Structured filter pruning is an effective approach for reducing the computational cost of deep neural networks while preserving efficient deployment on standard hardware. However, most existing pruning methods evaluate filters independently, overlooking the inter-layer spectral coupling between consecutive layers, whil...
Soumia Laroui, H. Seba, K. Amrouche et al.· Jordanian Journal of Compute...· 0 citations
X-StrGNN is presented, a post-hoc explanation layer that wraps a trained, frozen StrGNN and emits, for every flagged edge, dual attributions: a structural attribution identifying which contextual interactions in the enclosing subgraph drove the decision, and a temporal attribution identifying which historical snapshot...
Iyad Assaad Nekka, H. Seba, Walid Khaled Hidouci et al.· 0 citations
X-AddGraph is presented, a strictly post-hoc explainability framework built on a Dual Spatial-Temporal Attribution (DSTA) mechanism whose three components are each aligned with one of AddGraph's architectural modules: a gradient-based relevance attribution over the current adjacency structure (spatial), a direct readin...
Iyad Assaad Nekka, H. Seba, Khaled Walid Hidouci et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.