Friendly Introduction to Temporal Graph Neural Networks (and some Traffic Forecasting)

Поделиться
HTML-код
  • Опубликовано: 2 ноя 2024

Комментарии • 37

  • @me_hanics
    @me_hanics Год назад +6

    Thank you! This channel seems like it's run by someone well-read. I very much love that you include research papers too.

  • @henk_iii
    @henk_iii 4 месяца назад

    Thank you for the excellent presentation of the topic, a job well done!

  • @leo.y.comprendo
    @leo.y.comprendo 2 года назад +1

    Great first video on TGNNs! Looking forward to the next part

  • @cuongnguyenuc1776
    @cuongnguyenuc1776 6 месяцев назад +1

    This work is crazy good!!

  • @eneserdogan34
    @eneserdogan34 2 года назад +1

    Amazing video on such a challenging topic

  • @prakaashsukhwal1984
    @prakaashsukhwal1984 2 года назад +1

    awesome explanation. Do share some more pytorch based example use-cases on temporal GNNs. Appreciate your sharing!

    • @DeepFindr
      @DeepFindr  2 года назад +3

      Hi! I have one for traffic forecasting :) and a video on how to generate temporal graph datasets

  • @mukeshnarendran1083
    @mukeshnarendran1083 Год назад +1

    Great video and am enjoying the GNN playlist. If there are open requests for new topics will it be okay to request for a hands on tutorial for skeletal action recognition (ex: berkley MHAD dataset) using temporal-based graph networks. Thanks

  • @mountainwolf12
    @mountainwolf12 9 месяцев назад

    Dear instructor, is it possible to do node classification on temporal GNNs as well? for example, using a trained model predicting the category of each node during each time step based on given time series of node features?

  • @zahramovahedinia1896
    @zahramovahedinia1896 Год назад

    This video is wonderful! Please, I wish to know what is the difference between higher and lower proximity orders? (In the table shown at 11:55)

  • @mountainwolf12
    @mountainwolf12 6 месяцев назад

    Hi, can node classification be done on these final temporal GNN outputs, for a predicted timestep in the future for each node?

  • @sunnyarora4916
    @sunnyarora4916 9 месяцев назад

    My CSV dataset has time values and corresponding sensor values measured every 5 min, when i tried to make a graph out of this TS ,taking node the time value and sensor value its attribute. Node gets wrong sensor values. How shall I convert this CSV to correct Graph? Any basic codes, I am a beginner?

  • @ayushsaha5539
    @ayushsaha5539 Год назад

    I don't understand the gating mechanism and the math behind the time series predictions. Any recommendations (i.e. papers)?

  • @wijdanchoukri6138
    @wijdanchoukri6138 2 года назад

    Great content, very helpful
    Thank you so much

    • @DeepFindr
      @DeepFindr  2 года назад

      Happy that you found it useful :)

  • @wilfredomartel7781
    @wilfredomartel7781 Год назад

    Nice work!

  • @kylecherry9869
    @kylecherry9869 2 года назад

    Thanks, really nice intro.

  • @VinayKumar-sd4dh
    @VinayKumar-sd4dh 2 года назад +2

    how do we handle the case where graph changes over a period of time? I mean the graph at t1 will not be same as graph at t2.

    • @DeepFindr
      @DeepFindr  2 года назад +2

      This is called dynamic graph and for example explained in this paper: arxiv.org/abs/2006.10637

    • @DeepFindr
      @DeepFindr  2 года назад +2

      The important part is to only update nodes that are present in the current graph. But nodes might be added or removed over time

    • @VinayKumar-sd4dh
      @VinayKumar-sd4dh 2 года назад

      @@DeepFindr thanks for the paper. Your videos are really helpful and simple to understand.

  • @priyankagautam4932
    @priyankagautam4932 Год назад

    can we use dgl for the GNN -lstm framework ?

  • @DEBRAJDEiot
    @DEBRAJDEiot 2 года назад

    Thank you for the very helpful video! Is the mentioned Google Colab notebook available to test and play with.

    • @DeepFindr
      @DeepFindr  2 года назад +2

      Very soon :) comes with the next video in the next days! Sorry for the delay

    • @DEBRAJDEiot
      @DEBRAJDEiot 2 года назад

      @@DeepFindr Thank you! :)

    • @DEBRAJDEiot
      @DEBRAJDEiot 2 года назад

      No problem at all! :) Thank you for sharing information and knowledge to the technical community

  • @nobywils
    @nobywils 2 года назад

    Amazing explanation sir!

  • @chientruong926
    @chientruong926 2 года назад +1

    Thank you so much!!!

  • @armandogomis7732
    @armandogomis7732 2 года назад

    Thank you very much for your video!!! I look forward to the next part. I am currently working with elliptic dataset to create temporal based classification of a dynamic graph with pytorch geometric, but I am finding it impossible to adapt the dataset to pytorch geometric. I would be very grateful if you could show me how to create a custom temporal dynamic graph in the library because the toy examples don't help much. Regards.

    • @DeepFindr
      @DeepFindr  2 года назад +1

      Hi! I somehow didn't receive a notification for your comment but found it by accident :D
      Next part will be uploaded in the next days. I will say some words around datasets and hope this will help you with your issues. Otherwise feel free to leave a comment and I'll come back to you :)
      I agree the examples could be better :D

  • @shrutishrestha8296
    @shrutishrestha8296 2 года назад

    Great content. Thank you.

  • @avishkarsaha8506
    @avishkarsaha8506 2 года назад

    great tutorial on TGNNs

  • @vincentyang8393
    @vincentyang8393 2 года назад

    Thanks, Very helpful!

  • @minalpatil564
    @minalpatil564 2 года назад

    very nicely explained..

  • @HeduAI
    @HeduAI 2 года назад

    Awesome animations! Which software did you use to create them?