We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes standard molecular feature extraction methods based on circular fingerprints. We show that these data-driven features are more interpretable, and have better predictive performance on a variety of tasks.
Convolutional Networks on Graphs for Learning Molecular Fingerprints
A convolutional neural network operating on graphs provides interpretable and predictive features for various tasks, generalizing standard molecular feature extraction.
- Year
- 2015
- Venue
- convolutional-networks-on-graphs-for-learning-1
- Authors
- 7
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/1509.09292v2ARXIV-DEFAULT
- TL;DR
- Semantic Scholar