{"id":13676385,"url":"https://github.com/giannisnik/segk","last_synced_at":"2025-04-29T07:32:11.551Z","repository":{"id":74422344,"uuid":"224216398","full_name":"giannisnik/segk","owner":"giannisnik","description":"Learning Structural Node Representations using Graph Kernels","archived":false,"fork":false,"pushed_at":"2024-02-02T11:15:51.000Z","size":868,"stargazers_count":6,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-11-11T18:41:16.057Z","etag":null,"topics":["graph-embeddings","graph-mining","node-embedding","representation-learning"],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/giannisnik.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2019-11-26T14:50:29.000Z","updated_at":"2024-04-25T01:29:44.000Z","dependencies_parsed_at":"2024-11-11T18:34:14.840Z","dependency_job_id":"69ac8d40-52fd-419c-af39-d7375390bdf3","html_url":"https://github.com/giannisnik/segk","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/giannisnik%2Fsegk","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/giannisnik%2Fsegk/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/giannisnik%2Fsegk/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/giannisnik%2Fsegk/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/giannisnik","download_url":"https://codeload.github.com/giannisnik/segk/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251455900,"owners_count":21592257,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["graph-embeddings","graph-mining","node-embedding","representation-learning"],"created_at":"2024-08-02T13:00:24.758Z","updated_at":"2025-04-29T07:32:10.590Z","avatar_url":"https://github.com/giannisnik.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"## Learning Structural Node Representations using Graph Kernels\nCode for the paper [Learning Structural Node Representations using Graph Kernels](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=8869809).\n\n### Requirements\nCode is written in Python 3.6 and requires:\n* grakel 0.1b7\n* scikit-learn 0.21\n\n### Basic Usage\nTo run *SEGK* on Barbell graph, execute the following command from the project home directory:\u003cbr/\u003e\n``python segk.py --path-to-edgelist datasets/barbell.edgelist --path-to-output-file embeddings/barbell.txt``\n\n#### Hyperparameters\nThe following three hyperparameters can be specified:\n* radius: the maximum radius of the neighborhood subgraphs\n* dim: the dimensionality of the generated embeddings\n* kernel: the employed graph kernel (either the shortest path kernel or the weisfeiler lehman kernel)\n\n#### Input\nThe supported input format is an edgelist where the endpoints are separated by the space character:\n\n    node1_id node2_id\n        \n#### Output\nThe output file contains *n* lines (where *n* is the number of nodes of the graph) as follows:\n\n    node_id dim1 dim2 ... dimd\nwhere dim1, ... , dimd is the *d*-dimensional representation learned by *SEGK*.\n\n### Experiments\nIn the project home directory, there are four jupyter notebooks that reproduce the experiments presented in the paper.\n\n### Cite\nPlease cite our paper if you use this code:\n```\n@article{nikolentzos2019learning,\n  title={Learning Structural Node Representations using Graph Kernels},\n  author={Nikolentzos, Giannis and Vazirgiannis, Michalis},\n  journal={IEEE Transactions on Knowledge and Data Engineering},\n  year={2019}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgiannisnik%2Fsegk","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgiannisnik%2Fsegk","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgiannisnik%2Fsegk/lists"}