graphs-datasets/IMDB-BINARY
收藏资源简介:
IMDB-BINARY数据集是一个电影合作数据集,包含1000个演员/演员的自我网络,这些演员在IMDB的电影中扮演角色。在每个图中,节点代表演员,如果他们在同一部电影中出现,则他们之间有边。这些图源自动作和爱情两种电影类型。数据集主要用于图分类任务,特别是用于预测电影图是动作片还是爱情片的二元分类任务。
The IMDB-BINARY dataset is a movie collaboration dataset containing 1,000 ego-networks of actors and actresses who have appeared in films on IMDB. In each graph, nodes represent actors/actresses, and edges exist between two nodes if they co-starred in the same film. These graphs are sourced from two movie genres: action and romance. The dataset is primarily used for graph classification tasks, specifically the binary classification task of predicting whether a given movie graph belongs to the action or romance genre.
数据集概述
数据集名称
- IMDb-B (IMDB-BINARY)
数据集描述
- 摘要: IMDb-B数据集包含1,000个演员/女演员的自我网络,这些演员/女演员在IMDb中的电影中扮演角色。在每个图中,节点代表演员/女演员,如果他们出现在同一部电影中,则节点之间存在边。这些图来自动作和浪漫电影类型。
- 任务: 用于图分类,目的是预测电影图是动作还是浪漫电影,这是一个二分类任务。
- 评估指标: 使用准确性作为评分,采用10折交叉验证。
数据集结构
- 数据属性:
- 规模: 中等
- 图数量: 1000
- 平均节点数: 19.79
- 平均边数: 193.25
- 数据字段:
edge_index: 边索引,2 x #edges的列表,表示构成边的节点对y: 标签列表,1 x #labels,包含可用于预测的标签数量(此处为1,等于零或一)num_nodes: 图的节点数量
许可证信息
- 许可证: 未知
引用信息
@inproceedings{10.1145/2783258.2783417, author = {Yanardag, Pinar and Vishwanathan, S.V.N.}, title = {Deep Graph Kernels}, year = {2015}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/2783258.2783417}, booktitle = {Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, pages = {1365–1374}, numpages = {10}, keywords = {collaboration networks, bioinformatics, r-convolution kernels, graph kernels, structured data, deep learning, social networks, string kernels}, location = {Sydney, NSW, Australia}, series = {KDD 15} }
贡献者
- 贡献者: @clefourrier




