论文标题
模型 - 敏捷的增强，以进行准确的图形分类
Model-Agnostic Augmentation for Accurate Graph Classification
论文作者
论文摘要
给定图数据集，我们如何扩展它以进行准确的图形分类？图表增强是提高基于图的任务的性能的重要策略，并已广泛用于分析网络和社交图。但是，以前用于图形增强的工作要么a）在增强过程中涉及目标模型，失去对其他任务的普遍性，b）依靠导致不可靠结果的简单启发式方法。在这项工作中，我们介绍了五个所需的属性以进行有效的增强。然后，我们提出了Nodesam（节点拆分和合并）和Obsix（子图混合），两种用于图形增强的模型 - 不合时式方法，可以满足所有具有不同动机的所需属性。 Nodesam对图形结构进行了平衡的变化，以最大程度地降低语义变化的风险，而Obsix则混合了多个图的随机子图，以创建丰富的软标签，结合了不同类别的证据。我们在社交网络和分子图上进行的实验表明，Nodesam和Submix在图形分类中的表现优于现有方法。
Given a graph dataset, how can we augment it for accurate graph classification? Graph augmentation is an essential strategy to improve the performance of graph-based tasks, and has been widely utilized for analyzing web and social graphs. However, previous works for graph augmentation either a) involve the target model in the process of augmentation, losing the generalizability to other tasks, or b) rely on simple heuristics that lead to unreliable results. In this work, we introduce five desired properties for effective augmentation. Then, we propose NodeSam (Node Split and Merge) and SubMix (Subgraph Mix), two model-agnostic approaches for graph augmentation that satisfy all desired properties with different motivations. NodeSam makes a balanced change of the graph structure to minimize the risk of semantic change, while SubMix mixes random subgraphs of multiple graphs to create rich soft labels combining the evidence for different classes. Our experiments on social networks and molecular graphs show that NodeSam and SubMix outperform existing approaches in graph classification.
