Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning
Improving the accuracy and robustness of deep neural nets (DNNs) and adapting them to small training data are primary tasks in deep learning (DL) research. In this paper, we replace the output activation function of DNNs, typically the data-agnostic softmax function, with a graph Laplacian-based high-dimensional interpolating function which, in the continuum limit, converges to the solution of a Laplace–Beltrami equation on a high-dimensional manifold. Furthermore, we propose end-to-end training and testing algorithms for this new architecture. The proposed DNN with graph interpolating activation integrates the advantages of both deep learning and manifold learning. Compared to the conventional DNNs with the softmax function as output activation, the new framework demonstrates the following major advantages: First, it is better applicable to data-efficient learning in which we train high capacity DNNs without using a large number of training data. Second, it remarkably improves both natural accuracy on the clean images and robust accuracy on the adversarial images crafted by both white-box and black-box adversarial attacks. Third, it is a natural choice for semi-supervised learning. This paper is a significant extension of our earlier work published in NeurIPS, 2018. For reproducibility, the code is available athttps://github.com/BaoWangMath/DNN-DataDependentActivation.
- Research Organization:
- Purdue Univ., West Lafayette, IN (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC)
- DOE Contract Number:
- SC0021142
- OSTI ID:
- 1853729
- Journal Information:
- European Journal of Applied Mathematics, Vol. 32, Issue 3; ISSN 0956-7925
- Publisher:
- Cambridge University Press
- Country of Publication:
- United States
- Language:
- English
Similar Records
Towards automating structural discovery in scanning transmission electron microscopy *
ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense