There are 10 repositories under graph-embeddings topic.
A curated list of network embedding techniques.
Python library for Representation Learning on Knowledge Graphs https://docs.ampligraph.org
Universal Graph Transformer Self-Attention Networks (TheWebConf WWW 2022) (Pytorch and Tensorflow)
Quaternion Graph Neural Networks (ACML 2021) (Pytorch and Tensorflow)
From Random Walks to Transformer for Learning Node Embeddings (ECML-PKDD 2020) (In Pytorch and Tensorflow)
Code for the paper "Fine-Grained Entity Typing in Hyperbolic Space"
An implementation of the Watset clustering algorithm in Java.
Embedding graphs in symmetric spaces
Code for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)
GyroSPD: Vector-valued Distance and Gyrocalculus on the Space of Symmetric Positive Definite Matrices
The SEMB library is an easy-to-use tool for getting and evaluating structural node embeddings in graphs.
GitHub repositories and users recommendations by embeddings
Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
An implementation of vdist2vec model in paper A Learning Based Approach to Predict Shortest-Path Distances
This repository introduces RezoJDM16K a French Knowledge Graph Dataset with 53 semantic relations created from RezoJDM. Different graph embeddings have gained from this dataset which are available for semantic link prediction task.
Experiments on improving the HinDroid model
Reconstructed GRU, used to process the graph sequence.
Social trust Network Embedding (ICDM 2019)
Code for the Big Data 2019 Paper - Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutions
Terraphim AI: deterministic AI Assistant
:sparkles: Implementation of Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning with pytorch and PyG
We are applying the notion of the spectral radius to NLP and data represented as graphs.
Learning Structural Node Representations using Graph Kernels
learning GNNs
Methods for embedding the structure of graphs into node features.
This package has been made to compare some graph embedding algorithms. The following methods are implemented: Laplacian EigenMaps, Locally Linear Embedding, Higher-Order Proximity preserved Embedding (HOPE), Multi-dimensional scaling of a dissimilarity matrix, Node2vec, Struc2vec, Verse, Singular Value Decomposition of the Adjacency matrix, Kamada-Kawai Layout (KKL), Structural Deep Network Embedding (SDNE)
This repo contains the code and datasets from our paper Learning Stance Embeddings from Signed Social Graphs.
A knowledge graph containing 5 million research papers. Uses: compute Erdős numbers, rank influence of cities on research areas, detect whether researchers with the same name are the same person.
Personal study notes.
Concept embedding and network analysis of scientific innovations emergence
PyTorch implementation of Splitter graph node embeddings