| 基于图注意力和特征融合的链路预测方法 |
| |
| 引用本文： | 李峰,王俊峰,陈虹吕.基于图注意力和特征融合的链路预测方法[J].四川大学学报(自然科学版),2023,60(5):052002-111. |
| |
| 作者姓名： | 李峰 王俊峰 陈虹吕 |
| |
| 作者单位： | 四川大学 计算机学院,四川大学 计算机学院,四川大学 计算机学院 |
| |
| 基金项目： | 基础加强计划重点项目(2019 JCJQ ZD 113)； 国家自然科学基金（U2133208）； 四川省青年科技创新研究团队（2022JDTD0014） |
| |
| 摘 要： | 链路预测是一种还原网络缺失信息的方法，通过当前已观察到的链路，预测实际存在但未被观察到的链路或可能出现的新链路.当前链路预测主要是基于图神经网络的深度学习方法，相比基于规则的启发式方法，前者可有效利用网络拓扑结构信息，较大地提升了网络链路预测性能，并可应用到类型更广泛的网络中.但是现有基于图神经网络的方法，仅利用网络中节点相对位置信息，忽视了节点基本属性和链路的邻居信息，且无法区分不同节点对链路形成的重要程度.为此，本文提出一种基于图注意力网络和特征融合的链路预测方法.通过增加节点的度、链路的共同邻居数量和共同邻居最大度等特征，丰富了网络的输入特征信息.本文首先提取以目标节点对为中心的子图，然后将其转化为对应的线图，线图中的节点和原图中的链路一一对应，从而将原图节点和链路信息融合到线图的节点中，提升了特征融合的有效性和可解释性.同时本文使用图注意力机制学习节点的权重，增强了特征融合的灵活性.实验表明，本文所提出的方法，在多个不同领域数据集上的AUC和AP均超过90%,在已观测链路缺失较多时，预测性能保持80%以上，且均优于现有最新方法.
|
| 关 键 词： | 链路预测 图神经网络 线图 特征融合 图注意力 |
| 收稿时间： | 2022/8/22 0:00:00 |
| 修稿时间： | 2022/11/13 0:00:00 |
Graph Attention based Feature Fusion for Link Prediction |
| |
| LI Feng,WANG Jun-Feng and CHENG Hong-Lv.Graph Attention based Feature Fusion for Link Prediction[J].Journal of Sichuan University (Natural Science Edition),2023,60(5):052002-111. |
| |
| Authors: | LI Feng WANG Jun-Feng and CHENG Hong-Lv |
| |
| Affiliation: | College of Computer Science,Sichuan University,College of Computer Science,Sichuan University,College of Computer Science,Sichuan University |
| |
| Abstract: | Link prediction is a method to restore the missing information of a network by predicting the actual but unobserved links or possible new links from the observed links. Currently, link prediction is mainly based on deep learning methods of graph neural networks, which compared with rule-based heuristics, can effectively utilize the network topology information, greatly improves the performance of network link prediction and can be applied to a wider range of network types. However, the existing graph neural network-based methods only use the relative position information of nodes in the network, ignore the basic attributes of nodes and the neighboring information of links, and cannot distinguish the importance of different nodes to the formation of links. To addess these limitation, this paper proposes a link prediction method based on graph attention network and feature fusion, the input features of the network are enriched by adding features such as the degree of nodes, the number of common neighbors of links and the maximum degree of common neighbors. This method first extracts the subgraph centered on the target node pair, and then transforms it into a corresponding line graph, where the nodes in the line graph correspond to the links in the original graph, thus fusing the nodes and link information of the original graph into the nodes of the line graph, which improves the effectiveness and interpretability of feature fusion. Meanwhile, the proposed method uses the graph attention mechanism to learn the weights of nodes, which enhances the flexibility of feature fusion. Experimental results on various network datasets show that the proposed method achieves over 90% in terms of AUC and AP, outperforming existing state-of-the-art methods. Moreover, the method maintains more than 80% prediction performance even when there are many missing observed links. |
| |
| Keywords: | Link prediction Graph neural network Line graph Feature fusion Graph attention |
|
| 点击此处可从《四川大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《四川大学学报(自然科学版)》下载全文 |
|
