Directed graph convolutional network

Z Tong, Y Liang, C Sun, DS Rosenblum… - arXiv preprint arXiv …, 2020 - arxiv.org
… (1) We present a novel graph convolutional networks called the "DGCN", which can be
applied to the directed graphs by utilizing first- and second-order proximity. To our knowledge, …

Motifnet: a motif-based graph convolutional network for directed graphs

F Monti, K Otness, MM Bronstein - 2018 IEEE data science …, 2018 - ieeexplore.ieee.org
… is their explicit assumption of an undirected graph, leading to a symmetric Laplacian matrix
… , a graph CNN capable of dealing with directed graphs by exploiting local graph motifs. We …

Spectral-based graph convolutional network for directed graphs

Y Ma, J Hao, Y Yang, H Li, J Jin, G Chen - arXiv preprint arXiv:1907.08990, 2019 - arxiv.org
directed graph by leveraging redefined Laplacians to improve its propagation model. Our
approach can work directly on directed graph … overfitting in our graph convolutional network. …

Ddgcn: A dynamic directed graph convolutional network for action recognition

M Korban, X Li - Computer Vision–ECCV 2020: 16th European …, 2020 - Springer
… To tackle these issues, we propose an end-to-end Dynamic Directed Graph Convolutional
Network (DDGCN), to recognize human actions on ST graphs. We develop three new …

Scalable graph convolutional networks with fast localized spectral filter for directed graphs

C Li, X Qin, X Xu, D Yang, G Wei - IEEE Access, 2020 - ieeexplore.ieee.org
… In this section, we propose a fast directed graph convolutional network model which is
called FDGCN for semi-supervised node classification. At first, the inspiration of FDGCN is …

A dual-path dynamic directed graph convolutional network for air quality prediction

X Xiao, Z Jin, S Wang, J Xu, Z Peng, R Wang… - Science of The Total …, 2022 - Elsevier
… Using dual-path dynamic directed graph and the GRUs, we propose the dual-path dynamic
gated graph convolutional network (DP-DDGCN) framework to extract the complex dynamic …

A directed graph convolutional neural network for edge-structured signals in link-fault detection

M Kenning, J Deng, M Edwards, X Xie - Pattern Recognition Letters, 2022 - Elsevier
… the edges of graphs. In this paper, we propose the directed graph convolutional neural
network (DGCNN), and describe a simple way to mitigate the inherent class imbalance in graphs. …

Graph convolutional policy network for goal-directed molecular graph generation

J You, B Liu, Z Ying, V Pande… - Advances in neural …, 2018 - proceedings.neurips.cc
… Here we propose Graph Convolutional Policy Network (GCPN), a general graph convolutional
network based model for goaldirected graph generation through reinforcement learning. …

Trajectory forecasting based on prior-aware directed graph convolutional neural network

Y Su, J Du, Y Li, X Li, R Liang, Z Hua… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
… work, we propose a directed graph convolutional network to exploit both the spatial and
temporal information of agents’ trajectories. According to [39], a directed graph topology can be …

Rumor detection on social media with bi-directional graph convolutional networks

T Bian, X Xiao, T Xu, P Zhao, W Huang… - Proceedings of the …, 2020 - ojs.aaai.org
… It leverages a GCN with a top-down directed graph of rumor … • We leverage Graph
Convolutional Networks to detect rumors… with other posts at each graph convolutional layer to …