-
-
测试cluster/cluster/Word2vecExample.scala，使用的数据是基于ogbn-100M的随机游走，该数据集大约有1.1亿个节点；
游走的参数是：epoch=1, step=10，即每个节点随机游走一次，每次长度是10。
使用master分支的代码，测试spark-on-angel下的cluster/cluster/Word2vecExample.scala，…
-
Originally done so following the node2vec source code. It makes sense to specify these parameters during the embedding function call, so that when embedding with different settings of ``p`` and ``q``,…
-
It is not mentioned, but I am wondering this repository is the implementation of this paper: http://www.kdd.org/kdd2016/subtopic/view/node2vec-scalable-feature-learning-for-networks
Is that right?
-
I used the hyperparameters provided, but the performance is actually bad. Take DBLP and twitter as examples, each of the results is about 20% below your result in the paper. Here is the command lines …
-
Hi,
Can I update node embeddings given and already trained model? I want to fit a model but then I want to update the network periodically and update the node embedding and not start from zero.
-
Hi,
How can I use this work to embed the graph with weight (such as the distance between tow nodes), could you please give some suggestions? Thanks in advance.
-
Hi,
I downloaded the whole projected and compiled the spark_node2vec project with mvn, without changing the pmo.xml file.
The build succeeded and target directory was created, but I got MethodN…
-
Hi!
I want to ask You about seed parameters for most node embeddings.
In the documentation, You have info that you put seed=42 as a default, but when You run, for example, Node2Vec twice, you get…
-
您好，咨询一下，
如果不考虑融合feature的embedding，只训练node的话，是不是encoders.py就没用了呀？
比如Node2Vec和LINE，不考虑特征的话是不是直接用layer.Embedding(inputs)就行了？