Jude Oh
Jude Oh
hello, While running your Spectralnet code, it raised the same non-reproducible issue for me as well. For "cc" dataset, I had pretty much similar result with the paper. However, using...
Thank you for the advice. Could you specify the detailed version of Ubuntu, Tensorflow, and Python that you have tested on?
I have tried python 3.5, tensorflow 1.4 in either Ubuntu 14.04.5 or Centos 7. The accuracy is now as expected: ACC 0.969 and NMI 0.921 (Ubuntu 14.04.5) ACC 0.97 and...
In original GraphSAGE, the default hidden dimension is 128 if you did not specified additionally. However, my shell script specified to use 512. Maybe this caused the difference.
I wonder if the above solution is applied to release in the near future.
It was found that the reason was the atomic_add operation in the awq_gemm_triton kernel. (https://github.com/casper-hansen/AutoAWQ/blob/main/awq/modules/triton/gemm.py#L249). Atomic operation is undeterministic so it can cause the difference in output. To avoid the...