Search Results for author:
Found 8 papers, 4 papers with code
The Deep Equilibrium Algorithmic Reasoner
Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms.
Parallel Algorithms Align with Neural Execution
Neural algorithmic reasoners are parallel processors.
Neural Algorithmic Reasoning for Combinatorial Optimisation
Solving NP-hard/complete combinatorial problems with neural networks is a challenging research area that aims to surpass classical approximate algorithms.
Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis
We propose a novel approach for producing global explanations for GNNs using neuron-level concepts to enable practitioners to have a high-level view of the model.
Algorithmic Concept-based Explainable Reasoning
Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems.
Neural Bipartite Matching
Graph neural networks (GNNs) have found application for learning in the space of algorithms.
