GraphMLP-Mixer：基于图-多层感知机架构的高效多行为序列推荐方法.pdf

计算机研究与发展DOI：10.7544/issn1000-1239.202440137

Journal

of

Computer

Research

and

Development61（8）：1917−1929，2024

GraphMLP-Mixer：基于图-多层感知机架构的高效多行为序列推荐方法

1,21,2111

卢晓凯封军韩永强王皓陈恩红

1

（认知智能全国重点实验室（中国科学技术大学）合肥230000）

2

（安徽省优质采科技发展有限责任公司合肥230000）

（xiaokailu@）

GraphMLP-Mixer:AGraph-MLPArchitectureforEfficientMulti-Behavior

SequentialRecommendationMethod

1,2

1,2

1

1

1

Lu

Xiaokai,

Feng

Jun,

Han

Yongqiang,

Wang

Hao,

and

Chen

Enhong

1

（StateKeyLaboratoryofCognitiveIntelligence(UniversityofScienceandTechnologyofChina),Hefei230000）

2

（YouZhiCaiScienceandTechnologyDevelopmentCo.,Ltd,Hefei230000）

AbstractIn

the

domain

of

multi-behavior

sequence

recommendation,

Graph

Neural

Networks

(GNNs)

have

been

widespreadly

adopted,

yet

they

have

limitations,

notably

in

terms

of

adequately

modeling

the

collaborative

signals

that

exist

between

different

sequences

and

addressing

the

challenges

posed

by

long-distance

dependencies.

To

bridge

these

gaps,

a

novel

framework

named

GraphMLP-Mixer

has

been

introduced.

This

innovative

framework

begins

by

constructing

a

global

item

graph,

which

is

designed

to

bolster

the

model’s

capacity

to

encapsulate

the

collaborative

signals

that

are

present

across

sequences.

It

then

merges

the

perceptron-mixer

architecture

with

graph

neural

networks,

resulting

in

a

graph-perceptron

mixer

model

capable

of

delving

deep

into

the

intricacies

of

user

interests.

GraphMLP-

Mixer

stands

out

for

its

two

principal

strengths: