benedekrozemberczki/AttentionWalk
A PyTorch Implementation of "Watch Your Step: Learning Node Embeddings via Graph Attention" (NeurIPS 2018).
AttentionWalk helps data scientists or researchers analyze complex network structures, like social media connections or biological interactions. It takes a file listing the connections between entities (like a CSV of who follows whom) and produces a numerical representation for each entity. These representations can then be used to predict missing links, classify nodes, or understand network communities without needing to manually tune complex parameters.
326 stars. No commits in the last 6 months.
Use this if you need to generate high-quality numerical embeddings for nodes in a graph and want an automated way to optimize the underlying model parameters for better performance in tasks like link prediction.
Not ideal if you are looking for a simple graph visualization tool or if you need to analyze the graph structure itself, rather than generating embeddings for downstream machine learning tasks.
Stars
326
Forks
48
Language
Python
License
GPL-3.0
Category
Last pushed
Nov 06, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/benedekrozemberczki/AttentionWalk"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.