期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 34, 期 12, 页码 10711-10723出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2022.3171199
关键词
Bipartite graph; Training; Message passing; Task analysis; Generative adversarial networks; Electronic commerce; Semantics; Adversarial learning; bipartite graphs; graph neural networks (GNNs); scalable learning; unsupervised learning
This work proposes a layerwise-trained bipartite graph neural network (L-BGNN) embedding method for e-commerce applications, such as recommendation, classification, and link prediction. The method utilizes customized interdomain message passing and intradomain alignment operations to aggregate information in the bipartite graph, and employs a layerwise training algorithm to capture multihop relationships and improve training efficiency.
Learning low-dimensional representations of bipartite graphs enables e-commerce applications, such as recommendation, classification, and link prediction. A layerwise-trained bipartite graph neural network (L-BGNN) embedding method, which is unsupervised, efficient, and scalable, is proposed in this work. To aggregate the information across and within two partitions of a bipartite graph, a customized interdomain message passing (IDMP) operation and an intradomain alignment (IDA) operation are adopted by the proposed L-BGNN method. Furthermore, we develop a layerwise training algorithm for L-BGNN to capture the multihop relationship of large bipartite networks and improve training efficiency. We conduct extensive experiments on several datasets and downstream tasks of various scales to demonstrate the effectiveness and efficiency of the L-BGNN method as compared with state-of-the-art methods. Our codes are publicly available at https://github.com/TianXieUSC/L-BGNN.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据