{"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/incorporating-symbolic-domain-knowledge-into","title":"Incorporating Symbolic Domain Knowledge into Graph Neural Networks","arxiv_id":"2010.13900","date":"2020-10-23","proceeding":null,"authors":["Tirtharaj Dash","Ashwin Srinivasan","Lovekesh Vig"],"abstract":"Our interest is in scientific problems with the following characteristics: (1) Data are naturally represented as graphs; (2) The amount of data available is typically small; and (3) There is significant domain-knowledge, usually expressed in some symbolic form. These kinds of problems have been addressed effectively in the past by Inductive Logic Programming (ILP), by virtue of 2 important characteristics: (a) The use of a representation language that easily captures the relation encoded in graph-structured data, and (b) The inclusion of prior information encoded as domain-specific relations, that can alleviate problems of data scarcity, and construct new relations. Recent advances have seen the emergence of deep neural networks specifically developed for graph-structured data (Graph-based Neural Networks, or GNNs). While GNNs have been shown to be able to handle graph-structured data, less has been done to investigate the inclusion of domain-knowledge. Here we investigate this aspect of GNNs empirically by employing an operation we term \"vertex-enrichment\" and denote the corresponding GNNs as \"VEGNNs\". Using over 70 real-world datasets and substantial amounts of symbolic domain-knowledge, we examine the result of vertex-enrichment across 5 different variants of GNNs. Our results provide support for the following: (a) Inclusion of domain-knowledge by vertex-enrichment can significantly improve the performance of a GNN. That is, the performance VEGNNs is significantly better than GNNs across all GNN variants; (b) The inclusion of domain-specific relations constructed using ILP improves the performance of VEGNNs, across all GNN variants. Taken together, the results provide evidence that it is possible to incorporate symbolic domain knowledge into a GNN, and that ILP can play an important role in providing high-level relationships that are not easily discovered by a GNN.","url_abs":"https://arxiv.org/abs/2010.13900v2","url_pdf":"https://arxiv.org/pdf/2010.13900v2.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":"incorporating-symbolic-domain-knowledge-into","repo_url":"https://github.com/tirtharajdash/VEGNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"incorporating-symbolic-domain-knowledge-into","repo_url":"https://github.com/tirtharajdash/BotGNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inductive-logic-programming","task_name":"Inductive logic programming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}