End-To-End Graph-based Deep Semi-Supervised Learning
arXiv:2002.09891
Abstract
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.
5 figures, 6 tables
References in corpus (11)
- Interpolation Consistency Training for Semi-Supervised Learning
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
- Semi-Supervised Learning with Generative Adversarial Networks
- Good Semi-supervised Learning that Requires a Bad GAN
- Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
- Learning by Association - A versatile semi-supervised training method for neural networks
- Semi-Supervised Learning via Compact Latent Space Clustering