KGEModel.test attempts division by zero if no hits are found for the specified k

[ACHinrichs]

🐛 Describe the bug

In KGEModel.test, if there is not a single hit for the given k the line
hits_at_k = int(torch.tensor(hits_at_k).sum()) / len(hits_at_k)
Attempts to perform a division by 0. Desired behavior in the case that no hits are found would be that hits_at_k gets set to 0.

Versions

[pip3] numpy==2.1.0
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] torch==2.5.1
[pip3] torch_geometric==2.5.3
[pip3] torch-kmeans==0.2.0
[pip3] torchmetrics==1.6.0
[pip3] torchvision==0.20.1
[pip3] triton==3.1.0
[conda] Could not collect