Lihui Liu
Lihui Liu
more than 4 days for each dataset. It is better to have the log for Query2Box dataset. Thanks a lot.
I used the pre-trained embedding on KGQA, the accuracy is very low. How did you learn the embedding use kge? @apoorvumang
I try to use kge to get the pre-train embedding of fbwq_half, and use the pre-trained embedding in multi-hop answering on fbwq_half. @apoorvumang
But the pre-train accuracy is very low when using kge. If I use that embedding, the kgqa accuracy is also much lower than the result in the paper. So, I...
Can you share your config file to me? so I can get the same performance in the paper @apoorvumang
The accuracy I got on webqsp half was 0.478. May I know how you got 53.2% accuracy? @apoorvumang Validation accuracy decreases to 0.468394 from 0.478508, 0 more epoch to check
I just downloaded the code and ran it following the instruction. @apoorvumang 
I have the same question. @AntixK
what are raw, filter, and RE-GCN w. GT
The command I use is "main.py -d WIKI --gpu=2 --train-history-len 3 --test-history-len 3 --dilate-len 1 --lr 0.001 --n-layers 2 --evaluate-every 1 --n-hidden 200 --self-loop --decoder convtranse --encoder uvrgcn --layer-norm --weight...