CLLGAug 6, 2019

Self-Balanced Dropout

arXiv:1908.01968v1
AI Analysis

This addresses a fundamental limitation in dropout for machine learning practitioners, though it appears incremental as it builds directly on existing dropout methods.

The paper tackled the problem of co-adaptation persisting in neural networks despite dropout, by proposing Self-Balanced Dropout, which uses a trainable variable to balance input correlation effects, resulting in significant performance improvements across various tasks.

Dropout is known as an effective way to reduce overfitting via preventing co-adaptations of units. In this paper, we theoretically prove that the co-adaptation problem still exists after using dropout due to the correlations among the inputs. Based on the proof, we further propose Self-Balanced Dropout, a novel dropout method which uses a trainable variable to balance the influence of the input correlation on parameter update. We evaluate Self-Balanced Dropout on a range of tasks with both simple and complex models. The experimental results show that the mechanism can effectively solve the co-adaption problem to some extent and significantly improve the performance on all tasks.

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