Deep Temporal Graph Clustering
30:42
Temporal Graph Analysis with TGX
40:17
Intensity Profile Projection
55:14
Пікірлер
@ScottzPlaylists
@ScottzPlaylists 5 ай бұрын
Is the code here yet? kzbin.info/www/bejne/Y4OkfJmmntdoh7c
@wdonno
@wdonno 6 ай бұрын
Hi, thank you, this is a very interesting and helpful presentation! Could the author or someone from the group refer us to other material to provide an update on where this work stands now, in context of other work in this domain? Are there other examples where this has been used? It’s a really interesting approach and I am not familiar with this field.
@TGL_RG
@TGL_RG 6 ай бұрын
Happy that you found the content useful! For more talks, please check the other recordings of the channel. For more materials, please check out the TGL website whose link is in the channel bio!
@2255.
@2255. 6 ай бұрын
Hello, would love your inputs on how to quantify the impact of an anomaly in one node on its neighbors given a homogeneous graph and known edges
@quad_vision4393
@quad_vision4393 6 ай бұрын
Great talk! Any papers on applying this to Android OS?
@张悦-z8b
@张悦-z8b 6 ай бұрын
How can I find the corresponding slides?
@TGL_RG
@TGL_RG 6 ай бұрын
If the presenter shares them, they will be available on our webpage. The link to the webpage can be found in the bio.
@mooncop
@mooncop 7 ай бұрын
We need LARGE GRAPH MODELS WE NEED LARGE GEOMETRY MODELS WEN?!
@abhinav9058
@abhinav9058 9 ай бұрын
Crazy work do we also have something with conditional message passing?
@ANJALI20PHD003
@ANJALI20PHD003 9 ай бұрын
I have multivariate time-series data for 56 years which consists of five variables for 28 locations (that I want to consider as the nodes in my forecasting model). I am facing an issue with how to adjust the multiple variables for each node to formulate a graph for my dataset.
@superman39756
@superman39756 9 ай бұрын
Maybe trying a hyper graph approach would work or some inductive graph model like FIGRL, GraphSAGE, or MIDAS-R.
@superman39756
@superman39756 9 ай бұрын
Also you could try sequence graph transform + any other well established forecasting model that works with vectors as inputs.
@auresdz701
@auresdz701 10 ай бұрын
The first question was right to the point, I think there should be some stochasticity or good negative sampling to solve the issue or G = G'
@mooncop
@mooncop 11 ай бұрын
solid saturday start! hello from san francisco
@mooncop
@mooncop Жыл бұрын
I like big graphs and I cannot lie 🐇⏱ ciao ciao
@赖生智-r7e
@赖生智-r7e Жыл бұрын
hi, can I have the slides in this video?😀
@TGL_RG
@TGL_RG Жыл бұрын
You can find the slides for this talk and many more resources on TGL-RG website! The link can be found in "About" section.