{"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/semi-supervised-graph-classification-a","title":"Semi-Supervised Graph Classification: A Hierarchical Graph Perspective","arxiv_id":"1904.05003","date":"2019-04-10","proceeding":null,"authors":["Jia Li","Yu Rong","Hong Cheng","Helen Meng","Wenbing Huang","Junzhou Huang"],"abstract":"Node classification and graph classification are two graph learning problems\nthat predict the class label of a node and the class label of a graph\nrespectively. A node of a graph usually represents a real-world entity, e.g., a\nuser in a social network, or a protein in a protein-protein interaction\nnetwork. In this work, we consider a more challenging but practically useful\nsetting, in which a node itself is a graph instance. This leads to a\nhierarchical graph perspective which arises in many domains such as social\nnetwork, biological network and document collection. For example, in a social\nnetwork, a group of people with shared interests forms a user group, whereas a\nnumber of user groups are interconnected via interactions or common members. We\nstudy the node classification problem in the hierarchical graph where a `node'\nis a graph instance, e.g., a user group in the above example. As labels are\nusually limited in real-world data, we design two novel semi-supervised\nsolutions named \\underline{SE}mi-supervised gr\\underline{A}ph\nc\\underline{L}assification via \\underline{C}autious/\\underline{A}ctive\n\\underline{I}teration (or SEAL-C/AI in short). SEAL-C/AI adopt an iterative\nframework that takes turns to build or update two classifiers, one working at\nthe graph instance level and the other at the hierarchical graph level. To\nsimplify the representation of the hierarchical graph, we propose a novel\nsupervised, self-attentive graph embedding method called SAGE, which embeds\ngraph instances of arbitrary size into fixed-length vectors. Through\nexperiments on synthetic data and Tencent QQ group data, we demonstrate that\nSEAL-C/AI not only outperform competing methods by a significant margin in\nterms of accuracy/Macro-F1, but also generate meaningful interpretations of the\nlearned representations.","url_abs":"http://arxiv.org/abs/1904.05003v1","url_pdf":"http://arxiv.org/pdf/1904.05003v1.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":"semi-supervised-graph-classification-a","repo_url":"https://github.com/benedekrozemberczki/SEAL-CI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-dd","task":"Graph Classification","dataset":"D&D","model":"SEAL-SAGE","rank_in_archive_order":11,"of":53,"metrics":{"Accuracy":"80.88%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-proteins","task":"Graph Classification","dataset":"PROTEINS","model":"SEAL-SAGE","rank_in_archive_order":33,"of":103,"metrics":{"Accuracy":"77.26%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.05003","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}