论文标题
基于端到图的深度半监督学习
End-To-End Graph-based Deep Semi-Supervised Learning
论文作者
论文摘要
图的质量由图的三个关键因素共同确定：节点，边缘和相似度度量（或边缘权重），对于基于图的半监督学习（SSL）方法的成功至关重要。最近，动态图（意味着在训练过程中都会动态更新其所有因素，但已证明对于基于图形的半监督学习是有希望的。但是，现有方法仅更新这三个因素的部分，并在学习阶段手动指定其余部分。在本文中，我们提出了一种基于图形的新型半监督学习方法，以端到端的学习方式同时优化所有三个因素。为此，我们将两个神经网络（功能网络和相似性网络）串联在一起，分别学习分类标签和语义相似性，并训练网络以最大程度地减少统一的SSL目标函数。我们还引入了扩展的图形拉普拉斯正则化项，以提高训练效率。在几个基准数据集上进行的广泛实验证明了我们方法的有效性。
The quality of a graph is determined jointly by three key factors of the graph: nodes, edges and similarity measure (or edge weights), and is very crucial to the success of graph-based semi-supervised learning (SSL) approaches. Recently, dynamic graph, which means part/all its factors are dynamically updated during the training process, has demonstrated to be promising for graph-based semi-supervised learning. However, existing approaches only update part of the three factors and keep the rest manually specified during the learning stage. In this paper, we propose a novel graph-based semi-supervised learning approach to optimize all three factors simultaneously in an end-to-end learning fashion. To this end, we concatenate two neural networks (feature network and similarity network) together to learn the categorical label and semantic similarity, respectively, and train the networks to minimize a unified SSL objective function. We also introduce an extended graph Laplacian regularization term to increase training efficiency. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our approach.
