pathpyG
pathpyG copied to clipboard
pathpy
GPU-accelerated Next-Generation Network Analytics and Graph Learning for Time Series Data on Complex Networks.
We should perform a systematic analysis of the scalability (both for CPU and GPU-based calculations) for the following features: - [ ] shortest path, centrality and temporal centrality calculations -...
In the current implementation, generating multiple higher-order models for different max. k requires to compute the temporal event graph multiple times, which is the main bottleneck in the computation. For...
Adds SQL-database support via a `read_sql(...)` and `write_sql(...)` function.
I think the current naming scheme of the `pp.io` module is somewhat inconsistent and confusing: - `df_to_graph` is misleading since it does not result in a "proper" graph because the...
## Overview In PathPy3, we had a module `processes` that implemented random walks and other processes like epidemic spreading. There have been some small efforts to migrate the module to...
While testing the updated visualisations on the DBGNN-tutorial notebook, I noticed that `TemporalGraph.to_static_graph()` results in a multigraph with potentially many duplicate edges if `weighted=False`. @IngoScholtes is this the intended behaviour?
- implementation based on preprint WL follows arrow of time