{"id":13481081,"url":"https://github.com/CheriseZhu/GSSNN","last_synced_at":"2025-03-27T11:31:46.311Z","repository":{"id":201899547,"uuid":"221692956","full_name":"CheriseZhu/GSSNN","owner":"CheriseZhu","description":"The implementation of our AAAI 2020 paper \"GSSNN: Graph Smoothing Splines Neural Network\".","archived":false,"fork":false,"pushed_at":"2020-07-30T12:32:45.000Z","size":1813,"stargazers_count":20,"open_issues_count":0,"forks_count":7,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-10-30T14:43:30.667Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/CheriseZhu.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}},"created_at":"2019-11-14T12:30:17.000Z","updated_at":"2021-08-23T15:27:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"426263e1-370e-4a06-881e-48fd426e693f","html_url":"https://github.com/CheriseZhu/GSSNN","commit_stats":null,"previous_names":["cherisezhu/gssnn"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CheriseZhu%2FGSSNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CheriseZhu%2FGSSNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CheriseZhu%2FGSSNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CheriseZhu%2FGSSNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CheriseZhu","download_url":"https://codeload.github.com/CheriseZhu/GSSNN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245836214,"owners_count":20680335,"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":[],"created_at":"2024-07-31T17:00:48.501Z","updated_at":"2025-03-27T11:31:45.922Z","avatar_url":"https://github.com/CheriseZhu.png","language":"Python","funding_links":[],"categories":["Deep Learning"],"sub_categories":[],"readme":"# GSSNN\nThe implementation of our AAAI 2020 paper \"[GSSNN: Graph Smoothing Splines Neural Network](https://www.researchgate.net/publication/337548602_GSSNN_Graph_Smoothing_Splines_Neural_Networks)\". \n\n# Requirements\npython == 3.6.2\u003cbr\u003e\ntorch == 1.1.0\u003cbr\u003e\nnumpy == 1.16.4\u003cbr\u003e\nscipy == 1.2.0\u003cbr\u003e\nnetworkx == 2.2\u003cbr\u003e\ntorch_scatter == 1.3.0\u003cbr\u003e\ntorch_geometric == 1.3.0\n\n# How to use\n  ### Dataset\n  The data folder includes our propocessed data for training and testing. \u003cbr\u003e\n  The orginal datasets can be founded from [here](https://ls11-www.cs.tu-dortmund.de/people/morris/graphkerneldatasets).\n\n  ### Model\n  The model folder includes our proposed model \"GSSNN\".\u003cbr\u003e\n  The model/utils folder includes graph utils and Scaled Smoothing Splines module used in model.\u003cbr\u003e\n  The model/process_data file processes data and computes the graph centrality.\u003cbr\u003e\n  The torch_geometeric/nn/pool folder includes the designed NodeImportance layer used in model.\u003cbr\u003e\n  The torch_geometeric/nn/conv folder includes the convolutional layers used in model provides by [torch_geometeric](https://github.com/rusty1s/pytorch_geometric) library.\u003cbr\u003e\n  \n  ### Prameters Setting\n  dim: the hidden dimension of node feature\u003cbr\u003e\n  conv_layer: the number of convolutional layer\u003cbr\u003e\n  ss_layer: the number of smoothing splines layer\u003cbr\u003e\n  Mi: the number of knot used in smoothing splines layer i\u003cbr\u003e\n  epsilon: used in smoothing splines to guarantee the denominator non-zero\u003cbr\u003e\n  add_knot: whether to consider the important nodes features as residual connection to the graph-level representation\u003cbr\u003e\n  \n  ### Training/Testing\n  ```\n  cd model\n  python process_data.py --dataset MUTAG\n  python GSSNN.py --dataset MUTAG --batch_size 128 --lr 0.01 --weight_decay 5e-4 --dim 32 --conv_layer 3 --ss_layer 2 --M1 5 --M2 5 --epsilon 1e-6 --add_knot True --epoch 100\n  python GSSNN_10_folds.py --dataset MUTAG --batch_size 128 --lr 0.01 --weight_decay 5e-4 --dim 32 --conv_layer 3 --ss_layer 2 --M1 5 --M2 5 --epsilon 1e-6 --add_knot True --epoch 100\n  ```\n  \n  \n# Citation\n```\n@inproceedings{zhu2020GSSNN\nauthor={Shichao Zhu and Lewei Zhou and Shirui Pan and Chuan Zhou and Guiying Yan and Bin Wang},\ntitle={GSSNN: Graph Smoothing Splines Neural Network},\njournal={Proceedings of the 34th AAAI Conference on Artificial Intelligence},\nyear={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCheriseZhu%2FGSSNN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCheriseZhu%2FGSSNN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCheriseZhu%2FGSSNN/lists"}