graph-attention-networks

A collection of important graph embedding, classification and representation learning papers with implementations.

Graph Attention Networks (https://arxiv.org/abs/1710.10903)

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

#计算机科学#My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy...

#计算机科学#A PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).

PyTorch Implementation and Explanation of Graph Representation Learning papers: DeepWalk, GCN, GraphSAGE, ChebNet & GAT.

KGAT: Knowledge Graph Attention Network for Recommendation, KDD2019

#自然语言处理#resources for graph convolutional networks （图卷积神经网络相关资源）

#计算机科学#Keras implementation of the graph attention networks (GAT) by Veličković et al. (2017; https://arxiv.org/abs/1710.10903)

#计算机科学#An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

#计算机科学#Free hands-on course about Graph Neural Networks using PyTorch Geometric.

#计算机科学#PyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).

Code for the paper "How Attentive are Graph Attention Networks?" (ICLR'2022)

DeepInf: Social Influence Prediction with Deep Learning

#计算机科学#A Unified Library for Deep Graph Clustering

[ICDE'2023] When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks

#计算机科学#A Context-aware Visual Attention-based training pipeline for Object Detection from a Webpage screenshot!

#自然语言处理#ECML 2019: Graph Neural Networks for Multi-Label Classification

PyTorch code for ICPR 2020 paper "DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting"

[ICDE2023] A PyTorch implementation of Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics Framework (START).