Thomas Kipf

Implementation of Graph Convolutional Networks in TensorFlow

The original research code for Graph Convolutional Networks, a machine learning method that classifies nodes in a graph by combining each node's own features with those of its neighbors, includes three citation network datasets to run immediately.

Graph Convolutional Networks in PyTorch

Implementation of Graph Auto-Encoders in TensorFlow

Keras-based implementation of Relational Graph Convolutional Networks

Keras implementation of Graph Convolutional Networks

Contrastive Learning of Structured World Models

CompILE: Compositional Imitation Learning and Execution (ICML 2019)

Python implementation of the Iterative Classification Algorithm

No description.

Neural relational inference for interacting systems - pytorch

Template for building 2D grid worlds with OpenAI Gym and Pycolab

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.