![]() Graphs can also be indexed by strings or pairs of vertex indices or vertex names. Graph also overrides some functions from GraphBase to provide a more convenient interface e.g., layout functions return a Layout instance from Graph instead of a list of coordinate pairs. This extension was needed to make Graph serializable through the pickle module. An example is the attribute handling in the constructor: the constructor of Graph accepts three dictionaries corresponding to the graph, vertex and edge attributes while the constructor of GraphBase does not. Graph provides many functions that GraphBase does not, mostly because these functions are not speed critical and they were easier to implement in Python than in pure C. Nohup python run_pubmed.py -dataset tencent > running_asgcn.This class is built on top of GraphBase, so the order of the methods in the generated API documentation is a little bit obscure: inherited methods come after the ones implemented directly in the subclass. Nohup sh run_gae.sh pubmed > log_run_gae_pubmed.txt 2>&1 & Nohup sh run_gae.sh citeseer > log_run_gae_citeseer.txt 2>&1 & Nohup sh run_gae.sh cora > log_run_gae_cora.txt 2>&1 & Nohup sh run_gae.sh tencent > log_run_gae_tencent.txt 2>&1 & Nohup sh run_graphsage.sh pubmed > log_run_graphsage_pubmed.txt 2>&1 & Nohup sh run_graphsage.sh citeseer > log_run_graphsage_citeseer.txt 2>&1 & ![]() Nohup sh run_graphsage.sh cora > log_run_graphsage_cora.txt 2>&1 & Nohup sh run_graphsage.sh tencent > log_run_graphsage_tencent.txt 2>&1 & Nohup sh run_gcn.sh pubmed > log_run_gcn_pubmed.txt 2>&1 & Nohup sh run_gcn.sh citeseer > log_run_gcn_citeseer.txt 2>&1 & Nohup sh run_gcn.sh cora > log_run_gcn_cora.txt 2>&1 & Nohup sh run_gcn.sh tencent > log_run_gcn_tencent.txt 2>&1 & Nohup sh run_node2vec.sh pubmed > log_run_node2vec_pubmed.txt 2>&1 & Nohup sh run_node2vec.sh citeseer > log_run_node2vec_citeseer.txt 2>&1 & Nohup sh run_node2vec.sh cora > log_run_node2vec_cora.txt 2>&1 & Nohup sh run_node2vec.sh tencent > log_run_node2vec_tencent.txt 2>&1 & Nohup sh run_abcgraph_mlp.sh pubmed > log_run_abcgraph_mlp_pubmed.txt 2>&1 & Nohup sh run_abcgraph_mlp.sh citeseer > log_run_abcgraph_mlp_citeseer.txt 2>&1 & Nohup sh run_abcgraph_mlp.sh cora > log_run_abcgraph_mlp_cora.txt 2>&1 & Nohup sh run_abcgraph_mlp.sh tencent > log_run_abcgraph_mlp_tencent.txt 2>&1 & Nohup sh run_abcgraph_adv.sh pubmed > log_run_abcgraph_adv_pubmed.txt 2>&1 & Nohup sh run_abcgraph_adv.sh citeseer > log_run_abcgraph_adv_citeseer.txt 2>&1 & Nohup sh run_abcgraph_adv.sh cora > log_run_abcgraph_adv_cora.txt 2>&1 & Nohup sh run_abcgraph_adv.sh tencent > log_run_abcgraph_adv_tencent.txt 2>&1 & From the other datasets, we can see that our model's performance is better than the GAE model. To apply GAE to the large-scale graph data is another research topic, so we don't report the result in the "Tencent" dataset. Bipartite graph code#N/A (*): For the GAE model, the code of the original GAE paper can not simply applied to the large-scale bipartite graph due to the memory constrain. ![]() Only Linux (*): For the Node2Vec model, its binary file is only ELF 64-bit LSB executable, x86-64, for GNU/Linux. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |