-
An end user API should have at least the following points:
- [ ] Patch constructor for each day
- [ ] Node features for each patch
- [ ] Node renumbering, nodes should be numbered $0 \ldots|V|-1$…
-
## Neighbourhood Sampling Module
This issue was created to discuss the API and design goals of the sampling module in `openDG`.
### Design Goals
_Provide efficient sampling primitives over te…
-
How to store and process temporal graph data is a central topic to any temporal graph library. In this project, we aim to store and process both discrete and continuous time dynamic graphs, forming th…
-
Follow up from: https://github.com/shenyangHuang/openDG/issues/2
### High-level Idea
- Drop the maps and put all the core data in a large pre-allocated **sparse** tensor.
- A temporal index for …
-
Hello!
This is an extremely intriguing project. Thank you for building it!
I was curious if there was any benchmarking on cost and latency when it comes to extraction with this tool? Aside from …
-
Hi PyGOD team,
First of all, thank you for the fantastic work you’ve done with PyGOD! It’s an incredibly valuable resource for anomaly detection in graph data, and I truly appreciate the extensive …
-
**Summary**
This paper investigates the relationship between temperature and cherry blossom bloom duration in Japan using a dual model approach. By combining historical and modern data from satellite…
-
https://link.springer.com/article/10.1007/s10844-024-00840-5
-
### What would you like to see?
This is a really cool project! Memory management seems pretty primitive at this stage. I'm one of the authors of [Graphiti](https://github.com/getzep/graphiti), an ope…
-
**Summary**
The paper examines cherry blossom bloom timing in Japan through a dual-model approach. The first model predicts bloom duration based on temperature, while the second estimates temperatu…