GEM
pytorch_geometric_temporal
GEM | pytorch_geometric_temporal | |
---|---|---|
1 | 18 | |
1,264 | 2,491 | |
- | - | |
0.0 | 1.8 | |
6 months ago | 20 days ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
GEM
-
[D] Why I'm Lukewarm on Graph Neural Networks
Besides, they implemented a fast C++ version of the code that works for much larger graphs. If one searches for ProNE's implementation, they would (hypothetically) find the scikit-style wrapper instead of the fully-functional release. It reminds me of a situation with HOPE, when authors of one survey "implemented" it as naive SVD (https://github.com/palash1992/GEM/blob/master/gem/embedding/hope.py#L68) instead of Jacobi-Davidson generalized solver described in the paper (and literally with code released!!). In the end, I would assume that poor paper was less cited because of that repackaging effort.
pytorch_geometric_temporal
-
Ask HN: ML Papers to Implement
I have done this a few times now. Alone (e.g. https://github.com/paulmorio/geo2dr) and in collaboration with others (e.g. https://github.com/benedekrozemberczki/pytorch_geometric_tem...) primarily as a way to learn about the methods I was interested in from a research perspective whilst improving my skills in software engineering. I am still learning.
Starting out I would recommend implementing fundamental building blocks within whatever 'subculture' of ML you are interested in whether that be DL, kernel methods, probabilistic models, etc.
Let's say you are interested in deep learning methods (as that's something I could at least speak more confidently about). In that case build yourself an MLP layer, then an RNN layer, then a GNN layer, then a CNN layer, and an attention layer along with some full models with those layers on some case studies exhibiting different data modalities (images, graphs, signals). This should give you a feel for the assumptions driving the inductive biases in each layer and what motivates their existence (vs. an MLP). It also gives you the all the building blocks you can then extend to build every other DL layer+model out there. Another reason is that these fundamental building blocks have been implemented many times so you have a reference to look to when you get stuck.
On that note: here are some fun GNN papers to implement in order of increasing difficulty (try building using vanilla PyTorch/Jax instead of PyG).
- GitHub - benedekrozemberczki/pytorch_geometric_temporal: PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
- PyTorch Geometric Temporal 0.37
- PyTorch Geometric Temporal - Spatiotemporal Signal Processing with Neural Machine Learning Models
- [P] PyTorch Geometric Temporal
- Show HN: Deep Learning for Windmill Output Forecasting with PyTorch
-
[R] PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models
Repo: https://github.com/benedekrozemberczki/pytorch_geometric_temporal
- PyTorch Geometric Temporal 0.27
- Show HN: Machine Learning on Spatiotemporal Data – PyTorch Geometric Temporal
- PyTorch Geometric Temporal
What are some alternatives?
cleora - Cleora AI is a general-purpose model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data.
osmnx - OSMnx is a Python package to easily download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.
sursis - A [personal]<-[notebook]->[network]. Complete with custom numerics for constrained Gaussian gravitation physics.
dgl - Python package built to ease deep learning on graph, on top of existing DL frameworks.
karateclub - Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
torchdrug - A powerful and flexible machine learning platform for drug discovery
node2vec-c - node2vec implementation in C++
graphein - Protein Graph Library
gnn - TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
pytorch_geometric - Graph Neural Network Library for PyTorch
awesome-graph-classification - A collection of important graph embedding, classification and representation learning papers with implementations.
euler - A distributed graph deep learning framework.