{"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/geometric-deep-learning-on-graphs-and","title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","arxiv_id":"1611.08402","date":"2016-11-25","proceeding":"CVPR 2017 7","authors":["Federico Monti","Davide Boscaini","Jonathan Masci","Emanuele Rodolà","Jan Svoboda","Michael M. Bronstein"],"abstract":"Deep learning has achieved a remarkable performance breakthrough in several\nfields, most notably in speech recognition, natural language processing, and\ncomputer vision. In particular, convolutional neural network (CNN)\narchitectures currently produce state-of-the-art performance on a variety of\nimage analysis tasks such as object detection and recognition. Most of deep\nlearning research has so far focused on dealing with 1D, 2D, or 3D\nEuclidean-structured data such as acoustic signals, images, or videos.\nRecently, there has been an increasing interest in geometric deep learning,\nattempting to generalize deep learning methods to non-Euclidean structured data\nsuch as graphs and manifolds, with a variety of applications from the domains\nof network analysis, computational social science, or computer graphics. In\nthis paper, we propose a unified framework allowing to generalize CNN\narchitectures to non-Euclidean domains (graphs and manifolds) and learn local,\nstationary, and compositional task-specific features. We show that various\nnon-Euclidean CNN methods previously proposed in the literature can be\nconsidered as particular instances of our framework. We test the proposed\nmethod on standard tasks from the realms of image-, graph- and 3D shape\nanalysis and show that it consistently outperforms previous approaches.","url_abs":"http://arxiv.org/abs/1611.08402v3","url_pdf":"http://arxiv.org/pdf/1611.08402v3.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":"geometric-deep-learning-on-graphs-and","repo_url":"https://github.com/HeapHop30/graph-attention-nets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"geometric-deep-learning-on-graphs-and","repo_url":"https://github.com/theswgong/MoNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"geometric-deep-learning-on-graphs-and","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/monet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"geometric-deep-learning-on-graphs-and","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/monet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-regression","task_name":"Graph Regression"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"superpixel-image-classification","task_name":"Superpixel Image Classification"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"monet","method_name":"MoNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"monet","name":"MoNet","full_name":"Mixture model network"}],"results":[{"leaderboard":"/sota/document-classification-on-cora","task":"Document Classification","dataset":"Cora","model":"MoNet","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"81.7%"},"uses_additional_data":false},{"leaderboard":"/sota/graph-classification-on-cifar10-100k","task":"Graph Classification","dataset":"CIFAR10 100k","model":"MoNet","rank_in_archive_order":19,"of":20,"metrics":{"Accuracy (%)":"53.42"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-100k","task":"Graph Regression","dataset":"ZINC 100k","model":"MoNet","rank_in_archive_order":7,"of":8,"metrics":{"MAE":"0.407"},"uses_additional_data":false},{"leaderboard":"/sota/graph-regression-on-zinc-500k","task":"Graph Regression","dataset":"ZINC-500k","model":"MoNet","rank_in_archive_order":31,"of":36,"metrics":{"MAE":"0.292"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pattern-100k","task":"Node Classification","dataset":"PATTERN 100k","model":"MoNet","rank_in_archive_order":6,"of":9,"metrics":{"Accuracy (%)":"85.482"},"uses_additional_data":false},{"leaderboard":"/sota/superpixel-image-classification-on-75","task":"Superpixel Image Classification","dataset":"75 Superpixel MNIST","model":"Monet","rank_in_archive_order":6,"of":6,"metrics":{"Classification Error":"8.89"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.08402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08402"}},"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/HeapHop30/graph-attention-nets","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/monet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/theswgong/MoNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/monet","reach":null}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"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":"4ac4a1493301e71a","entry":"evaluate","repo":"theswgong/MoNet","repo_kind":"listed","path":"graph/train_eval.py","file_url":"https://github.com/theswgong/MoNet/blob/HEAD/graph/train_eval.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":"4ac4a1493301e71a"}},{"code_sha256_prefix":"a70eb3051c972797","entry":"test","repo":"theswgong/MoNet","repo_kind":"listed","path":"image/train_eval.py","file_url":"https://github.com/theswgong/MoNet/blob/HEAD/image/train_eval.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":"a70eb3051c972797"}},{"code_sha256_prefix":"fa42f81c7ba963a8","entry":"test","repo":"theswgong/MoNet","repo_kind":"listed","path":"manifolds/train_eval.py","file_url":"https://github.com/theswgong/MoNet/blob/HEAD/manifolds/train_eval.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":"fa42f81c7ba963a8"}},{"code_sha256_prefix":"668c5f7e61273fc2","entry":"train","repo":"theswgong/MoNet","repo_kind":"listed","path":"image/train_eval.py","file_url":"https://github.com/theswgong/MoNet/blob/HEAD/image/train_eval.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":"668c5f7e61273fc2"}},{"code_sha256_prefix":"b38fca4c55c291bc","entry":"train","repo":"theswgong/MoNet","repo_kind":"listed","path":"manifolds/train_eval.py","file_url":"https://github.com/theswgong/MoNet/blob/HEAD/manifolds/train_eval.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":"b38fca4c55c291bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}