Graph Attention Networks with Positional Embeddings

05/09/2021
by   Liheng Ma, et al.
0

Graph Neural Networks (GNNs) are deep learning methods which provide the current state of the art performance in node classification tasks. GNNs often assume homophily – neighboring nodes having similar features and labels–, and therefore may not be at their full potential when dealing with non-homophilic graphs. In this work, we focus on addressing this limitation and enable Graph Attention Networks (GAT), a commonly used variant of GNNs, to explore the structural information within each graph locality. Inspired by the positional encoding in the Transformers, we propose a framework, termed Graph Attentional Networks with Positional Embeddings (GAT-POS), to enhance GATs with positional embeddings which capture structural and positional information of the nodes in the graph. In this framework, the positional embeddings are learned by a model predictive of the graph context, plugged into an enhanced GAT architecture, which is able to leverage both the positional and content information of each node. The model is trained jointly to optimize for the task of node classification as well as the task of predicting graph context. Experimental results show that GAT-POS reaches remarkable improvement compared to strong GNN baselines and recent structural embedding enhanced GNNs on non-homophilic graphs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/15/2022

Incorporating Heterophily into Graph Neural Networks for Graph Classification

Graph neural networks (GNNs) often assume strong homophily in graphs, se...
research
10/06/2022

Geodesic Graph Neural Network for Efficient Graph Representation Learning

Recently, Graph Neural Networks (GNNs) have been applied to graph learni...
research
08/26/2021

Web Image Context Extraction with Graph Neural Networks and Sentence Embeddings on the DOM tree

Web Image Context Extraction (WICE) consists in obtaining the textual in...
research
02/11/2019

Deep Node Ranking: an Algorithm for Structural Network Embedding and End-to-End Classification

Complex networks are used as an abstraction for systems modeling in phys...
research
02/23/2021

Dynamic Labeling for Unlabeled Graph Neural Networks

Existing graph neural networks (GNNs) largely rely on node embeddings, w...
research
09/18/2023

GDM: Dual Mixup for Graph Classification with Limited Supervision

Graph Neural Networks (GNNs) require a large number of labeled graph sam...
research
08/22/2022

NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs

While Graph Neural Networks (GNNs) have demonstrated their efficacy in d...

Please sign up or login with your details

Forgot password? Click here to reset