Apr 1, 2021 · We propose a novel Graph Autoencoder structure, MIAGAE, which achieves state-of-the-art performance on graph compression and representation learning tasks.

This repository contains an implementation of the models introduced in the paper Graph Autoencoder for Graph Compression and Representation Learning by Ge et al. The model …

Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective …

In this paper, we propose an auto graph encoder-decoder model compression (AGMC) method combined with graph neural networks (GNN) and reinforce-ment learning (RL) to find the best …

Apr 27, 2022 · The proposed architecture, named Autoencoder-Aided GCN (AA-GCN), compresses the convolutional features in an information-rich embedding at multiple hidden …

To fill this gap, we propose Multi-kernel Inductive Attention Graph Autoencoder (MIAGAE), which, instead of compressing nodes/edges separately, utilizes the node similarity and graph …

Graph Generation: Given a set of example graphs, we can use a graph autoencoder to learn a compressed representation of the graphs that captures their most important features. We can …

6 days ago · propose a dual-decoder graph autoencoder model (DGAE) for unsupervised graph representation learning, which encode the graph structure and node attributes with a GCNs, …

Attention Graph Autoencoder (MIAGAE), a GAE structure with GNN for graph compression and graph representation learning (Hamilton et al., 2017b; Goyal & Ferrara, 2018) (Fig. 1). …

To fill this gap, we propose Multi-kernel Inductive Attention Graph Autoencoder (MIAGAE), which, instead of compressing nodes/edges separately, utilizes the node similarity and graph …