blocks have isolated nodes in EdgeDataLoader of unsupervised graphsage example

## 🐛 Bug

## To Reproduce

Steps to reproduce the behavior:

1. In the example code: https://github.com/dmlc/dgl/blob/master/examples/pytorch/graphsage/advanced/train_sampling_unsupervised.py
2. for block in blocks:
print("isolate", block.dstdata[dgl.NID][block.in_degrees()==0])

## Expected behavior

## Environment

- DGL Version (e.g., 1.0): 0.8.1cu101
- Backend Library & Version (e.g., PyTorch 0.4.1, MXNet/Gluon 1.3): PyTorch 1.8.1+cu101
- OS (e.g., Linux): Docker
- How you installed DGL (`conda`, `pip`, source): pip
- Build command you used (if compiling from source):
- Python version: 3.6.13
- CUDA/cuDNN version (if applicable): 101
- GPU models and configuration (e.g. V100): V100
- Any other relevant information:

## Additional context

I have added self loop in my dataset.