Search Results for author:
Found 4 papers, 2 papers with code
Global Concept Explanations for Graphs by Contrastive Learning
Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.
Mitigating Molecular Aggregation in Drug Discovery with Predictive Insights from Explainable AI
As the importance of high-throughput screening (HTS) continues to grow due to its value in early stage drug discovery and data generation for training machine learning models, there is a growing need for robust methods for pre-screening compounds to identify and prevent false-positive hits.
Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies
In this work, we extend artificial simulatability studies to the domain of graph neural networks.
MEGAN: Multi-Explanation Graph Attention Network
Unlike existing graph explainability methods, our network can produce node and edge attributional explanations along multiple channels, the number of which is independent of task specifications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
