Max-Margin DeepWalk: Discriminative Learning of Network Representation
Max-Margin DeepWalk: Discriminative Learning of Network Representation
复制标题
DOI：
--
复制
发表时间：
2016-07
期刊：
影响因子：
--
通讯作者：
Cunchao Tu;Weicheng Zhang;Zhiyuan Liu;Maosong Sun
中科院分区：
文献类型：
--
作者：
Cunchao Tu;Weicheng Zhang;Zhiyuan Liu;Maosong Sun
DeepWalk是一种典型的表示学习方法，它学习社交网络中顶点的低维表示。与其他网络表示学习（NRL）模型类似，它将网络结构编码为顶点表示，并以无监督的形式学习。然而，学习表示通常缺乏歧视的能力时，应用于机器学习任务，如顶点分类。在本文中，我们克服了这一挑战，提出了一种新的半监督模型，最大边缘深度行走（MMDW）。MMDW是一个统一的NRL框架，它联合优化了最大间隔分类器和目标社会表征学习模型。在最大间隔分类器的影响下，学习到的表示不仅包含了网络结构，而且还具有区分性。学习表示的可视化表明，我们的模型比无监督模型更具鉴别力，顶点分类的实验结果表明，我们的方法比其他最先进的方法取得了显着的改善。源代码可以从https://github.com/thunlp/MMDW获得。
DeepWalk is a typical representation learning method that learns low-dimensional representations for vertices in social networks. Similar to other network representation learning (NRL) models, it encodes the network structure into vertex representations and is learnt in unsupervised form. However, the learnt representations usually lack the ability of discrimination when applied to machine learning tasks, such as vertex classification. In this paper, we overcome this challenge by proposing a novel semi-supervised model, max-margin Deep-Walk (MMDW). MMDW is a unified NRL framework that jointly optimizes the max-margin classifier and the aimed social representation learning model. Influenced by the max-margin classifier, the learnt representations not only contain the network structure, but also have the characteristic of discrimination. The visualizations of learnt representations indicate that our model is more discriminative than unsupervised ones, and the experimental results on vertex classification demonstrate that our method achieves a significant improvement than other state-of-the-art methods. The source code can be obtained from https://github.com/thunlp/MMDW.