Position encoding for heterogeneous graph neural networks

Xi Zeng; Qingyun Dai; Fangyuan Lei

doi:10.1117/12.2639209

21 July 2022 Position encoding for heterogeneous graph neural networks

Xi Zeng, Qingyun Dai, Fangyuan Lei

Proceedings Volume 12258, International Conference on Neural Networks, Information, and Communication Engineering (NNICE 2022); 1225805 (2022) https://doi.org/10.1117/12.2639209
Event: International Conference on Neural Networks, Information, and Communication Engineering (NNICE 2022), 2022, Qingdao, China

Abstract

Many real-world networks are suitable to be modeled as heterogeneous graphs, which are made up of many sorts of nodes and links. When the heterogeneous map is a non-attribute graph or some features on the graph are missing, it will lead to poor performance of the previous models. In this paper, we hold that useful position features can be generated through the guidance of topological information on the graph and present a generic framework for Heterogeneous Graph Neural Networks(HGNNs), termed Position Encoding(PE). First of all, PE leverages existing node embedding methods to obtain the implicit semantics on a graph and generate low-dimensional node embedding. Secondly, for each task-related target node, PE generates corresponding sampling subgraphs, in which we use node embedding to calculate the relative positions and encode the positions into position features that can be used directly or as an additional feature. Then the set of subgraphs with position features can be easily combined with the desired Graph Neural Networks (GNNs) or HGNNs to learn the representation of target nodes. We evaluated our method on graph classification tasks over three commonly used heterogeneous graph datasets with two processing ways, and experimental results show the superiority of PE over baselines.

Citation Download Citation

Xi Zeng, Qingyun Dai, and Fangyuan Lei "Position encoding for heterogeneous graph neural networks", Proc. SPIE 12258, International Conference on Neural Networks, Information, and Communication Engineering (NNICE 2022), 1225805 (21 July 2022); https://doi.org/10.1117/12.2639209

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available