Login / Signup

ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention.

Yang LiuJiaxiang LiuLi ChenYuxiang LuShikun FengZhida FengYu SunHao TianHua WuHaifeng Wang
Published in: CoRR (2022)
Keyphrases
  • learning tasks
  • multi task
  • sparse learning
  • bayesian networks
  • multi modal
  • multi modality