Skip to main content

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

Authors

  • Zhao Chen

  • Jiquan Ngiam

  • Yanping Huang

  • Thang Luong

  • Henrik Kretzschmar
  • Yuning Chai

  • Dragomir Anguelov

    Abstract

    The vast majority of deep models use multiple gradient signals, typically corresponding to a sum of multiple loss terms, to update a shared set of trainable weights. However, these multiple updates can impede optimal training by pulling the model in conflicting directions. We present Gradient Sign Dropout (GradDrop), a probabilistic masking procedure which samples gradients at an activation layer based on their level of consistency. GradDrop is implemented as a simple deep layer that can be used in any deep net and synergizes with other gradient balancing approaches. We show that GradDrop outperforms the state-of-the-art multiloss methods within traditional multitask and transfer learning settings, and we discuss how GradDrop reveals links between optimal multiloss training and gradient stochasticity.