邻接矩阵
计算机科学
判别式
图形
邻接表
人工智能
理论计算机科学
模式识别(心理学)
数据挖掘
算法
作者
Luying Zhong,Jielong Lu,Zhaoliang Chen,Na Song,Shiping Wang
标识
DOI:10.1016/j.ins.2023.120012
摘要
The domain of multi-view semi-supervised classification is an appealing topic in real-world applications. Due to the powerful capability of gathering information from neighbors, Graph Convolutional Network (GCN) has become a hotspot in the classification task. However, most of multi-view classification works based on GCN only assign weights for feature fusion, and directly consider the weighted sum of the adjacency matrices, ignoring the interaction and correlation among features. These may be problematic since aggregating the matrices from less relevant views may destroy the original topology space, leading to undesired performance. To tackle the aforementioned challenges, this paper presents an Adaptive Multi-Channel Graph Convolutional Network (AMC-GCN). To extract the interactive information, AMC-GCN designs a deep interactive feature integration network to incorporate consensus and complementary information. To fuse the graph structures, AMC-GCN exploits the relevance between views and imposes an adjacency matrix fusion network on constructing multiple GCN channels, thereby delivering discriminative information on graphs. To enhance the homogeneity of the framework, AMC-GCN applies a contrastive loss to joint learning during the optimization for classification. With these considerations, AMC-GCN exploits relevant and interactive information between views to promote graph and feature fusion. Substantial experimental results on real-world datasets verify the superiority of AMC-GCN.
科研通智能强力驱动
Strongly Powered by AbleSci AI