{"task":"Graph Classification","dataset":"FRANKENSTEIN","metric_names":["Accuracy"],"rows":[{"id":95378,"task":"Graph Classification","parent_task":null,"dataset":"FRANKENSTEIN","model_name":"GWL_WL","metrics":{"Accuracy":"78.9"},"paper_url":"https://dl.acm.org/citation.cfm?id=2832747.2832773","paper_title":"Graph Invariant Kernels","paper_date":"2015-07-25","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95379,"task":"Graph Classification","parent_task":null,"dataset":"FRANKENSTEIN","model_name":"MEWISPool","metrics":{"Accuracy":"73.46"},"paper_url":"https://arxiv.org/abs/2107.01410v1","paper_title":"Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks","paper_date":"2021-07-03","code_links":[{"title":"mewispool/mewispool","url":"https://github.com/mewispool/mewispool"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95380,"task":"Graph Classification","parent_task":null,"dataset":"FRANKENSTEIN","model_name":"MAGPool","metrics":{"Accuracy":"67.21"},"paper_url":"https://ieeexplore.ieee.org/document/10454077","paper_title":"Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective","paper_date":"2024-03-04","code_links":[{"title":"p-haddadian/MAGPool","url":"https://github.com/p-haddadian/MAGPool"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95381,"task":"Graph Classification","parent_task":null,"dataset":"FRANKENSTEIN","model_name":"ASAP","metrics":{"Accuracy":"66.26"},"paper_url":"https://arxiv.org/abs/1911.07979v3","paper_title":"ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations","paper_date":"2019-11-18","code_links":[{"title":"malllabiisc/ASAP","url":"https://github.com/malllabiisc/ASAP"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95382,"task":"Graph Classification","parent_task":null,"dataset":"FRANKENSTEIN","model_name":"SAGPool_g","metrics":{"Accuracy":"62.57"},"paper_url":"https://arxiv.org/abs/1904.08082v4","paper_title":"Self-Attention Graph Pooling","paper_date":"2019-04-17","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sagpool"},{"title":"inyeoplee77/SAGPool","url":"https://github.com/inyeoplee77/SAGPool"},{"title":"walidgeuttala/Synthetic-Benchmark-for-Graph-Classification","url":"https://github.com/walidgeuttala/Synthetic-Benchmark-for-Graph-Classification"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95383,"task":"Graph Classification","parent_task":null,"dataset":"FRANKENSTEIN","model_name":"SAGPool_h","metrics":{"Accuracy":"61.73"},"paper_url":"https://arxiv.org/abs/1904.08082v4","paper_title":"Self-Attention Graph Pooling","paper_date":"2019-04-17","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sagpool"},{"title":"inyeoplee77/SAGPool","url":"https://github.com/inyeoplee77/SAGPool"},{"title":"walidgeuttala/Synthetic-Benchmark-for-Graph-Classification","url":"https://github.com/walidgeuttala/Synthetic-Benchmark-for-Graph-Classification"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122147,"task":"Graph Classification","parent_task":"Classification","dataset":"FRANKENSTEIN","model_name":"GWL_WL","metrics":{"Accuracy":"78.9"},"paper_url":"https://dl.acm.org/citation.cfm?id=2832747.2832773","paper_title":"Graph Invariant Kernels","paper_date":"2015-07-25","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122148,"task":"Graph Classification","parent_task":"Classification","dataset":"FRANKENSTEIN","model_name":"MEWISPool","metrics":{"Accuracy":"73.46"},"paper_url":"https://arxiv.org/abs/2107.01410v1","paper_title":"Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks","paper_date":"2021-07-03","code_links":[{"title":"mewispool/mewispool","url":"https://github.com/mewispool/mewispool"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122149,"task":"Graph Classification","parent_task":"Classification","dataset":"FRANKENSTEIN","model_name":"MAGPool","metrics":{"Accuracy":"67.21"},"paper_url":"https://ieeexplore.ieee.org/document/10454077","paper_title":"Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective","paper_date":"2024-03-04","code_links":[{"title":"p-haddadian/MAGPool","url":"https://github.com/p-haddadian/MAGPool"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122150,"task":"Graph Classification","parent_task":"Classification","dataset":"FRANKENSTEIN","model_name":"ASAP","metrics":{"Accuracy":"66.26"},"paper_url":"https://arxiv.org/abs/1911.07979v3","paper_title":"ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations","paper_date":"2019-11-18","code_links":[{"title":"malllabiisc/ASAP","url":"https://github.com/malllabiisc/ASAP"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122151,"task":"Graph Classification","parent_task":"Classification","dataset":"FRANKENSTEIN","model_name":"SAGPool_g","metrics":{"Accuracy":"62.57"},"paper_url":"https://arxiv.org/abs/1904.08082v4","paper_title":"Self-Attention Graph Pooling","paper_date":"2019-04-17","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sagpool"},{"title":"inyeoplee77/SAGPool","url":"https://github.com/inyeoplee77/SAGPool"},{"title":"walidgeuttala/Synthetic-Benchmark-for-Graph-Classification","url":"https://github.com/walidgeuttala/Synthetic-Benchmark-for-Graph-Classification"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122152,"task":"Graph Classification","parent_task":"Classification","dataset":"FRANKENSTEIN","model_name":"SAGPool_h","metrics":{"Accuracy":"61.73"},"paper_url":"https://arxiv.org/abs/1904.08082v4","paper_title":"Self-Attention Graph Pooling","paper_date":"2019-04-17","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sagpool"},{"title":"inyeoplee77/SAGPool","url":"https://github.com/inyeoplee77/SAGPool"},{"title":"walidgeuttala/Synthetic-Benchmark-for-Graph-Classification","url":"https://github.com/walidgeuttala/Synthetic-Benchmark-for-Graph-Classification"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]}]}