GATNE
GATNE copied to clipboard
Source code and dataset for KDD 2019 paper "Representation Learning for Attributed Multiplex Heterogeneous Network"
是在生成train.txt文件的时候前面的node1和node2就是单向关系呢? 还是我需要重新定义一个边类型呢? 是否需要大改代码呢?
您好! test与valid中某一类别的non-edge是否需要仅在相同类别中抽样,例如test中类别1边对应的点集为[1,2,3...1024],那生成non-edge时是否仅能在该点集中采样,或是可以全局采样?
Hi, Thanks a lot for sharing the code ! I am curious if GATNE can works a dataset containing 80 edges types, and some edges types are very rare (only...
Generating neighbors for layer 0 0%| | 192/2136051 [00:00
请问如何获取训练好的graph embedding呢?
Hi, Could you provide information on number of features for Alibaba/Alibaba-S dataset?
Hello, I want to ask if my data size is around 3 million, how can I use the distributed version of this algorithm to split the data and make the...