From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks
Authors: Thodoris Lymperopoulos, Denia Kanellopoulou
Summary
arXiv:2605. 15328v1 Announce Type: new Abstract: Fully Connected Neural Networks (FCNNs) are often regarded as simple and intuitive architectures, yet they serve as the foundation for more complex models.
Relevance
Read next because From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)", clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)", experiment "Follow-up to #354: cascading chunk-binding — does A→B, B→C, C→D propagate the full chain on a recipient trained only to emit A?". Matching terms: under, line, full, model. Source: arxiv cs.LG (Machine Learning).
Threat model
Potential threat/caveat for clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)": this item discusses limitation, limitations, bias.
Abstract
arXiv:2605.15328v1 Announce Type: new Abstract: 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 consensus on their interpretability continues to pose challenges, underscoring the enduring relevance of simpler, attribution-based approaches for understanding even the most advanced neural architectures. In this regard, we explore a novel idea for estimating feature attribution, by applying perturbation to the features' attached weights instead of their values. This method offers a fresh perspective aimed at mitigating common limitations in Occlusion techniques, such as Added Bias and Out-of-Distribution data. The application of this rule leads to the formation of a pair of novel attribution methods we call XWP and XWP_c. Founded on simple rules, our methods achieve competitive performance in identifying image signals for simple DNNs, competing with the most established attribution methods on standard baseline metrics. Our work thus contributes to the field of Explainability by introducing a robust framework that paves the way for addressing these long-standing vulnerabilities, and leads to more reliable and interpretable model explanations.