In a directed graph, an edge is typically represented as an ordered pair of vertices, such as (A, B), which means there is a directed edge from vertex A to vertex B.

"Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition", IJCAI-ECAI 2022 [Paper] [Project] The main novelty of the proposed approach in comparison to ...

This repository provides prototypical implementations of reinforcement learning algorithms and graph-based (multi-agent) environments. We introduce a new environment definition in which not only the ...

Few-shot image classification with graph neural network (GNN) is a hot topic in recent years. Most GNN-based approaches have achieved promising performance. These methods utilize node features or ...

Graph attention, used in GAT and GaAN, assigns weights to nodes based on their importance. ENADPool is a cluster-based hierarchical pooling method that assigns nodes to unique clusters, calculates ...

Graph convolutional networks have been used in machine-learning-based models for power grid applications like voltage estimation for their ability to capture the network topology of the grid. This ...

Few-shot image classification with graph neural network (GNN) is a hot topic in recent years. Most GNN-based approaches have achieved promising performance. These methods utilize node features or ...