完全图高阶关系驱动的链接预测.pdfVIP

计算机研究与发展DOI：10.7544/issn1000-1239.202221045

Journal

of

Computer

Research

and

Development61（7）：1825−1835，2024

完全图高阶关系驱动的链接预测

张惠鹃黄钦阳胡诗彦杨青张敬伟13221

1

（广西可信软件重点实验室（桂林电子科技大学）广西桂林541004）

2

（广西自动检测技术与仪器重点实验室（桂林电子科技大学）广西桂林541004）

3

（桂林电子科技大学计算机与信息安全学院广西桂林541004）

（965727190@）

LinkPredictionDrivenbyHigh-OrderRelationsinCompleteGraph

1

3

2

2

1

Zhang

Huijuan,

Huang

Qinyang,

Hu

Shiyan,

Yang

Qing,

and

Zhang

Jingwei

1

（GuangxiKeyLaboratoryofTrustedSoftware(GuilinUniversityofElectronicTechnology),Guilin,Guangxi541004）

2

（GuangxiKeyLaboratoryofAutomaticDetectingTechnologyandInstruments(GuilinUniversityofElectronicTechnology),Guilin,Guangxi

541004）

3

（SchoolofComputerScienceandInformationSecurity,GuilinUniversityofElectronicTechnology,Guilin,Guangxi541004）

AbstractGraph

convolutional

network

(GCN)

has

been

widely

used

in

recommendation

systems

due

to

its

unique

advantages

in

processing

graph

data.

GCN

propagates

node

attribute

information

by

exploiting

the

dependencies

between

nodes

in

the

graph,

which

greatly

improves

the

accuracy

of

node

representation

and

thus

improves

recommendation

performance.

However,

existing

GCN-based

recommendation

methods

still

have

difficulty

in

modeling

deeper

layers

due

to

the

over-smoothing

problem,

which

limits

the

representation

of

higher-order

relationships

between

users

and

items.

To

this

end,

we

propose

a

novel

link

prediction

method

driven

by

high-order

relations

among

items

in

complete

graph

(short

for

LinkCG).

The

LinkCG

method

utilizes

a

heterogeneous

graph