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 2006.13009cs.LGstat.ML
收藏

图神经网络的迭代深度图学习:更好和鲁棒的节点嵌入

Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings

Rensselaer Polytechnic Institute(伦斯勒理工学院);IBM Research(IBM研究院)

Yu Chen, Lingfei Wu, Mohammed J. Zaki

摘要:

在本文中,我们提出了一个端到端的图学习框架,即迭代深度图学习(IDGL),用于联合迭代地学习图结构和图嵌入。IDGL的关键原理是基于更好的节点嵌入来学习更好的图结构,反之亦然(即,基于更好的图结构的更好的节点嵌入)。我们的迭代法动态停止时,学习的图形结构接近足够接近的图优化的下游预测任务。此外,我们将图学习问题转换为相似性度量学习问题,并利用自适应图正则化来控制学习图的质量。最后,结合基于锚点的近似技术,提出了一种可扩展的IDGL算法IDGL-Anch,在不影响性能的前提下,显著降低了IDGL算法的时间复杂度和空间复杂度.我们对九个基准测试的广泛实验表明,我们提出的IDGL模型可以始终优于或匹配最先进的基线。此外,IDGL可以对对抗图更鲁棒,并且可以处理转导学习和归纳学习。

英文摘要:

In this paper, we propose an end-to-end graph learning framework, namely Iterative Deep Graph Learning (IDGL), for jointly and iteratively learning graph structure and graph embedding. The key rationale of IDGL is to learn a better graph structure based on better node embeddings, and vice versa (i.e., better node embeddings based on a better graph structure). Our iterative method dynamically stops when the learned graph structure approaches close enough to the graph optimized for the downstream prediction task. In addition, we cast the graph learning problem as a similarity metric learning problem and leverage adaptive graph regularization for controlling the quality of the learned graph. Finally, combining the anchor-based approximation technique, we further propose a scalable version of IDGL, namely IDGL-Anch, which significantly reduces the time and space complexity of IDGL without compromising the performance. Our extensive experiments on nine benchmarks show that our proposed IDGL models can consistently outperform or match the state-of-the-art baselines. Furthermore, IDGL can be more robust to adversarial graphs and cope with both transductive and inductive learning.

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。

↑