基于自注意力网络的深度图匹配模型

现有深度图匹配模型在节点特征提取阶段常利用图卷积网络(GCN)学习节点的特征表示。然而,GCN对节点特征的学习能力有限,影响了节点特征的可区分性,造成节点的相似性度量不佳,最终导致模型的匹配精度受损。为解决这一问题,提出一种基于自注意力网络的深度图匹配模型。所提模型在节点特征提取阶段使用新的自注意力网络来学习节点特征,其原理是通过空间编码器和自注意力机制分别学习节点的空间结构以及所有节点之间的联系,从而改善节点的特征描述。此外,为了减小放松图匹配问题所带来的精度损失,将图匹配问题建模为整数线性规划问题,在图匹配问题的节点匹配基础上增加结构匹配约束,以及引入高效的组合优化求解器来计算图匹配问题的局部最优解。实验结果表明,在PASCALVOC数据集上,与PCA-GM相比,所提模型在20类图像上的匹配精度平均值提高了14.8个百分点;在Willow Object数据集上,所提模型在5类图像上的匹配精度平均值提高了7.3个百分点,并且在自行车、植物等目标匹配任务上达到了最佳的效果。

A Study on Short Text Matching Method Based on KS-BERT Algorithm

To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input text.Finally,the match was determined based on the fusion result of the two features.Experiment results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE 2.0.This Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text matching.In BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.