Pytorch Geometric tutorial: Edge analysis

แชร์
ฝัง
  • เผยแพร่เมื่อ 2 พ.ย. 2024

ความคิดเห็น • 14

  • @karanbania2785
    @karanbania2785 ปีที่แล้ว +1

    Hey Antonio,
    Amazing videos and thanks for this!
    However, in this tutorial, as pointed out by @Arjay2186, the model is just learning to predict a lot of non-existant edges and the accuracy seems high; F1 score would be a better metric in this case. For anyone following these tutorials I suggest you compute pos_logits and neg_logits separately and then concatenate them, also add a margin (~1.5) to neg_logits, the model should learn better features. You can also try to make the model more complex (more convolutions, bigger feature dimension, etc.). This will bring down the number from 3M+ to a comparable magnitude. I tried this and it worked.

  • @jobiquirobi123
    @jobiquirobi123 3 ปีที่แล้ว +2

    These videos are gold

  • @chavo004
    @chavo004 ปีที่แล้ว

    Great tutorials Antonio. If your dataset is an edge-list with edge-level features and no node level features (e.g., no x feature matrix), can this still work with this autoencoder?

  • @annavarbella8228
    @annavarbella8228 2 ปีที่แล้ว +3

    Hi Antonio! Great video, I have not understood if after training, the decode_all step is supposed to give you new links, not seen during training.

  • @Arjay2186
    @Arjay2186 2 ปีที่แล้ว +3

    Hi Antonio. Amazing videos. One question, however: The final decode_all returns overall 3M+ edges in the final_edge_index. Isn't it a bit too much given that the initial edge_index has just 10.5k?

    • @liammagargal3164
      @liammagargal3164 2 ปีที่แล้ว

      I have the same issue. Was this ever resolved?

  • @736939
    @736939 2 ปีที่แล้ว

    Is this prediction or the classification? I need to know how to predict an existing of the future edge, based on the historical data how can I do it?

  • @prakaashsukhwal1984
    @prakaashsukhwal1984 3 ปีที่แล้ว

    Great video. May i ask a question: i have a KG stored in networkx graph G. how should i load it in your notebook to perform link prediction? I am not sure if i need to convert from networkx format to cora dataset type format.

    • @mohamadabdulkarem206
      @mohamadabdulkarem206 2 ปีที่แล้ว

      what is positive edges and negative edges in the graph by example?

  • @canernm
    @canernm 3 ปีที่แล้ว

    Hi, thank you for the videos. Quick question: why don't you use DataLoaders to split the downloaded dataset into batches before training? Thanks

    • @94longa2112
      @94longa2112  3 ปีที่แล้ว +1

      you are right :)
      if you keep following our videos, you'll find it out :)

  • @partialtransmission5815
    @partialtransmission5815 3 ปีที่แล้ว

    Hello Antonio, how could we modify the train-test edge splitting function for directed graphs? It does not work correctly for those and I am quite stuck..

    • @94longa2112
      @94longa2112  3 ปีที่แล้ว

      Hi, one simple idea, could be the one to copy the function from the repository, modify it, and use the modified version locally.

  • @megalovania8707
    @megalovania8707 2 ปีที่แล้ว

    (i am sure you're great at all of this but i am talking about the delivery of the explanation). The z value in decode() where it takes the value of edge index generated in the line before needs better intuitive explanation. Totally lost there.