Table 3 The impact of user-only Edge Dropout, MLKA and GSAU on the performance of the GR-MC model.

From: A graph neural network recommendation algorithm based on multi-scale attention and contrastive learning

Methods

Movielens-100K

Movielens-1M

Gowalla

Yelp2018

Amazon-book

 

R@20

N@20

R@20

N@20

R@20

N@20

R@20

N@20

Re@20

N@20

GR-MC

0.1646

0.2095

0.2971

0.3380

0.2081

0.1640

0.0731

0.0627

0.0596

0.0462

item-only

0.1627

0.2059

0.2918

0.3302

0.2027

0.1583

0.0695

0.0590

0.0564

0.0425

symmetric

0.1639

0.2056

0.2942

0.3341

0.2049

0.1611

0.0714

0.0608

0.0578

0.0444

w/o MLKA

0.1531

0.1986

0.2884

0.2930

0.1976

0.1568

0.0649

0.0546

0.0473

0.0387

w/o GSAU

0.1593

0.2040

0.2961

0.3012

0.2044

0.1623

0.0682

0.0569

0.0528

0.0431

Back to article page