Thanks, I appreciate your words! If you think the channel is underrated, then do not hesitate to share out the content! 😁 By doing so, you can actively help! Thank you so much!
Love it, thanks Coffee Bean. I'd worked with Graph Theory and worked a lot with NNs, but I didn't know what Graph convolutional NNs were. Thanks for updating my skills. I came here because I kept seeing the Graph Neutral Network term everywhere.
I have been watching videos about GNNs for two days and I got the idea, but here I completely understood everything. Thank you very much I am glad that I found your channel, keep going.
Thanks for the sub, really nice to have you around! I discovered your channel just yesterday and subscribed, but completely unrelated to this comment you left here! 😎
Haha, "to the point" is kind of the motto of the whole channel! But especially for everyone keen to find out everything around the topic, they have you! 😉
The way you break down and explain the mathematical formulae of GNN is amazing and beautiful. At the same time introducing and clearing the concept of permutation-invariance in such a short video is commendable. Thank you ❤️ Liking, sharing, & subscribing.
Very cute and entertaining idea with the coffee bean. Makes an otherwise dry subject a little bit... moist? Anyway thank you for the informative video. FYI I played it on 1.25x speed because she spoke a little bit too slow for me! Great work!
Thanks for watching! The speaking speed is something I am still adjusting to find my pace. Happy that you used the speedup functionality to help yourself. :)
Oh my GOD , I have been trying to study gnns for so long and this is by far the best video I have seen on this topic. Thank you for clarifying that "convolution" is misleading in GCNs.
Thanks, I really tried to convey the important concepts. The other Schnick-schnack in GNNs is very good at scaring away people trying to learn about GNNs for the first time.
@@AICoffeeBreak Soo, we are still using backpropagation to learn the weights right? And how do we get the final output from the individual node embeddings? (Considering that the output is global for the entire graph and not local for each node) Thanks in advanced
@@ditherycarbon8661 Yes, it is still backprop and gradient descent. If we need to make a classification of the whole graph, we need to apply the few extra classification layers on the aggregation of the whole graph. Just an idea (GNNs are not my area of expertise): one could still do graph classification if the GNN layers are so many that the information had time to smooth out over the entire graph. Then we could still use one output node alone to say something about the whole graph.
I can't quite understand how the weighted sum of neighbour vectors is permutation invariant. For example if we swap node 4 and node 2 vectors, then node 4 vector will now get weight Ci2 and the node 2 vector will get Ci4. Why won't the sum change?
First we multiply node's 4 vector representation with a matrix W, we also multiply the vector representation of node to with the same matrix W. So swapping them in the sum does not change anything (commutative).
@@cesar73silva Depends a lot what you want to do. An an example: for NLP it is quite common to initialize h_0 with word embeddings. In applications where you really have nothing to start with, h_0 could be even initialized randomly.
Thanks very much for the explanation. I still didn't get it with the notation of 'W' and 'U' in the formula. Where is it exactly on the figure? is that in the edges of the graph so we can multiply with the 'H' ? or in somewhere else (another figure) you didn't show? If there is another NN after this graph, I am curious how do you connect this graph with that NN
Hey, thanks for reaching out! I would love to upload on bilibili myself, the problem is that I do not get past the account creation verification due to my poor Chinese. I would love some help with that. Would you mind writing me an email? ☺️
The term \Sum_(j in Nbr(i))1/c_(i,j) * h_j^t * U , does this follow from the Kolmogorov-Arnold representation theorem for continuous mulitvariate functions? Excellent video I may add.
There is certainly a striking similarity to it. But I am not really sure, I can only cite a paper I found about this and point you to it: "The Kolmogorov-Arnold representation decomposes a multivariate function into an interior and an outer function and therefore has indeed a similar structure as a neural network with two hidden layers. But there are distinctive differences. One of the main obstacles is that the outer function depends on the represented function and can be wildly varying even if the represented function is smooth." export.arxiv.org/pdf/2007.15884.pdf
Thank you very much for all your videos. We always hear that computer vision performance has exceeded human performances. But where do we get this information from and how about other domains like NLP, Speech recognition, financial fraud detection, autonomous driving and malware detection ? thanks again
This channel is so underrated. There is lot of info if you are learning for first time. But best approach is to watch video 3-4 times.
Thanks, I appreciate your words! If you think the channel is underrated, then do not hesitate to share out the content! 😁 By doing so, you can actively help! Thank you so much!
Love it, thanks Coffee Bean.
I'd worked with Graph Theory and worked a lot with NNs, but I didn't know what Graph convolutional NNs were.
Thanks for updating my skills.
I came here because I kept seeing the Graph Neutral Network term everywhere.
Ms. Coffee Bean is so glad this video was helpful for you!
I have been watching videos about GNNs for two days and I got the idea, but here I completely understood everything.
Thank you very much I am glad that I found your channel, keep going.
That is a nice intro. Thanks for taking the time to make it.
Glad you like it!
i love your channel. Just found you yesterday and as a nearly complete scrub in ML this helps for a solid foundation!
Thank you Miss Coffee Bean !
Really useful and I like the creative animations! Keep up the great work, subscribed!
Thanks for the sub, really nice to have you around!
I discovered your channel just yesterday and subscribed, but completely unrelated to this comment you left here! 😎
@@AICoffeeBreak heheh nice, glad to hear that and glad to be here!
Really well presented and animated. Keep it up!
I finally have the formula on lock. Thank you
I also made a video on GNNs but I have to admit yours is more compressed and gets faster "to the point" :) Well done!
Haha, "to the point" is kind of the motto of the whole channel! But especially for everyone keen to find out everything around the topic, they have you! 😉
BTW, great channel! Your GNN videos are also accompanied by a blog post! You have something for everyone!
Thanks! Sounds good, I look forward to your future videos :)
Nice! Keep up the good work! You are a true researcher and helping us other researchers to keep on track the real relevant things from literature!
The way you break down and explain the mathematical formulae of GNN is amazing and beautiful. At the same time introducing and clearing the concept of permutation-invariance in such a short video is commendable. Thank you ❤️ Liking, sharing, & subscribing.
Wow, thank you! This comment made my day.
Thank you for such Clear and Concise information !!
Just discovered this channel and ngl, I think im in love with coffee bean 😂 very good and succinct video
Great intro!
She is phenomenal
You are phenomenal!
I find this video very useful. I have subscribed!
Awesome! 👍
Very cute and entertaining idea with the coffee bean. Makes an otherwise dry subject a little bit... moist? Anyway thank you for the informative video. FYI I played it on 1.25x speed because she spoke a little bit too slow for me! Great work!
Thanks for watching! The speaking speed is something I am still adjusting to find my pace. Happy that you used the speedup functionality to help yourself. :)
Very helpful video, such complicated concept explained so beautifully and in simple manner
Oh my GOD , I have been trying to study gnns for so long and this is by far the best video I have seen on this topic. Thank you for clarifying that "convolution" is misleading in GCNs.
Thanks, I really tried to convey the important concepts. The other Schnick-schnack in GNNs is very good at scaring away people trying to learn about GNNs for the first time.
2.54 - I was happy
3.00 - RIP
😅
i was about to leave.. then her voice at the end said, "hey, do not forget to like & subscribe ..", and that's how she caught her fish!
Love your "fish-catching" formulation.😅 Is it right for her to assume from your profile picture that you like sailing?
@@AICoffeeBreak you’re absolutely right! lol
Cool! I will tell you a secret: Ms. Coffee Bean loves sailing too (but she is quite the beginner in the matter)!
Great explanation, loved this.
Thanks a ton ma'am !
Thank you so much.
I can not thank you enough!! Great great work!
So glad it helped! Means a lot to Ms. Coffee Bean.
Nice explanation thanks!
Glad to help!
Really cute channel. Why you don't have more subscribers is beyond my understanding.
Such a clear and accessible explanation, thank you!!!
Great to hear, thanks! ☺️
Thanks a lot !
This was a helpful and stellar video!!
Great introduction with examples 👏🏽🙌🏽👍🏽!!
Glad you liked it!
Thank you!
Thank you
So what is the groundtruth and loss function for graphs? (how do you actually learn the weights)?
Depends on what you are trying to do: For node classification, you have a cross-entropy loss for predicting the label of each node, for example.
@@AICoffeeBreak Soo, we are still using backpropagation to learn the weights right?
And how do we get the final output from the individual node embeddings? (Considering that the output is global for the entire graph and not local for each node)
Thanks in advanced
@@ditherycarbon8661 Yes, it is still backprop and gradient descent.
If we need to make a classification of the whole graph, we need to apply the few extra classification layers on the aggregation of the whole graph.
Just an idea (GNNs are not my area of expertise): one could still do graph classification if the GNN layers are so many that the information had time to smooth out over the entire graph. Then we could still use one output node alone to say something about the whole graph.
@@AICoffeeBreak Thanks, makes sense
I can't quite understand how the weighted sum of neighbour vectors is permutation invariant. For example if we swap node 4 and node 2 vectors, then node 4 vector will now get weight Ci2 and the node 2 vector will get Ci4. Why won't the sum change?
First we multiply node's 4 vector representation with a matrix W, we also multiply the vector representation of node to with the same matrix W. So swapping them in the sum does not change anything (commutative).
This is excellent
Really nice explanation!
Very succinct explanation
Yes. This is good.
Thanks!
@@AICoffeeBreak A question, how do I get the initial representations for h_i ? Or what possible ways are there
@@cesar73silva Depends a lot what you want to do. An an example: for NLP it is quite common to initialize h_0 with word embeddings.
In applications where you really have nothing to start with, h_0 could be even initialized randomly.
Awesome video!
Thanks! You are THE Pratham Prasoon! I know you from Twitter. 😄
Wow This was such a good explanation.
Thanks very much for the explanation. I still didn't get it with the notation of 'W' and 'U' in the formula. Where is it exactly on the figure? is that in the edges of the graph so we can multiply with the 'H' ? or in somewhere else (another figure) you didn't show? If there is another NN after this graph, I am curious how do you connect this graph with that NN
i would love some links or names to the original papers you are referring to
Is there an easy implementation of simple GNNs available somewhere? On github I can see only sophisticated approaches for wierd problems.
If there is one, I would also like to know. :)
This is so beautiful. I am crying. Thanks a lot
Thank you so much! It means a lot to me that it meant something to you!
i still have many questions in mind, but this is surely a very good introduction
Good explanation of such dry topic
🏜️
thanks!
Hi Ms. Coffee Ban, could I translate the video and pub to another video domain(bilibili) with that language with cite the origin from?
Hey, thanks for reaching out! I would love to upload on bilibili myself, the problem is that I do not get past the account creation verification due to my poor Chinese. I would love some help with that. Would you mind writing me an email? ☺️
Well done 🥳
Are you sure that for each "h" we need to apply weight matrix "W", and not scalar "w"???
Each h is a vector, therefore W is a matrix. 😃
@@AICoffeeBreak Thank you.
Thanks for this video. I wanted to ask - does this video not also describe GNNs with RNNs? Given that nodes you describe have some short term memory?
The term \Sum_(j in Nbr(i))1/c_(i,j) * h_j^t * U , does this follow from the Kolmogorov-Arnold representation theorem for continuous mulitvariate functions? Excellent video I may add.
There is certainly a striking similarity to it. But I am not really sure, I can only cite a paper I found about this and point you to it: "The Kolmogorov-Arnold representation decomposes a multivariate function into an interior and an outer function and therefore has indeed a similar structure as a neural network with two hidden layers. But there are distinctive differences. One of the main obstacles is that the outer function depends on the represented function and can be wildly varying even if the represented function is smooth."
export.arxiv.org/pdf/2007.15884.pdf
Thank you very much for all your videos. We always hear that computer vision performance has exceeded human performances. But where do we get this information from and how about other domains like NLP, Speech recognition, financial fraud detection, autonomous driving and malware detection ? thanks again
Thank you so much! #prayinghandsemoji
Well explained. Thanks!
Very basic info but you still used terms and notations hard for a new learner. haha. but it is good one 加油。
You have a beautiful accent girl
GCNNs, what a horrible name!...
Gone are the times of AlexNet... 😅
why can't you use XGboost or decision trees for node level classification instead of GCN?
I love you ma'am
you’re cute
Honestly, couldn't understand in the first attempt :(
The coffee bean acts as a distraction. Good explanation otherwise.
Me: 😀🎉
Ms. Coffee Bean: 😶
lol