{"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/differentiable-physics-informed-graph","title":"Differentiable Physics-informed Graph Networks","arxiv_id":"1902.02950","date":"2019-02-08","proceeding":null,"authors":["Sungyong Seo","Yan Liu"],"abstract":"While physics conveys knowledge of nature built from an interplay between\nobservations and theory, it has been considered less importantly in deep neural\nnetworks. Especially, there are few works leveraging physics behaviors when the\nknowledge is given less explicitly. In this work, we propose a novel\narchitecture called Differentiable Physics-informed Graph Networks (DPGN) to\nincorporate implicit physics knowledge which is given from domain experts by\ninforming it in latent space. Using the concept of DPGN, we demonstrate that\nclimate prediction tasks are significantly improved. Besides the experiment\nresults, we validate the effectiveness of the proposed module and provide\nfurther applications of DPGN, such as inductive learning and multistep\npredictions.","url_abs":"http://arxiv.org/abs/1902.02950v2","url_pdf":"http://arxiv.org/pdf/1902.02950v2.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":"differentiable-physics-informed-graph","repo_url":"https://github.com/sungyongs/dpgn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"inductive-learning","task_name":"Inductive Learning"},{"task_slug":"weather-forecasting","task_name":"Weather Forecasting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weather-forecasting-on-sd","task":"Weather Forecasting","dataset":"SD","model":"DPGN","rank_in_archive_order":4,"of":10,"metrics":{"MSE (t+1)":"0.5149 ± 0.0831","MSE (t+6)":"0.6714 ± 0.1106"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.02950","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}