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 2407.01194cs.LG
收藏

一种基于学习的广义测地距离函数的图节点特征增强方法

A Learned Generalized Geodesic Distance Function-Based Approach for Node Feature Augmentation on Graphs

Singapore Management University(新加坡管理大学)

Amitoz Azad, Yuan Fang

AI总结:

本文提出LGGD方法,通过结合训练数据、图拓扑和节点内容特征学习广义测地距离函数来生成图节点特征,提升了节点分类性能并证明了参数可学习性。

摘要:

流形上的测地距离在图像处理、计算机图形学和计算机视觉中有大量应用。在本研究中,我们引入了一种名为LGGD(Learned Generalized Geodesic Distances)的方法。该方法通过一个结合训练数据、图拓扑和节点内容特征的训练管道来学习广义测地距离函数,从而生成节点特征。该方法的优势在于广义测地距离对噪声和异常值具有已被证明的鲁棒性。我们的贡献包括:提升了节点分类任务的性能,在真实图数据集上取得了与最先进方法相媲美的结果,证明了图上广义测地方程中参数的可学习性,以及动态纳入新标签的能力。

英文摘要:

Geodesic distances on manifolds have numerous applications in image processing, computer graphics and computer vision. In this work, we introduce an approach called `LGGD' (Learned Generalized Geodesic Distances). This method involves generating node features by learning a generalized geodesic distance function through a training pipeline that incorporates training data, graph topology and the node content features. The strength of this method lies in the proven robustness of the generalized geodesic distances to noise and outliers. Our contributions encompass improved performance in node classification tasks, competitive results with state-of-the-art methods on real-world graph datasets, the demonstration of the learnability of parameters within the generalized geodesic equation on graph, and dynamic inclusion of new labels.

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。

↑