{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/capsule-graph-neural-network","title":"Capsule Graph Neural Network","arxiv_id":null,"date":"2019-05-01","proceeding":"ICLR 2019 5","authors":["Zhang Xinyi","Lihui Chen"],"abstract":"The high-quality node embeddings learned from the Graph Neural Networks (GNNs) have been applied to a wide range of node-based applications and some of them have achieved state-of-the-art (SOTA) performance. However, when applying node embeddings learned from GNNs to generate graph embeddings, the scalar node representation may not suffice to preserve the node/graph properties efficiently, resulting in sub-optimal graph embeddings.\n\nInspired by the Capsule Neural Network (CapsNet), we propose the Capsule Graph Neural Network (CapsGNN), which adopts the concept of capsules to address the weakness in existing GNN-based graph embeddings algorithms. By extracting node features in the form of capsules, routing mechanism can be utilized to capture important information at the graph level. As a result, our model generates multiple embeddings for each graph to capture graph properties from different aspects. The attention module incorporated in CapsGNN is used to tackle graphs with various sizes which also enables the model to focus on critical parts of the graphs.\n\nOur extensive evaluations with 10 graph-structured datasets demonstrate that CapsGNN has a powerful mechanism that operates to capture macroscopic properties of the whole graph by data-driven. It outperforms other SOTA techniques on several graph classification tasks, by virtue of the new instrument.","url_abs":"https://openreview.net/forum?id=Byl8BnRcYm","url_pdf":"https://openreview.net/pdf?id=Byl8BnRcYm","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":"capsule-graph-neural-network","repo_url":"https://github.com/benedekrozemberczki/CapsGNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-collab","task":"Graph Classification","dataset":"COLLAB","model":"CapsGNN","rank_in_archive_order":16,"of":39,"metrics":{"Accuracy":"79.62%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"CapsGNN","rank_in_archive_order":45,"of":53,"metrics":{"Accuracy":"75.38%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-enzymes","task":"Graph Classification","dataset":"ENZYMES","model":"CapsGNN","rank_in_archive_order":37,"of":54,"metrics":{"Accuracy":"54.67%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"CapsGNN","rank_in_archive_order":33,"of":51,"metrics":{"Accuracy":"73.10%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-m","task":"Graph Classification","dataset":"IMDb-M","model":"CapsGNN","rank_in_archive_order":22,"of":36,"metrics":{"Accuracy":"50.27%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"CapsGNN","rank_in_archive_order":54,"of":74,"metrics":{"Accuracy":"86.67%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci1","task":"Graph Classification","dataset":"NCI1","model":"CapsGNN","rank_in_archive_order":41,"of":69,"metrics":{"Accuracy":"78.35%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"CapsGNN","rank_in_archive_order":53,"of":103,"metrics":{"Accuracy":"76.28%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-re-m12k","task":"Graph Classification","dataset":"RE-M12K","model":"CapsGNN","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy":"46.62%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-re-m5k","task":"Graph Classification","dataset":"RE-M5K","model":"CapsGNN","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy":"52.88%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"benedekrozemberczki/CapsGNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3a256d579fbd81a2889aa4fee8e6ba760e1970aeedfe7d239e63d0b4d5af7d31","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}