{"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/graphvae-towards-generation-of-small-graphs","title":"GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders","arxiv_id":"1802.03480","date":"2018-02-09","proceeding":"ICLR 2018 1","authors":["Martin Simonovsky","Nikos Komodakis"],"abstract":"Deep learning on graphs has become a popular research topic with many\napplications. However, past work has concentrated on learning graph embedding\ntasks, which is in contrast with advances in generative models for images and\ntext. Is it possible to transfer this progress to the domain of graphs? We\npropose to sidestep hurdles associated with linearization of such discrete\nstructures by having a decoder output a probabilistic fully-connected graph of\na predefined maximum size directly at once. Our method is formulated as a\nvariational autoencoder. We evaluate on the challenging task of molecule\ngeneration.","url_abs":"http://arxiv.org/abs/1802.03480v1","url_pdf":"http://arxiv.org/pdf/1802.03480v1.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":"graphvae-towards-generation-of-small-graphs","repo_url":"https://github.com/JiaxuanYou/graph-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.03480","atlas_url":"https://app.syntology.ai/?focus=1802.03480","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}