2 papers
cs.LG2026
XtrAIn: Training-Guided Occlusion for Feature Attribution
Thodoris Lymperopoulos, Ioannis Kakogeorgiou, Denia Kanellopoulou
Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting change in model output. However…
cs.LG2026
From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks
Thodoris Lymperopoulos, Denia Kanellopoulou
Fully Connected Neural Networks (FCNNs) are often regarded as simple and intuitive architectures, yet they serve as the foundation for more complex models. Nonetheless, the lack of…