Graph Attention Networks with LSTM-based Path Reweighting

by   Jianpeng Chen, et al.

Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, traditional GNNs suffer from over-smoothing, non-robustness and over-fitting problems. To solve these weaknesses, we design a novel GNN solution, namely Graph Attention Network with LSTM-based Path Reweighting (PR-GAT). PR-GAT can automatically aggregate multi-hop information, highlight important paths and filter out noises. In addition, we utilize random path sampling in PR-GAT for data augmentation. The augmented data is used for predicting the distribution of corresponding labels. Finally, we demonstrate that PR-GAT can mitigate the issues of over-smoothing, non-robustness and overfitting. We achieve state-of-the-art accuracy on 5 out of 7 datasets and competitive accuracy for other 2 datasets. The average accuracy of 7 datasets have been improved by 0.5% than the best SOTA from literature.


page 1

page 2

page 3

page 4


Graph Random Neural Network

Graph neural networks (GNNs) have generalized deep learning methods into...

How Robust Are Graph Neural Networks to Structural Noise?

Graph neural networks (GNNs) are an emerging model for learning graph em...

GNN-Ensemble: Towards Random Decision Graph Neural Networks

Graph Neural Networks (GNNs) have enjoyed wide spread applications in gr...

You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets

Recent works have impressively demonstrated that there exists a subnetwo...

G-Signatures: Global Graph Propagation With Randomized Signatures

Graph neural networks (GNNs) have evolved into one of the most popular d...

A Bird's-Eye Tutorial of Graph Attention Architectures

Graph Neural Networks (GNNs) have shown tremendous strides in performanc...

Estimating Aggregate Properties In Relational Networks With Unobserved Data

Aggregate network properties such as cluster cohesion and the number of ...

Please sign up or login with your details

Forgot password? Click here to reset