Graph transformation policy network for chemical reaction prediction Do, Kien, Tran, Truyen and Venkatesh, Svetha 2019, Graph transformation policy network for chemical reaction prediction, in KDD 2019 : Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, New York, N.Y., pp. 750-760, doi: 10.1145/3292500.3330958. Attached Files Name Description MIMEType Size Downloads Title Graph transformation policy network for chemical reaction prediction Author(s) Do, Kien Tran, Truyen orcid.org/0000-0001-6531-8907 Venkatesh, Svetha orcid.org/0000-0001-8675-6631 Conference name Knowledge Discovery & Data Mining. International Conference (25th : 2019 : Anchorage, Alaska) Conference location Anchorage, Alaska Conference dates 2019/08/04 - 2019/08/08 Title of proceedings KDD 2019 : Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining Publication date 2019 Start page 750 End page 760 Total pages 11 Publisher ACM Place of publication New York, N.Y. Summary We address a fundamental problem in chemistry known as chemical reaction product prediction. Our main insight is that the input reactant and reagent molecules can be jointly represented as graphs, and the process of generating product molecules from reactant molecules can be formulated as a set of graph transformations. To this end, we propose Graph Transformation Policy Network (GTPN) - a novel generic method that combines the strengths of graph neural networks and reinforcement learning to learn reactions directly from data with minimal chemical knowledge. Compared to previous methods, GTPN has some appealing properties such as: end-to-end learning, and making no assumption about the length or the order of graph transformations. In order to guide our model search through the complex discrete space of sets of graph transformations effectively, we extend the standard policy gradient loss by adding useful constraints. Evaluation results show that GTPN improves the top-1 accuracy over the current state-of-the-art method by about 3% on the large USPTO dataset. ISBN 9781450362016 Language eng DOI 10.1145/3292500.3330958 Indigenous content off HERDC Research category E1 Full written paper - refereed Copyright notice ©2019, The Authors Persistent URL http://hdl.handle.net/10536/DRO/DU:30129583 Document type: Conference Paper Collections: Faculty of Science, Engineering and Built Environment Centre for Pattern Recognition and Data Analytics (PRADA) Related Links Link Description Connect to published version (restricted access) Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Versions Version Filter Type Thu, 05 Sep 2019, 09:07:12 EST Thu, 05 Sep 2019, 11:28:36 EST Thu, 05 Sep 2019, 11:29:07 EST Fri, 06 Sep 2019, 05:02:43 EST Fri, 06 Sep 2019, 06:04:08 EST Mon, 09 Sep 2019, 10:40:51 EST Mon, 09 Sep 2019, 10:43:12 EST Sat, 12 Oct 2019, 01:30:17 EST Fri, 01 Nov 2019, 09:28:00 EST Filtered Full Citation counts:   Cited 1 times in TR Web of Science Cited 1 times in Scopus Search Google Scholar Access Statistics: 129 Abstract Views, 5 File Downloads  -  Detailed Statistics Created: Thu, 05 Sep 2019, 11:29:07 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.