GCNN
所属分类:图神经网络
开发工具:Python
文件大小:732KB
下载次数:0
上传日期:2021-05-21 16:54:07
上 传 者:
sh-1993
说明: 基于几何深度学习的GCNN模型在社交媒体虚假新闻检测中的Pytorch实现
(The Pytorch Implementation of GCNN model from paper Fake News Detection on Social Media using Geometric Deep Learning)
文件列表:
LICENSE (11357, 2021-05-22)
data (0, 2021-05-22)
data\PROTEINS (0, 2021-05-22)
data\PROTEINS\processed (0, 2021-05-22)
data\PROTEINS\processed\data.pt (2837541, 2021-05-22)
data\PROTEINS\processed\pre_filter.pt (431, 2021-05-22)
data\PROTEINS\processed\pre_transform.pt (431, 2021-05-22)
data\PROTEINS\raw (0, 2021-05-22)
data\PROTEINS\raw\PROTEINS_A.txt (2022990, 2021-05-22)
data\PROTEINS\raw\PROTEINS_graph_indicator.txt (169673, 2021-05-22)
data\PROTEINS\raw\PROTEINS_graph_labels.txt (2226, 2021-05-22)
data\PROTEINS\raw\PROTEINS_node_attributes.txt (478190, 2021-05-22)
data\PROTEINS\raw\PROTEINS_node_labels.txt (86942, 2021-05-22)
main.py (4825, 2021-05-22)
model.jpg (155252, 2021-05-22)
README for dataset PROTEINS
=== Usage ===
This folder contains the following comma separated text files
(replace DS by the name of the dataset):
n = total number of nodes
m = total number of edges
N = number of graphs
(1) DS_A.txt (m lines)
sparse (block diagonal) adjacency matrix for all graphs,
each line corresponds to (row, col) resp. (node_id, node_id)
(2) DS_graph_indicator.txt (n lines)
column vector of graph identifiers for all nodes of all graphs,
the value in the i-th line is the graph_id of the node with node_id i
(3) DS_graph_labels.txt (N lines)
class labels for all graphs in the dataset,
the value in the i-th line is the class label of the graph with graph_id i
(4) DS_node_labels.txt (n lines)
column vector of node labels,
the value in the i-th line corresponds to the node with node_id i
There are OPTIONAL files if the respective information is available:
(5) DS_edge_labels.txt (m lines; same size as DS_A_sparse.txt)
labels for the edges in DS_A_sparse.txt
(6) DS_edge_attributes.txt (m lines; same size as DS_A.txt)
attributes for the edges in DS_A.txt
(7) DS_node_attributes.txt (n lines)
matrix of node attributes,
the comma seperated values in the i-th line is the attribute vector of the node with node_id i
(8) DS_graph_attributes.txt (N lines)
regression values for all graphs in the dataset,
the value in the i-th line is the attribute of the graph with graph_id i
=== Previous Use of the Dataset ===
Feragen, A., Kasenburg, N., Petersen, J., de Bruijne, M., Borgwardt, K.M.: Scalable
kernels for graphs with continuous attributes. In: C.J.C. Burges, L. Bottou, Z. Ghahra-
mani, K.Q. Weinberger (eds.) NIPS, pp. 216-224 (2013)
Neumann, M., Garnett R., Bauckhage Ch., Kersting K.: Propagation Kernels: Efficient Graph
Kernels from Propagated Information. Under review at MLJ.
=== References ===
K. M. Borgwardt, C. S. Ong, S. Schoenauer, S. V. N. Vishwanathan, A. J. Smola, and H. P.
Kriegel. Protein function prediction via graph kernels. Bioinformatics, 21(Suppl 1):i47–i56,
Jun 2005.
P. D. Dobson and A. J. Doig. Distinguishing enzyme structures from non-enzymes without
alignments. J. Mol. Biol., 330(4):771–783, Jul 2003.
近期下载者:
相关文件:
收藏者: