arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.09621cs.LGstat.ML
收藏

深度图匹配共识

Deep Graph Matching Consensus

TU Dortmund University(多特蒙德工业大学);NNAISENSE(NNAISENSE(需确认具体中文译名,此处按原文保留))

Matthias Fey, Jan E. Lenssen, Christopher Morris, Jonathan Masci, Nils M. Kriege

摘要:

这项工作提出了一个两阶段的神经架构,用于学习和细化图之间的结构对应关系。首先,我们使用本地化节点嵌入计算的图神经网络,以获得一个初始的排名节点之间的软对应。其次,我们采用同步消息传递网络迭代重新排序的软对应,以达到匹配的共识,在局部邻域之间的图。我们表明,理论和经验,我们的消息传递计划计算一个有充分依据的措施,相应的社区,然后用于指导迭代重新排序过程的共识。我们的纯本地和稀疏感知架构可以很好地扩展到大型的真实世界输入,同时仍然能够一致地恢复全局对应关系。我们证明了我们的方法在现实世界的任务,从计算机视觉和实体之间的对齐领域的知识图谱,我们改进了当前的最先进的。我们的源代码是在https://github.com/rusty1s/ deep-graph-matching-consensus。

英文摘要:

This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondences between nodes. Secondly, we employ synchronous message passing networks to iteratively re-rank the soft correspondences to reach a matching consensus in local neighborhoods between graphs. We show, theoretically and empirically, that our message passing scheme computes a well-founded measure of consensus for corresponding neighborhoods, which is then used to guide the iterative re-ranking process. Our purely local and sparsity-aware architecture scales well to large, real-world inputs while still being able to recover global correspondences consistently. We demonstrate the practical effectiveness of our method on real-world tasks from the fields of computer vision and entity alignment between knowledge graphs, on which we improve upon the current state-of-the-art. Our source code is available under https://github.com/rusty1s/ deep-graph-matching-consensus.

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。

↑