基于动态嵌入的图编辑距离组合学习
Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
摘要：
图编辑距离（Graph Edit Distance，GED）是一种常用的两两图的相似性度量，它也指从源图到目标图的编辑路径的恢复。传统的A* 算法由于其穷举性质而存在可扩展性问题，其搜索算法严重依赖于人类的先验知识。本文提出了一种混合方法，通过结合传统的基于搜索的技术的可解释性，用于产生编辑路径，以及深度嵌入模型的效率和自适应性，以实现具有成本效益的GED求解器。受动态规划的启发，节点级嵌入以动态重用的方式指定，并鼓励修剪次优分支。为此，我们的方法可以很容易地集成到A* 过程中的一个动态的方式，以及显着减少计算负担与学习的启发式。在不同的图数据集上的实验结果表明，我们的方法可以显着简化A* 的搜索过程，而不会牺牲太多的准确性。据我们所知，这项工作也是第一个基于深度学习的GED方法，用于恢复编辑路径。
英文摘要：
Graph Edit Distance (GED) is a popular similarity measurement for pairwise graphs and it also refers to the recovery of the edit path from the source graph to the target graph. Traditional A* algorithm suffers scalability issues due to its exhaustive nature, whose search heuristics heavily rely on human prior knowledge. This paper presents a hybrid approach by combing the interpretability of traditional search-based techniques for producing the edit path, as well as the efficiency and adaptivity of deep embedding models to achieve a cost-effective GED solver. Inspired by dynamic programming, node-level embedding is designated in a dynamic reuse fashion and suboptimal branches are encouraged to be pruned. To this end, our method can be readily integrated into A* procedure in a dynamic fashion, as well as significantly reduce the computational burden with a learned heuristic. Experimental results on different graph datasets show that our approach can remarkably ease the search process of A* without sacrificing much accuracy. To our best knowledge, this work is also the first deep learning-based GED method for recovering the edit path.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
