wondergo2017/sild
Implementation codes for NeurIPS23 paper "Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts"
This project helps data scientists and researchers working with evolving network data make more accurate predictions. It takes dynamic graph datasets, which show how connections and nodes change over time, and processes them to identify stable underlying patterns. The output is a more robust prediction model for tasks like classifying nodes or predicting new connections, even when the network's behavior shifts unexpectedly.
No commits in the last 6 months.
Use this if you need to build predictive models on networks that change over time, and your current models struggle with unexpected shifts or new trends in the network structure.
Not ideal if your data is a static graph with no temporal changes, or if you are not comfortable working with Python and machine learning frameworks like PyTorch.
Stars
14
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/wondergo2017/sild"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
siapy/siapy-lib
🥷 A Python package for efficient processing of spectral images
yueliu1999/Awesome-Deep-Graph-Clustering
Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods...
Tony607/Keras_Deep_Clustering
How to do Unsupervised Clustering with Keras
bourdakos1/CapsNet-Visualization
🎆 A visualization of the CapsNet layers to better understand how it works
loretoparisi/CapsNet
CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art