Polynomial-time max-product algorithms for exact (neuron-level) and approximate (node-level) top-K relevant walk search in GNN-LRP explanations.
A Unified Approach to Interpreting Model Predictions , volume =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Message-passing algorithms compute GNN-LRP subgraph attributions in linear time w.r.t. network depth by exploiting the distributive property.
SemiConLens is a visual analytics platform that uses correlation-aware imputation and linked views with uncertainty glyphs to support reliable discovery of 2D semiconductors from limited datasets.
citing papers explorer
-
Relevant Walk Search for Explaining Graph Neural Networks
Polynomial-time max-product algorithms for exact (neuron-level) and approximate (node-level) top-K relevant walk search in GNN-LRP explanations.
-
Efficient Higher-order Subgraph Attribution via Message Passing
Message-passing algorithms compute GNN-LRP subgraph attributions in linear time w.r.t. network depth by exploiting the distributive property.
-
SemiConLens: Visual Analytics for 2D Semiconductor Discovery
SemiConLens is a visual analytics platform that uses correlation-aware imputation and linked views with uncertainty glyphs to support reliable discovery of 2D semiconductors from limited datasets.