SocNL: Bayesian Label Propagation with Confidence
SocNL: Bayesian Label Propagation with Confidence
复制标题
DOI：
10.1007/978-3-319-18038-0_49
复制
发表时间：
2015-05
期刊：
影响因子：
--
通讯作者：
Yuto Yamaguchi;C. Faloutsos;H. Kitagawa
中科院分区：
文献类型：
--
作者：
Yuto Yamaguchi;C. Faloutsos;H. Kitagawa
如果我们知道史密斯朋友的主要爱好，我们如何预测史密斯的主要爱好？如果我们只知道斯密的几个朋友的主要爱好，我们能测量出预测的可信度吗？本文主要研究如何估计节点分类问题的置信度。为分类问题提供一个置信度是很重要的，因为现实世界网络中的大多数节点往往只有很少的邻居，因此只有少量的证据。我们的贡献有三个方面：(a)新颖的算法；提出了一种收敛速度快的半监督学习算法，并给出了置信度估计(b)理论分析；我们展示了我们算法的坚实理论基础以及与标签传播和贝叶斯推理的联系(c)经验分析；我们在三个不同的真实网络上进行了广泛的实验。具体而言，实验结果表明，我们的算法在平滑度较低和标签密度较低的图上优于其他算法。
How can we predict Smith’s main hobby if we know the main hobby of Smith’s friends? Can we measure the confidence in our prediction if we are given the main hobby of only a few of Smith’s friends? In this paper, we focus on how to estimate the confidence on the node classification problem. Providing a confidence level for the classification problem is important because most nodes in real world networks tend to have few neighbors, and thus, a small amount of evidence. Our contributions are three-fold: (a)novel algorithm; we propose a semi-supervised learning algorithm that converges fast, and provides the confidence estimate (b)theoretical analysis; we show the solid theoretical foundation of our algorithm and the connections to label propagation and Bayesian inference (c)empirical analysis; we perform extensive experiments on three different real networks. Specifically, the experimental results demonstrate that our algorithm outperforms other algorithms on graphs with less smoothness and low label density.