Comments (1)
发表一下个人拙见:
- 为了便于计算采用了定长的均匀采样作为领域(也就是采集到正负样本都有可能)
- 论文中的3.2部分所述损失函数是由两部分加起来的(目的是使得邻域嵌入表示尽可能相近,非领域【应该也就是负样本点】表示尽可能远),前半部分是一个点与其正样本(也就是邻接节点)的相似度,后半部分是一个点与其负样本(非邻接节点)的相似度的相反数。
- 不同点的邻域点数量不同处理很麻烦(输入就变成一个变长序列了),作者说未来工作可以研究如何使用非均匀采样,如果只采集正样本的话就变成了你说的这种方式。
from graphsage-pytorch.
Related Issues (18)
- no model_save function? HOT 1
- How to adapt for weighted graph
- RuntimeError: stack expects a non-empty TensorList HOT 1
- The implementation may be incorrect because the two embedding layers are very sparse. HOT 4
- How to perform the inductive learning? HOT 2
- File not found error. HOT 5
- typo in line 73 of main.py? HOT 2
- Low memory utilization
- deleted
- Edges not directed HOT 1
- Not convergenced. HOT 1
- Not convergence. HOT 2
- Could not find a version that satisfies the requirement torch==1.0.1.post2 HOT 2
- where is the embedding metrix?
- how can we use it on mr or R8 datasets ?
- some questions about the models.py HOT 5
- assert len(embs) == len(nodes) AssertionError HOT 1
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 graphsage-pytorch.