Graph Neural Networks (GNN) using Pytorch Geometric | Stanford University

This is the Graph Neural Networks: Hands-on Session from the Stanford 2019 Fall CS224W course.
In this tutorial, we will explore the implementation of graph neural networks and investigate what representations these networks learn. Along the way, we'll see how PyTorch Geometric and TensorBoardX can help us with constructing and training graph models.
Pytorch Geometric tutorial part starts at -- 0:33:30
Details on:
* Graph Convolutional Neural Networks (GCN)
* Custom Convolutional Model
* Message passing
* Aggregation functions
* Update
* Graph Pooling
The Google Colab Link: colab.research...
The course website Link: web.stanford.ed...

[@xiaoyumo7403]

PyG starts from 33:33

[@jianchen2550]

You are my hero. Love you

[@alirezasamadi5804]

AMAZING ... all tutorials start with either very basic level and leave u high and dry when it reaches to actual point, or they start with a point that u don't have any idea... this tutorial is amazing

[@SRV902]

CrossEntropyLoss already does log softmax behind the scenes. On top of that F.softmax is applied at the end of the model forward which is not needed if nn.CrossEntropyLoss is used. This is before PyTorch Geometric is introduced

[@SteveSperandeo]

No only not needed, but 2x softmax will break your model.

[@williamashbee]

i'm unworthy of this presentation. good job.

[@m.khanmohamadi9815]

Thank you very much. it was very good tutorial of gnn neural network

[@user-tz2pc6wy7f]

Really good tutorial.

[@hiro_happysky12]

Thanks for this amazing tutorial!! was really helpful for me☺

[@jinchenghuang3755]

There is something to simplify ：nn.CrossEntropy = F.nll_loss(F.log_softmax(x), label)

[@joemeyer9655]

Nice!

[@sumitkumar-el3kc]

Can anyone please tell me the prerequisites to start with GNN? I'm new to neural networks. Although I have some experience in ML but neural networks are still new to me.

[@spartacusche]

you can see the coursera course deep learning, or cs229 stanford

[@stevegabrial1106]

Hi
Plz upload more videos of Ml, DL by Stanford . thx

[@TechVizTheDataScienceGuy]

👍

[@dam1an096]

gg, good tutorial ✌

[@CXL601]

model = pyg_nn.GAE(Encoder(dataset.num_features, channels)).to(dev)
model.split_edge(data)
--- get error saying ''GAE' object has no attribute 'split_edges'",
Just checked the documentation, it is true that the latest version of GAE object doesn't have 'split_edges' functions.
so random split?

[@CXL601]

oh, it is negative sampling

[@prajwol_poudel]

Hey, do you have more tutorials in coding from cs22aw like these?
If anyone knows where I can find more coding playlist please share.

[@jz7327]

I'm wondering why that pool layer is necessary for the graph level task? Can't we just use some linear layers to predict some property that corresponds to the whole graph? Somebody can help me with this? Ty!

[@jz7327]

I think it's due to the dimension? For graph level tasks we want the whole graph represented by a vector, so this pooling is transferring the node embedding matrix to a vector?

[@laurasnow7822]

I’m like two years late to this question, but the node property matrix will be of different dimension for each graph size, so we can’t train a neural network on it directly. We could train a sequential neural network, but we don’t want to get different results based different edge orderings. The most naive approach would be to just take a sum or average of all node embedding and use that as a graph embedding. It might be enough in some cases.

[@brandomiranda6703]

what is the best GNN library as of now 2021 for PyTorch?

[@mhadnanali]

i have the same question

[@user-uq7ri1pz2c]

hey, what about other seminar tapes from the cs224w?

[@lindseyai4843]

You can find them here:
snap.stanford.edu/class/cs224w-videos-2019/

[@aidasadeghi2147]

hey the link is private is there any public?
@@lindseyai4843

[@pablobanchero3812]

@@lindseyai4843 Can you tell us the username and password?

[@vincentedeh3926]

How do i download the code used in the presentation?

[@alirezasamadi5804]

IT IS IN THE COLAB :)

[@tongliu5755]

码一下

[@expectopatronum2784]