An Introduction to Graph Neural Networks: Models and Applications

[@leixun]

*My takeaways:* 1. Background 0:48 2. Graph neural networks (GNN) and neural message passing 6:35 - Gated GNN 26:35 - Graph convolutional networks 29:27 3. Expressing GGNNs as matrix operations 33:36 4. GNN application examples 41:25 5. Other models as special cases of GNNs 47:53 6. ML in practice 49:28

[@shawnz9833]

can you help with that: what is a MLP in "you multiply it with a single layer MLP" @23:29?

[@leixun]

@@shawnz9833 Multilayer perceptron

[@shawnz9833]

@@leixun Cool, thank you mate!

[@leixun]

@@shawnz9833 You are welcome mate, I am doing some deep learning research as well. You are welcome to check out our research talks on my KZbin channel.

[@mehmetf.demirel8647]

great talk! the audience questions were helpful, but i felt like they were a bit too many in that they kinda negatively affected the flow of the talk.

[@susmitislam1910]

So GNNs are basically something like calculating word embeddings in NLP. We have a dataset describing the relationships between pairs of words (nodes), and we want a vector representation that reflects how often they co-occur (weight of the edge between the nodes), i.e., how much relatedness the two words have. Once we have such vectors, we can build a vanilla, recurrent, or convolutional neural net to find out a mapping between the vectors and the output we desire.

[@syllogismo]

Don't know why people are criticizing this video and the audience. Great introduction to graph neural networks!

[@iltseng]

At time 34:11, the (dot product of matrix A and matrix N) should be [ b + c ; c ; 0 ]

[@MingshanJia]

Actually, here what we use is the incoming edges (see 14:55), but that is true the slide is confusing about that.

[@michaelkovaliov8877]

It seems that the mistake is in the graph adjacency matrix, because the result vector is true given the drawing of the graph.

[@PenguinMaths]

That is a mistake in the slide, A should be transposed to describe the incoming edges instead of the outgoing ones.

[@khwajawisal1220]

its using einstein notation, not the normal one that we use.

[@kristofneys2349]

There are many mistakes or confusing comments in this presentation, no wonder the audience keeps asking questions. Not a good talk at all....

[@ashutoshukey3803]

The explanation ability and use of high-level diagrams by the presenter were phenomenal. Questions from the audience definitely messed up the flow of the presentation quite a bit though.

[@rembautimes8808]

"Spherical Cow" - funniest analogy yet for a Neural Net layers. Great talk

[@Peaceluvr18]

Wow, what an excellent presentation, from someone with an ML background. Explains the basics a bit but also covers deep concepts. Super clear graphics! Seriously whoever made the graphics for this can I hire you to do my slide graphics? And thought it was very cool that the lecture attendees were bold enough to ask so many questions! Wish people asked more questions during my lectures+talks.

[@runggp]

awesome talk! The MSR audience asked quite a few questions, which are actually helpful , eg, what are they, how they work/update, why they are created and designed this way, etc

[@shawnz9833]

can you help with that: what is a MLP in "you multiply it with a single layer MLP" @23:29?

[@MobileComputing]

While the audience questions were mildly irritating (to put it, mildly), bombarding the speaker during his intro with questions that could reasonably be expected to be answered eventually in an 1-hour talk, why would the speaker give a talk on one of the most advanced neural network architecture to an audience without any machine learning background?

[@ziranshuzhang6831]

You are right, I am expecting to quickly adopt the GNN concept but the audience keeps asking irritating questions that I have to constantly hit the right button.

[@ohmyumbrella]

I agree. I mean I do see the point of giving this lecture to an audience without previous exposure to ML , if it is for the purpose of attracting them to the subject but in that case there should have been another video of the same lecture without so much interruption. It would take extra time and effort but for people who are trying to effectively learn GNN and have some knowledge of basic ML, these questions are very annoying and hinders the learning experience.

[@robbat1209]

The questions of the audience are absolutely valid, if they bother you there are plenty of other videos without an audience that you could watch

[@MobileComputing]

@@robbat1209 This comment is absolutely valid. If it bothers you, there are plenty of other comments that you could read. This talk was from 4 years ago. This was one of the only sources about GNN, and before GenAI video summaries would allow audience like myself to comfortably skip ahead without fear of missing important information.

[@robbat1209]

@@MobileComputing 🤣🤣 true, my bad. The questions weren’t too horrible tho

[@alphaO27]

In 16:51, I think he meant for each node connecting to n (instead of n_j), because from the expression, we take all nodes n_j connected to n to be able to calculate the new state of node n h_t^n.

[@jonfe]

I dont understand why GRU is used, the input in GRU is a (Node x Caracteristics) Matrix, where is the temporal dimension?

[@instantpotenjoyer]

DiscussIon on the actual topic starts ~ 6:40

[@heejuneAhn]

He explains using time progress, which make some cofusion to the audience and me.

[@eljangoolak]

Very good presentation, but it is very difficult to follow with all the interrupting questions

[@sm_xiii]

Where can we get the slide deck please?

[@losiu998]

Great presentation. But I have to point out something. I have no idea why you would use einstein notation instead of simple matrix multiplication? It raises unnecessary confusion and it's not related to GNNs.

[@pielang5524]

Let the speaker talk!

[@arjitarora8418]

Great Introduction!

[@Exhora]

29:35 about CGNs, he said you multiply the sum of the messages with your own state. But in the equation, it is a sum. I didn't get which one is correct.

[@DED_Search]

is there anyway to get access to the slides? Great talk! Thanks.

[@FsimulatorX]

OMG! For a second I thought he looked like the CEO of Google and was wondering to myself: why would the CEO of Google do a presentation about Neural Networks AT MICROSOFT!!

[@mansurZ01]

35:40 I think the dimensionality of M should be (num_nodes x D), unless D==M. EDIT: from what follows, it should be M = HE, and D can be different from M.

[@aladdin1776]

The talk is quite intriguing; however, the interruptions from the audience are quite disturbing.

[@sunaxes]

So GNN is just message passing on a graph or did I miss something? This has been around since way back, isnt it??

[@pharofx5884]

dat cough frequency suspiciously high. Distance thyself socially sir.

[@maloxi1472]

Don't worry, it's from November 2019

[@jmplaza4947]

@@maloxi1472 COVID was already spreading then, right? I hope he's ok... wherever he is now...

[@danielliu9616]

He is maybe THE patient zero

[@yanzexu6912]

bless him

[@stackexchange7353]

@@danielliu9616oh shii

[@soniagupta2851]

Excellent explanation

[@minghan111]

too many questions, just wait for the speaker please.

[@pharofx5884]

In formulating their questions they re-explained what is going on an order of magnitude better than the speaker. thats kinda sad

[@MobileComputing]

@@pharofx5884 I just watched the version from 2 years ago. Only 18 minutes long, but almost identical in content, yet that was much clearer. Really sad to see.

[@codewithyouml8994]

The miss, at 40:00 was right .... as i was alsoooo really confused, like all the matrix operations were seemed to be invalid if not swapped ... lol what kind of inverted conventions are these ....

[@peter-holzer-dev]

I am pretty sure this is a great talk but unfortunately all the questions in between disturbs the flow a lot (also because most of them are hard to understand acoustically).

[@vritansh14]

Amazin Talk !

[@leventesipos1456]

The notation is incomplete or incorrect in so many places on the presentation, that it was hard to follow.

[@klaimouad740]

can we propagate messages for example depending on the edges features for example if the distance from node n to m is greater than their distance to p then we propagate the message first to p then we perform the propagation to the other node m

[@BapiKAR]

could you please post the ppt here? Thanks

[@sebamurgui]

OH MY GOD that audience

[@miketurner3461]

I had to stop watching because of them

[@kellybrower301]

I wanted to believe it wasn’t true.

[@lidiias5976]

36:53 what is M in the shape (num_nodes by M)?

[@samuisuman]

There is no intuitive explaination, but quite informative

[@goblue1011]

Honestly some of the audience who raised questions have quite big ego and have no idea what they are talking about.

[@hamishhall5423]

What is the dimension M, for the msg_to_be_sent and received_messages etc. I get that D is the dimension of the node representation, N the num_nodes etc

[@arisioz]

Are those actual MS employers in the crowd? They are worse than 1st year CS students

[@giannismanousaridis4010]

I found the slide for everyone who asked here: miltos.allamanis.com/files/slides/2020gnn.pdf (Idk If I'm not supposed or allowed to post the link here, if not sorry for that, I'll delete my comment. Just let me know).

[@warpdrive9229]

You can let it remain here :)

[@NewtonInDaHouseYo]

Excellent introduction, thanks a lot!

[@mohammedamraoui4147]

and for Edge classification?

[@halilibrahimakgun7569]

Can you share the slides please. I like them.

[@r.dselectronics3349]

i am a researcher..the video contain the beautiful concept ...i like very much....:)..specially binary classification part ...i am so excited about this concepts....

[@BruceChen27]

Seems several people were not healthy

[@patrickadjei9676]

People are not happy for the many questions. However, I'm kinda sad that he doesn't re-state the questions before answering :( like why?

[@hfkssadfrew]

34:46 . it is NOT A* N, it is N' * A ....

[@ZephyrineFreiberg]

It should be (A^T)*N

[@rocking4joy]

Don't understand the praise in the comment section, I actually found it kind of sloppy with typo-s but the audience and the questions are really great.

[@pielang5524]

at time 35:51, the adjacency matrix A should also depend on edge type k imo.

[@pielang5524]

OK.. The presenter confirmed this shortly after...

[@khwajawisal1220]

thats why software engineers should not teach, you assume everything is a design/modeling detail when in reality they are part of the mathematics behind them. and i seriously miss those old days where professors used to teach with a chalk and board.

[@arashjavanmard5911]

It would be great if you could also publish the slides!

[@mayankgolhar8761]

Slides from the presenter's website: miltos.allamanis.com/files/slides/2020gnn.pdf

[@arashjavanmard5911]

@@mayankgolhar8761 thanks

[@sherazbaloch1642]

Need more tutorial on GNN

[@2000sunnybunny]

Great session !

[@yb801]

Is this a 2016 talk?

[@WeeeAffandi]

You can tell this lecture was recorded during the prime Covid by hearing the constant coughing from audience (and the speaker)

[@blanamaxima]

Is this related to bread baking ?

[@RARa12812]

How tp turn off questions

Where is the inputs and outputs?

[@miketurner3461]

Clearly you would've been one of the people asking foolish questions they could answer using Google

[@aichemozenerator8446]

good

[@lifelemons8176]

horror crowd. this is something I see in every microsoft talk

[@JK-sy4ym]

Unfortunately many good researchers can’t present their work well.

[@losiu998]

34:22 - is it vector-matrix multiplication? if so, the result is wrong i guess @edit: Matrix A should have ones under diagonal, not above - then result is as presented

[@sirisaksirisak6981]

At least it save time in doing strategy.

[@CodingwithIndy]

Is that SPJ I hear in the audience at 9:18

[@carloderamo]

Some good person should take this video and remove all the awful questions from the audience

[@ngideo]

I hear Simon Peyton Jones in the audience

[@rherrmann]

Easily recognizable indeed!

[@guest1754]

Wondering how many people had covid in that recording...

[@kutilkol]

Rip ears. Wtf with the caughing. Use at least some compressor for the vocal audio omg.

[@dalahmah]

I found the lecture’s atmosphere dull and depressing. It seems that the lecturer was forced to give the lecture!

[@yanyipu4029]

Great Video but annoying audience

[@kushalneo]

👍

[@barriesosinsky9566]

An aromatic ring is not a "single bone" next to a "double bone." The bonds are a resonance form in a single state. Treating them with graph theory is not supported by current models.

[@aglaiawong8058]

the interruptions are so annoying...

[@jebinjames6317]

People need to remember they’re watching a free video on KZbin...it’s not your advanced ML private tutoring session...

[@ММ_4321]

Kind of confusing for me. And the audience very annoying

[@KeshavDial]

The audience ruined this presentation. I have never felt worse for a presenter.

[@eaglesofmai]

are GNN's patented? does anyone know if using a paritcular ANN construct can be subject to litigation?

[@iSpades0]

that audience was pretty annoying tbh

[@thevanisher4609]

Horrible audience, great talk!

[@williamashbee]

cough totally ruined the presentation.

[@yiweijiang]

So that's machine learning! Haha, lol

[@miketurner3461]

The audience needs to take a freaking ML 101 class before asking stupid questions

[@MrArmas555]

++

[@Tyomas1]

awful introduction

[@robodoc1446]

Appalling talk! It shows why coders are terrible in public speaking or often fail to explain things in a transparent manner. Before explaining how message passing is done in an end-to-end learning architecture, he jumped to talk about Gated GNN leaving an impression that GRU may be an important part of GNN. This is one of the reasons why he got so many questions and confusion surrounding his lecture.....what is h_t? "well, this is not something that changes"... seriously Microsoft!

[@TheDavidlloydjones]

Word salad. A hopeless mess of talking at and around a topic without actually touching it. Take it down. Tell the guy to try again.

[@saulrojas2679]

Slides can be found at: miltos.allamanis.com/files/slides/2020gnn.pdf