search

INK-USC / RE-Net

Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (EMNLP 2020)
http://inklab.usc.edu/renet/
436 stars 95 forks source link

metric,know-evolve and WIKI datasets question #48

Closed CaiWZ closed 2 years ago

CaiWZ commented 3 years ago

Hi, Gentleman

Thank you for your excellent research and open source codes about RE-Net, I have some questions about this paper.

  1. But I can run codes in ICEWS14 and ICEWS18 in pretrain.py，But CUDA out of memory in WIKI even though the batch is 16, I don't how can I update codes. my pytorch is 1.7 python is 3.7.9 dgl is '0.4.3post2',CUDA Version: 11.0
  2. ICEWS14 does not have vaild.txt, so how can i run it?
  3. In Metric, I think only fifilter from the list all the events that occur on [time] maybe is a good idea?

image

 4. If you implement Know-Evolve in pytorch, can you provide codes.

Thanks a lot!

woojeongjin commented 2 years ago

Hi!

  1. Did you try a smaller batch size?
  2. I used the last checkpoint to test in ICEWS14.
  3. Yes you could filter all the events on [time]. But in my implementation, I didn't do that.
  4. I used the official Know-evolve.

Thanks!