{"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/when-work-matters-transforming-classical","title":"When Work Matters: Transforming Classical Network Structures to Graph CNN","arxiv_id":"1807.02653","date":"2018-07-07","proceeding":null,"authors":["Wenting Zhao","Chunyan Xu","Zhen Cui","Tong Zhang","Jiatao Jiang","Zhen-Yu Zhang","Jian Yang"],"abstract":"Numerous pattern recognition applications can be formed as learning from\ngraph-structured data, including social network, protein-interaction network,\nthe world wide web data, knowledge graph, etc. While convolutional neural\nnetwork (CNN) facilitates great advances in gridded image/video understanding\ntasks, very limited attention has been devoted to transform these successful\nnetwork structures (including Inception net, Residual net, Dense net, etc.) to\nestablish convolutional networks on graph, due to its irregularity and\ncomplexity geometric topologies (unordered vertices, unfixed number of adjacent\nedges/vertices). In this paper, we aim to give a comprehensive analysis of when\nwork matters by transforming different classical network structures to graph\nCNN, particularly in the basic graph recognition problem. Specifically, we\nfirstly review the general graph CNN methods, especially in its spectral\nfiltering operation on the irregular graph data. We then introduce the basic\nstructures of ResNet, Inception and DenseNet into graph CNN and construct these\nnetwork structures on graph, named as G_ResNet, G_Inception, G_DenseNet. In\nparticular, it seeks to help graph CNNs by shedding light on how these\nclassical network structures work and providing guidelines for choosing\nappropriate graph network frameworks. Finally, we comprehensively evaluate the\nperformance of these different network structures on several public graph\ndatasets (including social networks and bioinformatic datasets), and\ndemonstrate how different network structures work on graph CNN in the graph\nrecognition task.","url_abs":"http://arxiv.org/abs/1807.02653v1","url_pdf":"http://arxiv.org/pdf/1807.02653v1.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":[],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-classification-on-collab","task":"Graph Classification","dataset":"COLLAB","model":"G_DenseNet","rank_in_archive_order":4,"of":39,"metrics":{"Accuracy":"83.16%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-enzymes","task":"Graph Classification","dataset":"ENZYMES","model":"G_Inception","rank_in_archive_order":17,"of":54,"metrics":{"Accuracy":"67.50%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-b","task":"Graph Classification","dataset":"IMDb-B","model":"G_ResNet","rank_in_archive_order":8,"of":51,"metrics":{"Accuracy":"79.90%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-imdb-m","task":"Graph Classification","dataset":"IMDb-M","model":"G_ResNet","rank_in_archive_order":6,"of":36,"metrics":{"Accuracy":"54.53%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-mutag","task":"Graph Classification","dataset":"MUTAG","model":"G_Inception","rank_in_archive_order":5,"of":74,"metrics":{"Accuracy":"95.00%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-nci109","task":"Graph Classification","dataset":"NCI109","model":"G_DenseNet","rank_in_archive_order":22,"of":38,"metrics":{"Accuracy":"80.66"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-ptc","task":"Graph Classification","dataset":"PTC","model":"G_DenseNet","rank_in_archive_order":7,"of":37,"metrics":{"Accuracy":"73.24%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"176d7dc8ea2e01db8680ab1b795522dd1cf4d5c1dccadb04e5020725ca82cd4d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}