소스 코드
- 게시일 2024. 04. 27.
- ▬▬ Resources ▬▬▬▬▬▬▬▬▬▬
Paper: arxiv.org/pdf/1710.10903.pdf
Attention in NLP KRplus Series: • Rasa Algorithm Whitebo... (Rasa)
▬▬ Used Music ▬▬▬▬▬▬▬▬▬▬▬
Field Of Fireflies by Purrple Cat | purrplecat.com
Music promoted by www.free-stock-music.com
Creative Commons Attribution-ShareAlike 3.0 Unported
creativecommons.org/licenses/...
▬▬ Timestamps ▬▬▬▬▬▬▬▬▬▬▬
00:00 Introduction
00:32 Basics
5:55 Attention mechanism
11:55 The full picture
▬▬ Support me if you like 🌟
►Link to this channel: bit.ly/3zEqL1W
►Support me on Patreon: bit.ly/2Wed242
►Buy me a coffee on Ko-Fi: bit.ly/3kJYEdl
▬▬ My equipment 💻
- Microphone: amzn.to/3DVqB8H
- Microphone mount: amzn.to/3BWUcOJ
- Monitors: amzn.to/3G2Jjgr
- Monitor mount: amzn.to/3AWGIAY
- Height-adjustable table: amzn.to/3aUysXC
- Ergonomic chair: amzn.to/3phQg7r
- PC case: amzn.to/3jdlI2Y
- GPU: amzn.to/3AWyzwy
- Keyboard: amzn.to/2XskWHP
- Bluelight filter glasses: amzn.to/3pj0fK2 - 과학기술
![[여고추리반3] 순한 맛 뒤에 마라 맛이 숨어있는 학교생활 | 4분 하이라이트 | TVING](http://i.ytimg.com/vi/6Wv9UEpFRNU/mqdefault.jpg)
![수상한 연구소 (Suspicious Lab) #2｜[SKZ CODE] Ep.48](http://i.ytimg.com/vi/b-ztNXTxxLA/mqdefault.jpg)
I can admit that this is the best explanation for GAT and GNN one can find. Fantastic explanation with very simple English. The quality of sound and video is great as well. Many thanks.
Thank you for your kind words
This is the best and most in detail explanation on Graph CNN attention I've found. Great job!
This is pretty amazing content. The way you explain the concept is pretty great and I especially like the visual style and very neat looking visuals and animations you make. Thank you!
Thank you for your kind words :)
Your work has been an absolute game-changer for me! The way you break down complex concepts into understandable and actionable insights is truly commendable. Your dedication to providing in-depth tutorials and explanations has tremendously helped me grasp the intricacies of GNNs. Keep up the phenomenal work!
very well explained, provides a very intuitive picture of the concept. Thanks a ton for this awesome lecture series!
Amazingly easy to understand. Thank you.
I especially love your background pics.
Explained in terms of basic Neural Network terminologies!! Great work 👍
Extremely helpful. Very well explained in concrete and abstract terms.
This was simply a fantastic explanation video, I really do hope this video gets more coverage than it already has. It would be fantastic if you were to explain the concept of multi-head attention in another video. You've earned yourself a subscriber +1.
Thank you, I appreciate the feedback!
Sure, I note it down :)
Great! Thank you for explaining the math and the linear algebra with the simple tables.
This is a very great explanation covering basic GNN and the GAT. Thank you so much
Thank you so much for this beautiful video. Have been trying out too many videos on GNN and GAN but this video definitely tops. I finally understood the concept behind it. Keep up the good work :)
Thank you for sharing this clear and well-designed explanation.
I really salute you for this detailed video! that's very intriguing and clear! thank you again!
Thank you very much! This was my introduction into GAT and helped me to immediately get a good grasp of the basic concept :) I like the graphical support you provide to the explanation, it's gerat!
such an easy-to-grasp explanation! such a visually nice video! amazing job!
Thanks, I appreciate it :)
Clear explanation and visualization on attention mechanism. Really helpful in studying GNN.
Very Helpful Explanation! Thank you!
Very well explained. Thank you very much!
simple and informative! Thank you!
amazing!!! author well done!!!
This is the MOST BEST video of GCN and GAT, very great, thank you!
Very clear and helpful. Thank you so much!
Your visual explanation is super great, help many people to learn some-hour stuff in minutes!
Please make more videos on specialized topics of GNNs!
Thanks in advance!
I will soon upload more GNN content :)
Very nice video. Thanks for your work~
Great video! your explanation was amazing. Thank you!!
Thanks :)
most understandable explanation so far!
very good explanation! clear and crisp, even I, a beginner, feeling satisfied after watching this. Should get more recognition!
Thanks
Very clear explanation. Thank you!
Simply exceptional!
Wonderful explination! thanks
Great walkthrough.
Thanks for sharing the knowledge!
You're welcome :)
Very nice, thanks for effort!
Great quality thank you !
Muchas gracias por el video. Despues de haber visto muchos otros, puedo decir que el suyo es el mejor, el mas sencillo de entender. Estoy muy agradecido con usted. Saludos
Thank you! :)
clearly clear explanation, super best video lecture about GNN ever seen.
very helpful tutorial, clearly explained!
Thank you so much for this great video.
Brilliant video 👍👍👍
best video for learning GNN thank you so much!
Fantastic explaination.
I'd love it if you could explain multi-head attention as well. You really have such a good grasp of this very complex subject.
Hi! Thanks!
Multi-head attention simply means that several attention mechanisms are applied at the same time. It's like cloning the regular attention.
What exactly is unclear here? :)
@@DeepFindr The math and code are hard to fully grasp. If you could break down the linear algebra with the matrix diagrams as you have done for single head attention, I think people would find that very helpful.
Awesome video! Quick question: do you have a video explaining Cluster-GCN? And if yes, do you know if similar clustering idea can be applied to other networks (like GAT) to be able to train the model on large graphs? Thanks!
A great explanation, many thanks
Excellent explanation 👌 👏🏾
Outstanding explanation
Thanks for the best explanation.
Great video! Thank you
Excellent job, mate 👍👍
Thx :)
easy and best explanation
nice work
This is very helpful!
I learned so much from this video! Thanks a lot
That's great :)
A Great explanation
Thank you for wonderful content
Great Video!
I need more Graph Neural Network related video!!
There will be some more in the future. Anything in particular you are interested in? :)
Amazing thank you 🤩
Awesome.....
Thank you bro. Confused head now gets the idea about GNN.
Hehe
Love your work and thick accent, thank you! These attention coefficients look very similar to weighted edges for me, so I want to ask a question: If my graph is unweighted attributed graph, would GATConv produce different output compared with GCNConv by Kipf and Welling?
hahah, thanks!
I'm not sure if I understood the question correctly. If you have an unweighted graph, GAT will anyways learn the attention coefficients (which can be seen as edge weights) based on the embeddings. It can be seen as "learnable" edge weights.
So I'm pretty sure that GATConv and GCNConv will produce different outputs.
From my experience, using the attention mechanism, the output embeddings are better than using plain GCN.
Hi, Can you tell which tool you're using to make those amazing visualizations? All of your videos on GNNs are great btw :)
Thanks a lot! Haha I use active presenter (it's free for the basic version) but I guess there are better alternatives out there. Still experimenting :)
Thx for the awesome explanation!
A video with attention in CNN e.g. UNet would be great :)
I slightly capture that in my video on diffusion models. I've noted it down for the future though.
well explained.
THANK YOU!
Thanks for the great explanation! Just one thing that I do not really understand, may I ask how do you get the size of the learnable weight matrix [4,8]? I understood that there are 4 rows due to the number of features for each node. However, not sure where the 8 columns come from.
I think 8 is the arbitrarily chosen dimensionality of the embedding space.
Thank you for the great video. I have one question, what happens if weighted graphs are used with attention GNN? Do you think adding the attention-learned edge "weights" will improve the model compared to just having the input edge weights (e.g. training a GCNN with weighted graphs)?
Hi! Yes I think so. The fact that the attention weights are learnable makes them more powerful than just static weights.
The model might still want to put more attention on a node, because there is valuable information in the node features, independent of the weight.
A real world example of this might be the data traffic between two network nodes. If less data is sent between two nodes, you probably assign a smaller weight to the edge. Still it could be that the information coming from one nodes is very important and therefore the model pays more attention to it.
Great explination, really appretiated.
If you Please could u make a videa explain the loss calculation and backpropagation in gnn?
AWESOME!!!
Supper explaination
Thank you for the great video! I wanted to ask - how is training of this network performed when the instances (input graphs) have varying number of nodes and/or adjacency matrix? It seems that W would not depend on the number of nodes (as its shape is 4 node features x 8 node embeddings) but shape of attention weight matrix Wa would (as its shape is proportional to the number of edges connecting node 1 with its neighbors.)
Hi! The attention weight matrix has always the same shape. The input shape is twice the node embedding size because it always takes two neighbor - combinations and predicts the attention coefficient for them. Of course if you have more connected nodes, you will have more of these combinations, but you can think of it like the batch dimension increases, but not the input dimension.
For instance you have node embeddings of size 3. Then the input for the fully connected network is for instance [0.5, 1, 1, 0.6, 2, 1], so the concatenated node embeddings of two neighbors (size=3+3). It doesn't matter how many of these you input into the attention weight matrix.
If you have 3 neighbors for a node it would look like this:
[0.5, 1, 1, 0.6, 2, 1]
[0.5, 1, 1, 0.7, 3, 2]
[0.5, 1, 1, 0.8, 4, 3]
The output are then 3 attention coefficients for each of the neighbors.
Hope this makes sense :)
@@DeepFindr If graph sizes are already different, I mean if one have graph_1 that has 2200 nodes(that results in 2200,2200 adj. matrix, and graph_2 has 3000 nodes (3000,3000 adj matrix), you can zero pad graph_1 to 3000. This way you'll have fixed size of input for graph_1 and graph_2. Zero padding will create dummy nodes with no connection. So the sum with the neighboring nodes will be 0. And having dummy features for dummy nodes, you'll end up with fixed size graphs.
Hi, yes that's true! But for the attention mechanism used here no fixed graph size is required. It also works for a different number of nodes.
But yes padding is a good idea to get the same shapes :)
Very helpful video! Thank you for your great work! Two questions, 1. Could you please explain the Laplacian Matrix in GCN, the GNN explained in this video is spatial-based, and I hope I can get a better understanding of those spectral-based ones. 2. How to draw those beautiful pictures? Could you share the source files? Thanks again!
Hi!
The Laplacian is simply the degree matrix of a graph subtracted by the adjacency matrix. Is there anything in particular you are interested in? :)
My presentations are typically a mix of PowerPoint and active presenter, so I can send you the slides. For that please send an email to deepfindr@gmail.com :)
thank you. what if you also wanted to have edge features?
Hi, I have a video on how to use edge features in GNNs :)
Good explanation to the key idea. One question, what is the difference between GAT and self attention constrained by a adjacency matrix(eg. Softmax(Attn*Adj) )? The memory used for GAT is D*N^2, which is D times of the intermediate ouput of SA. The node number of graph used in GAT thus cannot be too large because of memory size. But it seems that they both implement dynamic weighting of neighborhood information constrained by a adjacency matrix.
Hi,
Did you have a look at the implementation iny PyG? pytorch-geometric.readthedocs.io/en/latest/_modules/torch_geometric/nn/conv/gat_conv.html#GATConv
One of the key tricks in GNNs is usually to represent the adjacency matrix in COO format. Therefore you have adjacency lists and not a nxn matrix.
Using functions like gather or index_select you can then do a masked selection of the local nodes.
Hope this helps :)
شكرا لك
Thanks
hi.. Your explanations are really nice and easy to understand and seem rooted in fundamentals. Thank you for that. I am new to reading research papers, and i find it difficult to understand them sometimes and end up wasting a lot of time on not-so-important things. But this is what I think my problem is, but it can be something else too...idk... like sometimes i don't have the pre req or have gap in my knowledge... Could you please make a video about it or help in the comments, or recommend some other resource to get better at reading papers and understanding from the bottom up? thank you very much 🙏🙏
Great Explanation! As you pointed out this is one way of attention mechanism. Can you also provide references to other attention mechanisms.
Hi! The video in the description from this other channel explains the general attention mechanism used in transformers quite well :) or do you look for other attention mechanisms in GNNs?
@@DeepFindr yes thanks for sharing that too in the video. I was curious about the attention mechanisms on gnn
OK :)
In my next video (of the current GNN series) I will also Quickly talk about Graph Transformers. There the attention coefficients are calculated with a dot product of keys and queries.
I hope to upload this video this or next week :)
I am following your playlist on GNN and this is the best content I get as of now.
I have a CSV file and want to apply GNN on it but I don't understand how to find the edge features from the CSV file
Thanks! Did you see my latest 2 videos? They show how to convert a CSV file to a graph dataset. Maybe it helps you to get started :)
@@DeepFindr thanks, hope i will get my answer :-)
Thanks for your awesome explanation, it's very clear and enlightening. But I have a question about the self-attention mechanism in this paper since it seems not very similar to the method in NLP. When it comes to NLP, the most common method of self-attention would do three times linear transform, which need 3 weight matrices `W_q`, `W_k` and `W_v`. Then it uses the results derived from W_q and W_k to get `a_ij`, which is the attention weight between token i and token j in a sentence. In this paper, it firstly uses `W`, `a` and `two node embedding` to compute `alpha_ij` for each node pairs. Then it uses `W`, `alpha` and `all node embedding` to get `new node embedding`.
Is my understanding correct? But I'm curious why the paper don't use different `W` in the two period. For example, we can use 2 weight matrices `W1` and `W2`, when the first `W1` can be used to get `alpha_ij` and the second `W2` can be used to calculate `new node embedding`.
Hi, yes you are right in NLP everything is differentiated with queries, keys and values.
This means, for word vectors they apply different transformations depending on the context (input query, key to map against and output value multiplied with attention).
In the GAT paper all node vectors are transformed with only one matrix W.
So there is no differentiation between q, k and v.
Additionally however, the attention coefficients are calculated with a weight vector, which is not done in the transformers model (there it's the dot product).
So I would say GAT uses just another flavor of attention and we cannot compare them directly - the idea is the same but the implementation slightly different.
I dont know if I understood you correctly, but W is only applied once to transform all nodes. Then there is a second weight vector to calculate a_ij.
Also, there are many variants of GNNs - some also do the same separation as its done in NLP.
For example if you have no self loops, you usually apply a different matrix for a specific node W_1 and for its neighbors W_2 - we can see this like q and k above.
Hope that helps! If not, let me know!
@@DeepFindr Yes, I think I have figured it out. Thank you very much for your detail and clear reply.
4:00 do you multiply "feature node matrix" with "adjacency matrix" before multiplying it with "learnable weight matrix" ?
Very understandable! Thank you.
Can you share your presentation?
Sure! Can you send me an email to deepfindr@gmail.com and I'll attach it :) thx
@@DeepFindr Hey I have also sent you an email, could you please attach the presentation?
Thanks a lot for the excellent tutorial. Just a quick question, when training the single layer attention network, what are the lables of input? How this single layer network is trained?
Thanks!
Typically you train it with your custom problem. So the embeddings will be specific to your use-case. For example if you want to classify molecules, then the loss of this classification problem is used to optimize the layer. The labels are then the classes.
It is however also possible to train universal embeddings. This can be done by using a distance metric such as cosine distance. The idea is that similar inputs should lead to similar embeddings and the labels would then be the distance between graphs.
With both options the weights in the attention layer can be optimized.
It is also possible to train GNNs in an unsupervised fashion, there exist different approaches in the literature.
Hope this answers the question :)
@@DeepFindr Thanks! Sorry, my question might be confusing. For the node classification task, if we use the distance metrics between nodes as labels to train the weights of attention layer, then I think the attention layer that computes attention coefficient is not needed. Because we can get the importance by computing the distance metrics. I wonder how we can train weights of the shared attentional mechanism. Thanks again!
Yes, you are right. The attention mechanism using the dot product will also lead to similar embeddings for nodes that share the same neighborhood.
However the difference is that the attention mechanism is local - it only calculates the attention coefficient for the neighboring nodes.
Using the distance as targets can however be applied to all nodes in the input graph.
But I agree, the various GNN layers might be differently useful depending on the application.
Got it! Thanks again!
Hello ,thanks for sharing, could you plz explain how you get learnable method,is it matrix randomly chosen or there is method behind,and is this equal to lablacian method.
One more question ,your embedding only on node level ,right
Hi, the learnable weight matrix is randomly initialized and then updated through back propagation. It's just a classical fully-connected neural network layer.
Yes the embedding is on the node level :)
Hi! Are what you explain in the "Basics" and the message-passing concept the same things?
Yes, they are the same thing :) passing messages is in the end nothing else but multiplying with the adjacency matrix. It's just a common term to better illustrate how the information is shared :)
Thanks for the video! There's a question: at 13:03, I think the 'adjacency matrix' consists of {e_ij} could be symmetric, but after the softmax operation, the 'adjacency matrix' consists of {α_ij} should not be symmetric any more. Is that right?
Yes usually the attention weights do not have to be symmetric. Is that what you mean? :)
@@DeepFindr Yes. Thanks for your reply!
At 11:30, should the denominator have k instead of j?
Also, this vector w_a, is it the same vector used for all edges, there isn't a different vector to learn for each node i, right? Thank you!
Ohh yeah you are right. Should be k...
Yes its a shared vector, used for all edges. Thank you for the finding!
very helpful video, but I still confuse in some part. Maybe I should watch this for few times. thanks
Hi! What is unclear to you?
:)
please use brackets and multiplication signs between matrices so i can map the mathematical formula to the visualization
how is learnable weight matrix is formed ? have some material to understand it better?
This simply comes from dense (fully connected layers). There are lots of resources, for example here: analyticsindiamag.com/a-complete-understanding-of-dense-layers-in-neural-networks/#:~:text=The%20dense%20layer's%20neuron%20in,vector%20of%20the%20dense%20layer.
weight vector are dependent on the nunber of node in graph? if i have a large of graph, i will got a bigger dimension weight vector?
No the weight vector has a fixed size. It is applied to each node feature vector. For example if you have 5 nodes and a feature size of 10, then the weight matrix with 128 neurons could be (10, 128). If you have more nodes, just the batch dimension is bigger.
Hope this answers the question :)
@@DeepFindr thank you so much
why replacing dot product attn with concat proj + leaky relu?
That's a good point. I think the TransformerConv is the layer that uses dot product attention. I'm also not aware of any reason why it was implemented like that. Maybe it's because this considers the direction of information (so source and target nodes) better. Dot product is cummutative, so i*j is the same as j*i, so it can't distinguish between the direction of information flow. Just an idea :)
Hi hope you're doing well
Is there any graph neural network architecture that receives multivariate dataset instead of graph-structured data as an input?
I'll be very thankful if you answer me i really nead it
Thanks in advanced
Hi! As the name implies, graph neural networks expect graph structured input. Please see my latest videos on how to convert a dataset to a graph. It's not that difficult :)
@@DeepFindr thanks for prompt response
Sure; I'll see it right now..
Would you please sent its link?
krplus.net/bidio/cbWNZZGdoJvZn2U
how do you think it will behave with complete graphs only ?
Well it will simply calculate attention weights with all neighbor nodes. So every node attends to all other nodes. Its a bit like the transformer that attends to all words.
This paper might also be interesting:
arxiv.org/abs/2105.14491
How is the adjacency matrix derived?
Hi, what exactly do you mean by derived? :)
@@DeepFindr What criteria decides what feature vector is zero'd out?
This depends on the input graph. For the molecule it's simple the atoms that are not connected with a specific atoms.
All nodes that are not connected to a specific node have a 0 in the adjacency matrix entries.
Good video, but you should have mentioned how in NLP, a sequence of words is used to build a fully connected adjacency graph. This is why attention can can be used in graph data; because even in NLP, it's already ON graph data!
Why does the new state calculated have more features than the original state? I dont understand
It's because the output dimension (neurons) of the neural network is different then the input dimension.
You could also have less or the same number of features.
Hi, sorry to bother you
I have a question
What's the difference between soft-attention and self-attention?
Hi! There is soft vs hard attention, you can search for it on Google.
For self attention there are great tutorials, such as this one peltarion.com/blog/data-science/self-attention-video
2:55 Looks like it should be sum(H * W) not sum(W * H). 5x4 * 4x8 works.Suggest you provide errata at the top of the description. Someone else has noticed an error later in the video.