LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification
This work addresses the need for efficient semi-supervised learning to reduce reliance on large labeled datasets, which is costly and time-consuming, though it appears incremental as it builds on existing graph and neural network techniques.
The authors tackled the problem of deep semi-supervised classification by proposing LaplaceNet, a hybrid graph-energy neural network that reduces model complexity and outperforms state-of-the-art methods on several benchmark datasets.
Semi-supervised learning has received a lot of recent attention as it alleviates the need for large amounts of labelled data which can often be expensive, requires expert knowledge and be time consuming to collect. Recent developments in deep semi-supervised classification have reached unprecedented performance and the gap between supervised and semi-supervised learning is ever-decreasing. This improvement in performance has been based on the inclusion of numerous technical tricks, strong augmentation techniques and costly optimisation schemes with multi-term loss functions. We propose a new framework, LaplaceNet, for deep semi-supervised classification that has a greatly reduced model complexity. We utilise a hybrid approach where pseudolabels are produced by minimising the Laplacian energy on a graph. These pseudo-labels are then used to iteratively train a neural-network backbone. Our model outperforms state-of-the art methods for deep semi-supervised classification, over several benchmark datasets. Furthermore, we consider the application of strong-augmentations to neural networks theoretically and justify the use of a multi-sampling approach for semi-supervised learning. We demonstrate, through rigorous experimentation, that a multi-sampling augmentation approach improves generalisation and reduces the sensitivity of the network to augmentation.