LGMLSep 13, 2020

Manifold attack

arXiv:2009.05965v2
AI Analysis

This addresses regularization challenges in machine learning, particularly for small datasets or large models, but appears incremental as it builds on existing adversarial learning techniques.

The paper tackles the problem of training models with limited data or many parameters by introducing 'manifold attack', a regularization method that enforces manifold preservation from original data to latent representations using adversarial learning, resulting in improved accuracy and robustness to adversarial examples.

Machine Learning in general and Deep Learning in particular has gained much interest in the recent decade and has shown significant performance improvements for many Computer Vision or Natural Language Processing tasks. In order to deal with databases which have just a small amount of training samples or to deal with models which have large amount of parameters, the regularization is indispensable. In this paper, we enforce the manifold preservation (manifold learning) from the original data into latent presentation by using "manifold attack". The later is inspired in a fashion of adversarial learning : finding virtual points that distort mostly the manifold preservation then using these points as supplementary samples to train the model. We show that our approach of regularization provides improvements for the accuracy rate and for the robustness to adversarial examples.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes