A Multi-Scale Approach for Graph Link Prediction
A Multi-Scale Approach for Graph Link Prediction
复制标题
DOI：
10.1609/aaai.v34i04.5731
复制
发表时间：
2020-04
影响因子：
3.1
通讯作者：
Lei Cai;Shuiwang Ji
中科院分区：
文献类型：
--
作者：
Lei Cai;Shuiwang Ji
经过多尺度信息培训时，可以将深层模型变为不变。鉴于它们的网格样结构，图像可以很容易地制成多尺度。将其扩展到通用图会带来重大挑战。例如，在链接预测任务中，输入表示为由节点和边缘组成的图。当前，链接预测的最新模型使用监督的启发式学习，该学习学习以两个目标节点为中心的图形结构功能。然后，它学习图形神经网络，以根据图结构特征预测链接的存在。因此，链接预测模型的性能高度取决于图形结构特征。在这项工作中，我们提出了一种新型的节点聚合方法，该方法可以将封闭的子图转换为不同的尺度，并保留两个目标节点之间的关系以进行链接预测。还提供了分析重新缩放过程中信息损失的理论。不同尺度的图形可以提供规模不变的信息，这使图形神经网络能够学习不变功能并改善链接预测性能。我们对来自不同领域的14个数据集的实验结果表明，我们所提出的方法通过使用没有其他参数的多尺度图来优于最先进的方法。
Deep models can be made scale-invariant when trained with multi-scale information. Images can be easily made multi-scale, given their grid-like structures. Extending this to generic graphs poses major challenges. For example, in link prediction tasks, inputs are represented as graphs consisting of nodes and edges. Currently, the state-of-the-art model for link prediction uses supervised heuristic learning, which learns graph structure features centered on two target nodes. It then learns graph neural networks to predict the existence of links based on graph structure features. Thus, the performance of link prediction models highly depends on graph structure features. In this work, we propose a novel node aggregation method that can transform the enclosing subgraph into different scales and preserve the relationship between two target nodes for link prediction. A theory for analyzing the information loss during the re-scaling procedure is also provided. Graphs in different scales can provide scale-invariant information, which enables graph neural networks to learn invariant features and improve link prediction performance. Our experimental results on 14 datasets from different areas demonstrate that our proposed method outperforms the state-of-the-art methods by employing multi-scale graphs without additional parameters.