文件列表:

LICENSE (1066, 2019-06-28)
args.py (166, 2019-06-28)
data (0, 2019-06-28)
data\ind.citeseer.allx (595021, 2019-06-28)
data\ind.citeseer.graph (61987, 2019-06-28)
data\ind.citeseer.test.index (5000, 2019-06-28)
data\ind.citeseer.tx (260321, 2019-06-28)
data\ind.citeseer.x (31087, 2019-06-28)
data\ind.cora.allx (257305, 2019-06-28)
data\ind.cora.graph (59847, 2019-06-28)
data\ind.cora.test.index (5000, 2019-06-28)
data\ind.cora.tx (148025, 2019-06-28)
data\ind.cora.x (22119, 2019-06-28)
data\ind.pubmed.allx (7578385, 2019-06-28)
data\ind.pubmed.graph (471808, 2019-06-28)
data\ind.pubmed.test.index (6000, 2019-06-28)
data\ind.pubmed.tx (405505, 2019-06-28)
data\ind.pubmed.x (23172, 2019-06-28)
input_data.py (1689, 2019-06-28)
model.py (2567, 2019-06-28)
preprocessing.py (4050, 2019-06-28)
train.py (4239, 2019-06-28)

# Variational Graph Auto-encoder in Pytorch This repository implements variational graph auto-encoder by Thomas Kipf. For details of the model, refer to his original [tensorflow implementation](https://github.com/tkipf/gae) and [his paper](https://arxiv.org/abs/1611.07308). # Requirements * Pytorch * python 3.x * networkx * scikit-learn * scipy # How to run * Specify your arguments in `args.py` : you can change dataset and other arguments there * run `python train.py` # Notes * The dataset is the same as what Kipf provided in his original implementation. Thus I used his preprocessing code as-is(maybe with minor modification). * Per-epoch training time is a bit slower then the original implementation.(0.2 sec/epoch --> 0.9 sec/epoch) * Train accuracy, validation(test) average precision, auroc are similar to those of the original. (over 90% for both AP and roc) * Dropout is not implemented now. * Feel free to report some inefficiencies in the code! (It's just initial version so may have much room for pytorch-adaptation)

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：