Kaiwen Dong

icon indicating an email [email protected]

icon company University of Notre Dame icon location Notre Dame, IN icon location Actually the success of all Machine Learning algorithms depends on how you present the data

Results 3 comments of Kaiwen Dong

When headless=True, Browser-Use does not follow my prompt correctly; the same prompt runs correctly when headless=False.

I also got this warning when using headless mode. Is it related to the headless mode only? ``` Unclosed client session client_session: Unclosed connector connections: ['deque([(, 968953.797247469)])'] connector: ```

NeighborSampler samples different nodes with disjoint=True and False

Thanks for your reply. However, the sampling seems to be more consistent on homogeneous data. Is that also expected somehow on heterogeneous data?

NeighborSampler samples different nodes with disjoint=True and False

If we sample on homogeneous graph, the sampled data for either disjoint=True or False will be the same. To reproduce, running `python disjoint.py --disjoint=0 --heter=0` and `python disjoint.py --disjoint=1 --heter=0`...