Graph neural networks: Variations and applications
Вставка
- Опубліковано 3 чер 2024
- Many real-world tasks require understanding interactions between a set of entities. Examples include interacting atoms in chemical molecules, people in social networks and even syntactic interactions between tokens in program source code. Graph structured data types are a natural representation for such systems, and several architectures have been proposed for applying deep learning methods to these structured objects. I will give an overview of the research directions inside Microsoft that have explored different architectures and applications for deep learning on graph structured data.
See more at www.microsoft.com/en-us/resea... - Наука та технологія
Give this guy a cookie. Clearly explained, make my life easier as I now refer people to this instead of explaining them for hours and hours
Links or no links, this video is far more clear than even the talks of the ones who published the paper...
Cannot agree more.
This lecturer is phenomenal
Thank you! This is fascinating!
Great intro to a bunch of useful resources
Thanks so much. This is very clear explained. A MUST SEE for GNN beginners.
:)
Thank you for the talk, I have good info on this as of now...
A very good and clear explaination.
On the eve of watching this presentation, I gave it a thump up because all the comments say it is phenomenal.
That's a collaborative recommendation.
can you share the great slides? it's so vivid!
I have question in nlp applications, We all know there is graph relationship in a sentence , but we do not know what the relationship(edges) is, so how can we use it in nlp?
Does this method work for dynamic graphs? Since we need information about neighbours of every node, the adjacent nodes should be known prior. Also, in what format the graph is given as input? Is it an adjacency matrix or list?
One can look into SAGE convolutions.
The animation of message passing is so cool. Where can I steal the slides? lol
for real i need these visuals
A bit confused about the networks representing edges. Which of the following is true? 1. Each edge is represented by a unique network, or 2. Edges of the same *type* are represented by the same network, each *type* is represented by a unique network?
2.
I think it can be both each networks type can create of unique ( for result or next chapter ) and it can be same for same reasons if you talking about targetting outputs like we training some networks.
How do I make such cool presentations? (Also which tool did he use to make this presentation slides?)
Wait how are they directed? Aren't they bidirectional? If the adjacency matrix is symmetric it is not a directed graph.. but a bidirectional one isn't it?
Can you share slides please.
I am not good about those function parameters and the historical of it but one me interesting I rectangular shape he create to contains object!
Anyof shape is diagonal symmetry or they are horizontal and vertical symmetry⁉️
Otherwise people need to do like this all the time they taken pictures 🤸
Microsoft has no related software to offer. As of 2018, look at "deepmind/graph_nets" and "dmlc/dgl" instead.
github.com/microsoft/tf-gnn-samples
nick talk.
A few thoughts:
- Their integration algorithm seems like a bad inspiration of what SNNs do. It would make more sense to have time constants and more dynamics.
- They should not always look from the "god's eye view" considering in many cases it highly specific features or subgraphs of graphs which are important for a function/
- I notice they didn't compare their method to established graph theoretic methods. They should.
what are SNN's ? As in the full form. Sorry to sound dumb, started with gnn's a week ago
As usual very exiting video with no links to recent papers. Very shame microsoft
if you go to 10:10 you can see a bunch of references for the most relevant papers. You just need to type them down in your search bar and voi la, links to all the papers.
Also checkout this talk vimeo.com/238221016 has many references.
Why do not you talk a bit clearly ? Has talking been monetized a time ago ? Very bad presentation