Daniele Grattarola

spektral. Graph Neural Networks with Keras and Tensorflow 2.

keras-gat. Keras implementation of the graph attention networks (GAT) by Veličković et al. (2017; https://arxiv.org/abs/1710.10903)

twitter-sentiment-cnn. An implementation in TensorFlow of a convolutional neural network (CNN) to perform sentiment classification on tweets.

GNCA. Code for "Learning Graph Cellular Automata" (NeurIPS 2021).

GINR. Code for "Generalised Implicit Neural Representations" (NeurIPS 2022).

SRC. Code for "Understanding Pooling in Graph Neural Networks" (TNNLS 2022).

deep-q-atari. Keras and OpenAI Gym implementation of the Deep Q-learning algorithm to play Atari games.

decimation-pooling. Code for "Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling" (TNNLS 2020).

cdt-ccm-aae. Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds (2018, https://arxiv.org/abs/1805.06299)

danielegrattarola.github.io. My blog

keras-multiplexer. A Keras layer that acts as multiplexer for Dense layers (Tensorflow backend only)

ccm-aae. Adversarial Autoencoders with Constant-Curvature Latent Manifolds (2018, https://arxiv.org/abs/1812.04314)

pncl. Plots in the browser with Python and Chart.js

deepRFS. Deep Feature Extraction for Sample-Efficient Reinforcement Learning