{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/constrained-graph-variational-autoencoders","title":"Constrained Graph Variational Autoencoders for Molecule Design","arxiv_id":"1805.09076","date":"2018-05-23","proceeding":"NeurIPS 2018 12","authors":["Qi Liu","Miltiadis Allamanis","Marc Brockschmidt","Alexander L. Gaunt"],"abstract":"Graphs are ubiquitous data structures for representing interactions between\nentities. With an emphasis on the use of graphs to represent chemical\nmolecules, we explore the task of learning to generate graphs that conform to a\ndistribution observed in training data. We propose a variational autoencoder\nmodel in which both encoder and decoder are graph-structured. Our decoder\nassumes a sequential ordering of graph extension steps and we discuss and\nanalyze design choices that mitigate the potential downsides of this\nlinearization. Experiments compare our approach with a wide range of baselines\non the molecule generation task and show that our method is more successful at\nmatching the statistics of the original dataset on semantically important\nmetrics. Furthermore, we show that by using appropriate shaping of the latent\nspace, our model allows us to design molecules that are (locally) optimal in\ndesired properties.","url_abs":"http://arxiv.org/abs/1805.09076v2","url_pdf":"http://arxiv.org/pdf/1805.09076v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"constrained-graph-variational-autoencoders","repo_url":"https://github.com/Microsoft/constrained-graph-variational-autoencoder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.09076","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}