Polynomial-time max-product algorithms for exact (neuron-level) and approximate (node-level) top-K relevant walk search in GNN-LRP explanations.
Distill , year =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.
Gated SAEs decouple which features to use from how large their activations should be, applying the L1 penalty only to selection and thereby eliminating shrinkage while halving the number of firing features needed for good fidelity.
Message-passing algorithms compute GNN-LRP subgraph attributions in linear time w.r.t. network depth by exploiting the distributive property.
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.
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.
-
From Mechanistic to Compositional Interpretability
Compositional interpretability defines explanations as commuting syntactic-semantic mapping pairs grounded in compositionality and minimum description length, with compressive refinement and a parsimony theorem guaranteeing concise human-aligned decompositions.
-
Improving Dictionary Learning with Gated Sparse Autoencoders
Gated SAEs decouple which features to use from how large their activations should be, applying the L1 penalty only to selection and thereby eliminating shrinkage while halving the number of firing features needed for good fidelity.
-
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.
-
There Will Be a Scientific Theory of Deep Learning
A mechanics of the learning process is emerging in deep learning theory, characterized by dynamics, coarse statistics, and falsifiable predictions across idealized settings, limits, laws, hyperparameters, and universal behaviors.