Out-of-Distribution Node Detection Based on Graph Heat Kernel Diffusion

Over the past few years, there has been a surge in research attention towards tasks involving graph data, largely due to the impressive performance demonstrated by graph neural networks (GNNs) in handling such information. Currently, out-of-distribution (OOD) detection in graphs is a hot research to...

Full description

Saved in:
Bibliographic Details
Main Authors: Fangfang Li, Yangshuai Wang, Xinyu Du, Xiaohua Li, Ge Yu
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/18/2942
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260375012900864
author Fangfang Li
Yangshuai Wang
Xinyu Du
Xiaohua Li
Ge Yu
author_facet Fangfang Li
Yangshuai Wang
Xinyu Du
Xiaohua Li
Ge Yu
author_sort Fangfang Li
collection DOAJ
description Over the past few years, there has been a surge in research attention towards tasks involving graph data, largely due to the impressive performance demonstrated by graph neural networks (GNNs) in handling such information. Currently, out-of-distribution (OOD) detection in graphs is a hot research topic. The goal of graph OOD detection is to identify nodes or new graphs that differ from the training data distribution, primarily in terms of attributes and structures. OOD detection is crucial for enhancing the stability, security, and robustness of models. In various applications, such as biological networks and financial fraud, graph OOD detection can help models identify anomalies or unforeseen situations, thereby enabling appropriate responses. In node-level OOD detection, existing models typically only consider first-order neighbors. This paper introduces graph diffusion to the OOD detection task for the first time, proposing the HOOD model, a graph diffusion-based OOD node detection algorithm. Specifically, the original graph is processed through graph diffusion to obtain a new graph that can directly capture high-order neighbor information, overcoming the limitation that message passing must go through first-order neighbors. The new graph is then sparsified using a top-k approach. Based on entropy information, regularization is employed to ensure the uncertainty of OOD nodes, thereby giving these nodes higher scores and enabling the model to effectively detect OOD nodes while ensuring the accuracy of in-distribution node classification. Experimental results demonstrate that the HOOD model outperforms existing methods in both node classification and OOD detection tasks on multiple benchmarks, highlighting its robustness and effectiveness.
format Article
id doaj-art-cab56f4fe97141d8bd7734476dbeae92
institution OA Journals
issn 2227-7390
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-cab56f4fe97141d8bd7734476dbeae922025-08-20T01:55:38ZengMDPI AGMathematics2227-73902024-09-011218294210.3390/math12182942Out-of-Distribution Node Detection Based on Graph Heat Kernel DiffusionFangfang Li0Yangshuai Wang1Xinyu Du2Xiaohua Li3Ge Yu4School of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaOver the past few years, there has been a surge in research attention towards tasks involving graph data, largely due to the impressive performance demonstrated by graph neural networks (GNNs) in handling such information. Currently, out-of-distribution (OOD) detection in graphs is a hot research topic. The goal of graph OOD detection is to identify nodes or new graphs that differ from the training data distribution, primarily in terms of attributes and structures. OOD detection is crucial for enhancing the stability, security, and robustness of models. In various applications, such as biological networks and financial fraud, graph OOD detection can help models identify anomalies or unforeseen situations, thereby enabling appropriate responses. In node-level OOD detection, existing models typically only consider first-order neighbors. This paper introduces graph diffusion to the OOD detection task for the first time, proposing the HOOD model, a graph diffusion-based OOD node detection algorithm. Specifically, the original graph is processed through graph diffusion to obtain a new graph that can directly capture high-order neighbor information, overcoming the limitation that message passing must go through first-order neighbors. The new graph is then sparsified using a top-k approach. Based on entropy information, regularization is employed to ensure the uncertainty of OOD nodes, thereby giving these nodes higher scores and enabling the model to effectively detect OOD nodes while ensuring the accuracy of in-distribution node classification. Experimental results demonstrate that the HOOD model outperforms existing methods in both node classification and OOD detection tasks on multiple benchmarks, highlighting its robustness and effectiveness.https://www.mdpi.com/2227-7390/12/18/2942out-of-distributiongraph diffusionregularizationgraph neural network
spellingShingle Fangfang Li
Yangshuai Wang
Xinyu Du
Xiaohua Li
Ge Yu
Out-of-Distribution Node Detection Based on Graph Heat Kernel Diffusion
Mathematics
out-of-distribution
graph diffusion
regularization
graph neural network
title Out-of-Distribution Node Detection Based on Graph Heat Kernel Diffusion
title_full Out-of-Distribution Node Detection Based on Graph Heat Kernel Diffusion
title_fullStr Out-of-Distribution Node Detection Based on Graph Heat Kernel Diffusion
title_full_unstemmed Out-of-Distribution Node Detection Based on Graph Heat Kernel Diffusion
title_short Out-of-Distribution Node Detection Based on Graph Heat Kernel Diffusion
title_sort out of distribution node detection based on graph heat kernel diffusion
topic out-of-distribution
graph diffusion
regularization
graph neural network
url https://www.mdpi.com/2227-7390/12/18/2942
work_keys_str_mv AT fangfangli outofdistributionnodedetectionbasedongraphheatkerneldiffusion
AT yangshuaiwang outofdistributionnodedetectionbasedongraphheatkerneldiffusion
AT xinyudu outofdistributionnodedetectionbasedongraphheatkerneldiffusion
AT xiaohuali outofdistributionnodedetectionbasedongraphheatkerneldiffusion
AT geyu outofdistributionnodedetectionbasedongraphheatkerneldiffusion