{"id":19296590,"url":"https://github.com/alexduvalinho/geometric-gnns","last_synced_at":"2026-02-01T02:02:45.920Z","repository":{"id":191817341,"uuid":"685454992","full_name":"AlexDuvalinho/geometric-gnns","owner":"AlexDuvalinho","description":"List of Geometric GNNs for 3D atomic systems","archived":false,"fork":false,"pushed_at":"2024-02-29T16:25:54.000Z","size":5103,"stargazers_count":109,"open_issues_count":0,"forks_count":6,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-16T22:42:07.324Z","etag":null,"topics":["ai4science","coding-resource","datasets","equivariant-networks","geometric-deep-learning","graph-neural-networks","molecules-and-materials"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AlexDuvalinho.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-31T09:10:32.000Z","updated_at":"2025-06-15T09:51:11.000Z","dependencies_parsed_at":"2024-11-09T22:48:26.322Z","dependency_job_id":"6dd706a6-ab56-44f3-9909-7de8c8f50d87","html_url":"https://github.com/AlexDuvalinho/geometric-gnns","commit_stats":null,"previous_names":["alexduvalinho/geometric-gnns"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AlexDuvalinho/geometric-gnns","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexDuvalinho%2Fgeometric-gnns","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexDuvalinho%2Fgeometric-gnns/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexDuvalinho%2Fgeometric-gnns/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexDuvalinho%2Fgeometric-gnns/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AlexDuvalinho","download_url":"https://codeload.github.com/AlexDuvalinho/geometric-gnns/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlexDuvalinho%2Fgeometric-gnns/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28964428,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-01T01:25:30.373Z","status":"online","status_checked_at":"2026-02-01T02:00:08.102Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai4science","coding-resource","datasets","equivariant-networks","geometric-deep-learning","graph-neural-networks","molecules-and-materials"],"created_at":"2024-11-09T22:48:18.187Z","updated_at":"2026-02-01T02:02:45.900Z","avatar_url":"https://github.com/AlexDuvalinho.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# Geometric-GNNs\n\nIn this readme, you will find a list of Geometric GNNs for 3D atomic systems, (hopefully) maintained up-to-date by the community. \nFor each method, we include its associated Geometric GNN family, tensor type and body order information. Check out the accompanying paper for more details: [A Hitchhiker's Guide to Geometric GNNs for 3D atomic systems ](https://arxiv.org/abs/2312.07511).\n\nIn the rest of the repository, you will find a [list of datasets for Geometric GNNs](https://github.com/AlexDuvalinho/geometric-gnns/blob/main/datasets.md) as well as a [list of useful software libraries](https://github.com/AlexDuvalinho/geometric-gnns/blob/main/software.md). \n\n\n\u003cfigure\u003e\u003ccenter\u003e\u003cimg src=\"image/timeline.png\" width=\"100%\"\u003e\u003c/center\u003e\u003c/figure\u003e\n\n\n| Method | Year | Family | Tensor type | Body order | Source |\n| :---  | ---: | ---:   | ---:         | ---: | ---: |\n|SchNet| 2017| invariant\t| scalar\t| 2 | [paper](https://arxiv.org/pdf/1706.08566.pdf) |\n|CGCNN|\t2017|\tinvariant|\tscalar|\t2| [paper](https://arxiv.org/abs/1710.10324)|\n|TFN|\t2018|\tequivariant|\tspherical|\t2|  [paper](https://arxiv.org/pdf/1802.08219.pdf)|\n|PhysNet|\t2019|\tinvariant|\tscalar|\t2| [paper](https://arxiv.org/pdf/1902.08408.pdf) |\n|DimeNet|\t2019|\tinvariant|\tscalar|\t3| [paper](https://arxiv.org/pdf/2003.03123.pdf)|\n|MEGnet|\t2019|\tinvariant||\t\t| [paper](https://arxiv.org/abs/1812.05055)|\n|Cormorant|\t2019|\tequivariant|\tspherical|\t2| [paper](https://arxiv.org/pdf/1906.04015.pdf)|\n|MXMNet|\t2020|\tinvariant|\tscalar|\t3| [paper](https://arxiv.org/pdf/2011.07457.pdf)|\n|DimeNet++|\t2020|\tinvariant|\tscalar|\t3| [paper](https://arxiv.org/abs/2011.14115)|\n|GVP-GNN|\t2020|\tequivariant|\tcartesian|\t3| [paper](https://arxiv.org/pdf/2009.01411.pdf)|\n|LieTransformer| 2020| equivariant |  | | [paper](https://arxiv.org/abs/2012.10885)|\n|LieConv| 2020 | equivariant |\t|| [paper](https://arxiv.org/abs/2002.12880)|\n|SE3-Transformers|\t2020|\tequivariant| spherical|\t\t| [paper](https://arxiv.org/abs/2006.10503)|\n|SpinConv|\t2021|\tinvariant| spherical|| [paper](https://arxiv.org/abs/2106.09575)|\n|ForceNet|\t2021|\tunconstrained| scalar|\t2| [paper](https://arxiv.org/abs/2103.01436)|\n|Graphormer|\t2021|\tinvariant| scalar |\t| [paper](https://arxiv.org/abs/2106.05234)|\n|SphereNet|\t2021|\tinvariant|\tscalar|\t4| [paper](https://arxiv.org/abs/2102.05013)|\n|GemNet|\t2021|\tinvariant|\tscalar|\t4| [paper](https://arxiv.org/abs/2106.08903)|\n|ChIRo|\t2021|\tinvariant|\tscalar|\t| [paper](https://arxiv.org/abs/2110.04383)|\n|SEGNN|\t2021|\tequivariant|\tspherical|\t2| [paper](https://arxiv.org/abs/2110.02905)|\n|EGNN|\t2021|\tequivariant|\tcartesian|\t2| [paper](https://arxiv.org/pdf/2102.09844.pdf)|\n|PaiNN|\t2021|\tequivariant|\tcartesian|\t3| [paper](https://arxiv.org/abs/2102.03150)|\n|NeuquIP|\t2021|\tequivariant|\tspherical|\t2| [paper](https://arxiv.org/abs/2101.03164)|\n|SpookyNet|\t2021|\tinvariant| scalar |\t 2| [paper](https://arxiv.org/abs/2105.00304)|\n|EQGAT|\t2022|\tequivariant|\tcartesian|\t2| [paper](https://arxiv.org/pdf/2202.09891.pdf)|\n|Torch-MDNet|\t2022|\tequivariant|\tcartesian|\t2| [paper](https://arxiv.org/abs/2202.02541)|\n|GNS|\t2022|\tunconstrained |\tscalar|\t| [paper](https://arxiv.org/abs/2002.09405)|\n|GNN-LF|\t2022|\tinvariant|\tscalar|| [paper](https://arxiv.org/abs/2208.00716)|\n|GCPNet|\t2022|\tequivariant| cartesian| |[paper](https://arxiv.org/abs/2211.02504) |\n|ComENet|\t2022|\tinvariant|\tscalar|4| [paper](https://arxiv.org/pdf/2206.08515.pdf)|\n|So3krates|\t2022|\tequivariant|\tcartesian|\t2| [paper](https://arxiv.org/abs/2205.14276)|\n|Equiformer|\t2022|\tequivariant|\tspherical|\t2| [paper](https://arxiv.org/abs/2206.11990)|\n|MACE|\t2022|\tequivariant|\tspherical |Many| [paper](https://arxiv.org/abs/2206.07697)|\n|GemNet-OC|\t2022|\tinvariant|\tscalar|\t4| [paper](https://arxiv.org/abs/2204.02782)|\n|ClofNet|\t2022|\tequivariant|\tcartesian|\t| [paper](https://arxiv.org/pdf/2110.14811.pdf)|\n|Allegro| 2022| equivariant |  spherical | Many| [paper](https://arxiv.org/abs/2204.05249)|\n|LEFTNet|\t2023 | equivariant|\tcartesian || [paper](https://arxiv.org/abs/2304.04757)|\n|ViSNet-LSRM|\t2023|\tequivariant |\tcartesian|\t| [paper](https://arxiv.org/pdf/2304.13542.pdf)|\n|SCN|\t2023|\tunconstrained|\tspherical\t| | [paper](https://arxiv.org/abs/2206.14331)|\n|TensorNet|\t2023| equivariant |\tcartesian || [paper](https://arxiv.org/abs/2306.06482)|\n|eSCN|\t2023|\tequivariant|\tspherical|\t2| [paper](https://arxiv.org/abs/2302.03655)|\n|FAENet|\t2023|\tunconstrained | scalar |\tMany| [paper](https://arxiv.org/abs/2305.05577)|\n\n\u003cfigure\u003e\u003ccenter\u003e\u003cimg src=\"image/axes.png\" width=\"75%\"\u003e\u003c/center\u003e\u003c/figure\u003e\n\n\n## Contact\n\nAuthors: Alexandre Duval (alexandre.duval@mila.quebec), Simon V. Mathis (simon.mathis@cl.cam.ac.uk), Chaitanya K. Joshi (chaitanya.joshi@cl.cam.ac.uk), Victor Schmidt (schmidtv@mila.quebec). \n\nWe welcome your questions and feedback via email or GitHub Issues.\n\n## Citation\n\n```\n@article{duval2023hitchhikers,\n  title   = {A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems},\n  author  = {Alexandre Duval and Simon V. Mathis and Chaitanya K. Joshi and Victor Schmidt and Santiago Miret and Fragkiskos D. Malliaros and Taco Cohen and Pietro Lio and Yoshua Bengio and Michael Bronstein},\n  year    = {2023},\n  journal = {arXiv preprint arXiv: 2312.07511}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexduvalinho%2Fgeometric-gnns","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falexduvalinho%2Fgeometric-gnns","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexduvalinho%2Fgeometric-gnns/lists"}