arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.04527cs.LG
收藏

LaplaceNet:一种用于深度半监督分类的混合图能量神经网络

LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification

Philip Sellars, Angelica I. Aviles-Rivero, Carola-Bibiane Schönlieb

摘要:

半监督学习近年来受到了广泛的关注,因为它需要大量的标记数据,这些数据通常是昂贵的,需要专家知识并且收集起来很耗时。最近在深度半监督分类方面的发展已经达到了前所未有的性能,监督学习和半监督学习之间的差距正在不断缩小。这种性能上的改进是基于包括许多技术技巧、强增强技术和具有多项损失函数的昂贵优化方案。我们提出了一个新的框架,LaplaceNet,深度半监督分类,大大降低了模型的复杂性。我们利用一种混合的方法,其中伪标签通过最小化图上的拉普拉斯能量来产生。这些伪标签然后被用于迭代地训练神经网络骨干。在几个基准数据集上,我们的模型优于最先进的深度半监督分类方法。此外,我们认为强增广神经网络的应用理论和证明使用多采样方法的半监督学习。我们证明,通过严格的实验,多采样增强方法提高了泛化能力,降低了网络对增强的敏感性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑