Add tutorials for hyperparamer tuning about pygod HOT 4 CLOSED

Hi there, thanks for posting this. One thing to note is unsupervised models, especially anomaly detection algorithms, are notoriously hard to tune. We have some recent works in this direction for unsupervised outlier model selection/tuning [1], while it is still unclear how to do this deep models like GNNs.

You are welcome to propose or bring some new ideas for this. Let us whether we could work something out together. Thanks

[1] Zhao, Y., Rossi, R. and Akoglu, L., 2021. Automatic Unsupervised Outlier Model Selection. Advances in Neural Information Processing Systems, 34.

from pygod.

Hi, thankyou for the response.

Aa a start I am planning to use it for time series data.

Data: https://github.com/d-ailin/GDN

from pygod.

Hi, thankyou for the response.

Aa a start I am planning to use it for time series data.

Data: https://github.com/d-ailin/GDN

Let me know if this works

from pygod.

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.

from pygod.