Comments (11)
from euler.
非常抱歉问一个可能比较低级的问题:我发现Python代码里deepwalk和node2vec都调用的是c++编译好的库libtf_euler.so里的random_walk函数,而在c++中,我看了所有的cc文件,都没有找到node2vec的实现,包括在random_walk_op.cc或者walks_ops.cc等。
能否麻烦您指示一下node2vec的实现在哪里呢?
from euler.
from euler.
明白啦,谢谢~
from euler.
你好,https://cs.stanford.edu/people/jure/pubs/node2vec-kdd16.pdf 原始论文中, 权重指的是边的权重,而不是当前节点neighbor的权重,我认为这里实现的有误。
实现在,GetSortedFullNeighbor里的neighbors_weight_在graphBuilder构建的时候读的是neighbor的顶点权重而不是边的权重,这里是否实现有误? 虽然可以trick一下不需要改代码,把邻居点的权重设置成边的权重,但是这样不太好。
同样如果lshne 也修改了p q超参数的话,也会走这个逻辑,导致出错。
from euler.
from euler.
我的意思是,用于控制结构性和同质性的P、Q参数 在条件下需要和节点之间的边的权重相乘作为游走的概率依据。而euler的实现是P、Q参数在条件下和”以自身节点看待neighbor权重“的信息做了相乘作为游走概率依据,和原始论文不一致。
from euler.
neighbor的权重是指的邻居边权重,不是邻居节点的权重
from euler.
{
"node_id": "顶点编号,int",
"node_type": "顶点类型,int",
"node_weight": "顶点权重,float",
"neighbor": {"边类型": {"邻居id": "权重", "...": "..."}, "...": "..."},
"uint64_feature": {"属性编号": ["int", "..."], "...": "..."},
"float_feature": {"属性编号": ["float", "..."], "...": "..."},
"binary_feature": {"属性编号": "string", "...": "..."},
"edge":[{
"src_id": "起点id, int",
"dst_id": "终点id, int",
"edge_type": "边类型, int",
"weight": "边权重, float",
"uint64_feature": {"属性编号": ["int", "..."], "...": ["int", "..."]},
"float_feature": {"属性编号": ["float", "..."], "...": ["float", "..."]},
"binary_feature": {"属性编号": "string", "...": "..."}
}, "..."]
}
那edge里的weight也是这条边的权重了,这两个有啥区别?
from euler.
from euler.
明白了,多谢
from euler.
Related Issues (20)
- ThreadLocalRandom() 随机数分布问题 - sample_neighbor_layerwise OP
- 找不到ppi_data.py
- samle_node样遇到 euler service cpu 100% 一直没有结果卡死问题
- pip install euler_gl python版本冲突导致失败 HOT 1
- pip install成功,site-packages下没有源码
- 关于节点权重
- install Grpc error
- 记 euler2 分布式例子run_ppi.sh 失败的原因
- 请问多ps 多euler的情况下有infer的例子可以借鉴吗
- euler目前支持导入预训练的embedding向量吗? HOT 1
- from euler.tools import json2dat相关
- euler2的graphsage怎么设置use_id=true
- 如何使用Euler做分布式的Embedding训练
- euler1 使用ppi数据集 无监督graphsage训练 loss突然特别特别大
- 子图采样的时候为什么将每一层的源节点拼接? HOT 1
- Euler1 邻居采样去重
- ValueError: inputs must be a list of at least oneTensor/IndexedSlices with the same dtype and shape
- sample_edge的输出shape是[count,3]吗?
- relation_cov code not understand
- 采样策略是入度还是出度
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from euler.