Comments (7)
tkipf
commented on July 17, 2024
You can extract and examine any hidden layer activation and check whether
it is useful as some form of graph embedding. If you train in a supervised
way, then these embeddings will be very specialized for the task that you
trained the model for, of course. If you want unsupervised embeddings, have
a look at my code for graph auto-encoders:
https://github.com/tkipf/gae
…On Sun 4. Nov 2018 at 23:03 Zhiqiang ZHONG ***@***.***> wrote:
Hi,
Could I get the node embedding with a certain length based on this code? I
should extract the output of which step?
Thanks,
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#26>, or mute the thread
<https://github.com/notifications/unsubscribe-auth/AHAcYKZtj3ZvnvnX0X33OFbSF6Fhcvr_ks5ur2QugaJpZM4YNiO4>
.
from pygcn.
zhiqiangzhongddu
commented on July 17, 2024
Excuse me that I'm training in a supervised way. It seems that GCN could only extract embeddings with the same length as num-class if I want to use the output of the last GCN-layer? Not available for a random defined range.
from pygcn.
tkipf
commented on July 17, 2024
In this case it’s best to simply take the embeddings just before doing the last linear projection to the softmax logits. In other words, if the last layer is softmax(A*H*W), take either the embedding H directly or A*H.
… On 5 Nov 2018, at 10:00, Zhiqiang ZHONG ***@***.***> wrote:
Excuse me that I'm training in a supervised way. It seems that GCN could only extract embeddings with the same length as num-class if I want to use the output of the last GCN-layer? Not available for a random defined range.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub <#26 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AHAcYCI1VOTbDa4kclXdOmlJfNyPNgsKks5ur_5IgaJpZM4YNiO4>.
from pygcn.
zhiqiangzhongddu
commented on July 17, 2024
It's clear now. Thanks.
from pygcn.
zfchen95
commented on July 17, 2024
I used the intermediate result H, but it seems the embeddings cannot be used for link prediction task, i.e. there is little difference between the dot product of the nodes with and without connection. It is understood because gcn is originally used for node classification instead of link prediction. Does anyone have an idea how to apply the embeddings for link predictions?
from pygcn.
tkipf
commented on July 17, 2024
The dot product will not be a good scoring function on embeddings trained
solely for classification. You can either use the embeddings from
github.com/tkipf/gae which are optimized for dot-product scoring (link
prediction), or you train a bilinear scoring function on top of the fixed
embeddings (taken from the supervised GCN model). A bilinear scoring
function looks like this: `\sigma(h^TWh)` where h are embeddings for nodes,
W is a matrix that you train via gradient descent on some training data for
link prediction and sigma is a sigmoid activation function.
…On Sat 1. Dec 2018 at 22:55 Zhenfeng ***@***.***> wrote:
I used the intermediate result H, but it seems the embeddings cannot be
used for link prediction task, i.e. there is little difference between the
dot product of the nodes with and without connection. It is understood
because gcn is originally used for node classification instead of link
prediction. Does anyone have an idea how to apply the embeddings for link
predictions?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#26 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/AHAcYPEud18_Br-D0RtXkuAVztNVyZKKks5u008vgaJpZM4YNiO4>
.
from pygcn.
IreneZihuiLi
commented on July 17, 2024
The dot product will not be a good scoring function on embeddings trained solely for classification. You can either use the embeddings from github.com/tkipf/gae which are optimized for dot-product scoring (link prediction), or you train a bilinear scoring function on top of the fixed embeddings (taken from the supervised GCN model). A bilinear scoring function looks like this:
\sigma(h^TWh)where h are embeddings for nodes, W is a matrix that you train via gradient descent on some training data for link prediction and sigma is a sigmoid activation function.
…
On Sat 1. Dec 2018 at 22:55 Zhenfeng @.***> wrote: I used the intermediate result H, but it seems the embeddings cannot be used for link prediction task, i.e. there is little difference between the dot product of the nodes with and without connection. It is understood because gcn is originally used for node classification instead of link prediction. Does anyone have an idea how to apply the embeddings for link predictions? — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#26 (comment)>, or mute the thread https://github.com/notifications/unsubscribe-auth/AHAcYPEud18_Br-D0RtXkuAVztNVyZKKks5u008vgaJpZM4YNiO4 .
Can you please make it clear that how to adapt W matrix for link prediction tasks?
To my understanding, we need the adjacency matrix of the last layer to check the linkings. But in the code 'adj' will not change.
Thanks.
from pygcn.
Related Issues (20)
- specifying modes train, validation and test HOT 1
- Where is Filter parameters in the code? HOT 1
- Hi, does pandas make the data preprocessing more simple?
- Normalization of features, batch-wise training, feature extraction
- question about the adjacency matrix HOT 2
- citeseer dataset seems doesnot work HOT 2
- Difference between TF and Pytorch version code HOT 5
- In tensor flow code you used early stopping,isn't it needed in pytorch???
- In `utils.py` line 36, wouldnt `adj = adj + (adj.T > adj)` also work? HOT 2
- Invoice node classification / meta-data extraction / single prediction with trained model
- How to do a semi-supervised learning? HOT 6
- Predicting node degree
- Question About fastmode
- Error: 'pybind11' must be installed before running the build.
- transform to other scope dataset
- Why do row normalization instead of column normalization？ HOT 2
- About the dataset split HOT 3
- citeseer dataset
- Cora dataset attributes
- accuracy in the experimental results 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 pygcn.