Yingtong Dou comments

Repositories
Issues
Comments

Results 5 comments of


                                            Yingtong Dou

how to deal this issues?

This problem is related to torch-geometric, you can refer to this [issue](https://github.com/rusty1s/pytorch_geometric/issues/1123#issue-598790822).

Add tutorials for hyperparamer tuning

> Data: https://github.com/d-ailin/GDN Our library is designed for handling anomalies in graph data, we would not consider applying it to time-series data for now.

ICLR2021

There is an alternative [Google Doc](https://docs.google.com/spreadsheets/d/1MLlgV82_4K1FJGSjUKm2R8cw5msn4xmrhtnS9FLAS6k/htmlview?usp=sharing&pru=AAABddfVNaI*DA1De2XqjMs3l8PEbXAMaQ#) for ICLR 2021.

Cannot use GPU when output.shape[1] * nnz(a) > 2^31

You can cast the sparse matrix to dense matrix and use tf.matmul