Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property скачать в хорошем качестве

Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property

Authors: Garrett Goh (Pacific Northwest National Laboratory); Charles Siegel (Pacific Northwest National Laboratory); Abhinav Vishnu (Pacific Northwest National Laboratory); Nathan Hodas (Pacific Northwest National Laboratory) Abstract: With access to large datasets, deep neural networks (DNN) have achieved human-level accuracy in image and speech recognition tasks. However, in chemistry, data is inherently small and frag- mented. In this work, we develop an approach of using rule-based knowledge for training ChemNet, a transferable and generaliz- able deep neural network for chemical property prediction that learns in a weak-supervised manner from large unlabeled chem- ical databases. When coupled with transfer learning approaches to predict other smaller datasets for chemical properties that it was not originally trained on, we show that ChemNet’s accuracy outperforms contemporary DNN models that were trained using conventional supervised learning. Furthermore, we demonstrate that the ChemNet pre-training approach is equally effective on both CNN (Chemception) and RNN (SMILES2vec) models, indi- cating that this approach is network architecture agnostic and is effective across multiple data modalities. Our results indicate a pre- trained ChemNet that incorporates chemistry domain knowledge, enables the development of generalizable neural networks for more accurate prediction of novel chemical properties. More on http://www.kdd.org/kdd2018/