ProDG generates high-fidelity prototypes from model weights alone for data-free post-hoc explainability in prototype-based networks.
This looks like that: deep learning for interpretable image recognition.Advances in neural information processing systems, 32
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Subgraph Concept Network is a new GNN architecture that distills meaningful concepts at node, subgraph, and graph levels via soft clustering to improve explainability while maintaining competitive accuracy.
Enhanced ProtoPNet delivers the highest faithfulness score of 0.1534 when explaining diffusion-based MRI synthesis compared to other prototype methods.
citing papers explorer
-
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
ProDG generates high-fidelity prototypes from model weights alone for data-free post-hoc explainability in prototype-based networks.
-
Subgraph Concept Networks: Concept Levels in Graph Classification
Subgraph Concept Network is a new GNN architecture that distills meaningful concepts at node, subgraph, and graph levels via soft clustering to improve explainability while maintaining competitive accuracy.
-
Explainability in Generative Medical Diffusion Models: A Faithfulness-Based Analysis on MRI Synthesis
Enhanced ProtoPNet delivers the highest faithfulness score of 0.1534 when explaining diffusion-based MRI synthesis compared to other prototype methods.