Multi-behavioral recommendation algorithm based on decoupled graph convolution

doi:10.1016/j.eswa.2025.129618

Return

Multi-behavioral recommendation algorithm based on decoupled graph convolution

2025-09-11

PRE

DOI：10.1016/j.eswa.2025.129618

Original

Original request for help

Save

Abstract

En 中文

• Decoupled graph convolution for multi-behavioral recommendation algorithm design. • Divide a multi-behavioral isomorphic graph into multiple non-overlapping ones. • Decoupled graph convolution and contrastive learning to learn feature representation. • Our model outperforms other state-of-the-art methods.