HSEGRL：一种分层可自解释的图表示学习模型.pdf

计算机研究与发展DOI：10.7544/issn1000-1239.202440142

Journal

of

Computer

Research

and

Development61（8）：1993−2007，2024

HSEGRL：一种分层可自解释的图表示学习模型

1,21,21,21,311

李平宋舒寒张园曹华伟叶笑春唐志敏

1

（处理器芯片全国重点实验室（中国科学院计算技术研究所）北京100190）

2

（中国科学院大学北京100049）

3

（中国科学院大学南京学院南京211135）

（liping20b@）

HSEGRL:AHierarchicalSelf-ExplainableGraphRepresentationLearningModel

1,2

1,2

1,2

1,3

1

1

Li

Ping,

Song

Shuhan,

Zhang

Yuan,

Cao

Huawei,

Ye

Xiaochun,

and

Tang

Zhimin

1

（StateKeyLabofProcessors(InstituteofComputingTechnology,ChineseAcademyofSciences),Beijing100190）

2

（UniversityofChineseAcademyofSciences,Beijing100049）

3

（UniversityofChineseAcademyofSciences,Nanjing211135）

AbstractIn

recent

years,

with

the

extensive

application

of

graph

neural

network

(GNN)

technology

in

the

fields

such

as

social

network,

information,

chemistry

and

biology,

the

interpretability

of

GNN

has

attracted

widespread

attention.

However,

prevailing

explanation

methods

fail

to

capture

the

hierarchical

explanation

information,

and

these

hierarchical

information

has

not

been

fully

utilized

to

improve

the

classification

accuracy

of

graph

tasks.

To

address

this

issue,

we

propose

a

hierarchical

self-explanation

graph

representation

learning

model

called

HSEGRL

(hierarchical

self-explanation

graph

representation

learning).

This

model,

by

discovering

hierarchical

information

in

the

graph

structure,

predicts

graph

classifications

while

outputting

hierarchical

self-explanation

results.

Specifically,

we

de