods are missing. These symbolic expressions facilitate future integration with formal verification methods, enabling richer counterfactual analyses of internal model behavior. Preliminary results on standard image classification models demonstrate that our approach improves the accuracy of predicted counterfactuals and enable extraction of higher-order component interactions compared to linear attribution methods.
2025-09-29
NeurIPS.cc/2025/Workshop/MechInterp (poster)
openreview.net
openreview.net