{"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/deep-convolutional-networks-on-graph","title":"Deep Convolutional Networks on Graph-Structured Data","arxiv_id":"1506.05163","date":"2015-06-16","proceeding":null,"authors":["Mikael Henaff","Joan Bruna","Yann Lecun"],"abstract":"Deep Learning's recent successes have mostly relied on Convolutional\nNetworks, which exploit fundamental statistical properties of images, sounds\nand video data: the local stationarity and multi-scale compositional structure,\nthat allows expressing long range interactions in terms of shorter, localized\ninteractions. However, there exist other important examples, such as text\ndocuments or bioinformatic data, that may lack some or all of these strong\nstatistical regularities.\n  In this paper we consider the general question of how to construct deep\narchitectures with small learning complexity on general non-Euclidean domains,\nwhich are typically unknown and need to be estimated from the data. In\nparticular, we develop an extension of Spectral Networks which incorporates a\nGraph Estimation procedure, that we test on large-scale classification\nproblems, matching or improving over Dropout Networks with far less parameters\nto estimate.","url_abs":"http://arxiv.org/abs/1506.05163v1","url_pdf":"http://arxiv.org/pdf/1506.05163v1.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":"deep-convolutional-networks-on-graph","repo_url":"https://github.com/Fuhongshuai/FUHS_GraphCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-convolutional-networks-on-graph","repo_url":"https://github.com/mdeff/cnn_graph","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-convolutional-networks-on-graph","repo_url":"https://github.com/zdcuob/cnn_graph-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.05163","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.05163"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mdeff/cnn_graph","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zdcuob/cnn_graph-","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Fuhongshuai/FUHS_GraphCNN","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1a0800a587098915","entry":"bspline_basis","repo":"zdcuob/cnn_graph-","repo_kind":"listed","path":"lib/models.py","file_url":"https://github.com/zdcuob/cnn_graph-/blob/HEAD/lib/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a0800a587098915"}},{"code_sha256_prefix":"fc1a4e21a94ce757","entry":"coarsen","repo":"zdcuob/cnn_graph-","repo_kind":"listed","path":"lib/coarsening.py","file_url":"https://github.com/zdcuob/cnn_graph-/blob/HEAD/lib/coarsening.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc1a4e21a94ce757"}},{"code_sha256_prefix":"01d4be9c45f5d3f2","entry":"distance_scipy_spatial","repo":"zdcuob/cnn_graph-","repo_kind":"listed","path":"lib/graph.py","file_url":"https://github.com/zdcuob/cnn_graph-/blob/HEAD/lib/graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01d4be9c45f5d3f2"}},{"code_sha256_prefix":"ebb82619c724ec7f","entry":"distance_sklearn_metrics","repo":"zdcuob/cnn_graph-","repo_kind":"listed","path":"lib/graph.py","file_url":"https://github.com/zdcuob/cnn_graph-/blob/HEAD/lib/graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ebb82619c724ec7f"}},{"code_sha256_prefix":"00b211ed8d329331","entry":"grid","repo":"zdcuob/cnn_graph-","repo_kind":"listed","path":"lib/graph.py","file_url":"https://github.com/zdcuob/cnn_graph-/blob/HEAD/lib/graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00b211ed8d329331"}},{"code_sha256_prefix":"5719e891497f15c2","entry":"metis","repo":"zdcuob/cnn_graph-","repo_kind":"listed","path":"lib/coarsening.py","file_url":"https://github.com/zdcuob/cnn_graph-/blob/HEAD/lib/coarsening.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5719e891497f15c2"}},{"code_sha256_prefix":"3db137c20dc3bdc1","entry":"metis_one_level","repo":"zdcuob/cnn_graph-","repo_kind":"listed","path":"lib/coarsening.py","file_url":"https://github.com/zdcuob/cnn_graph-/blob/HEAD/lib/coarsening.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3db137c20dc3bdc1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}