Tuformer: Data-driven Design of Transformers for Improved Generalization or EfficiencyDownload PDF

29 Sept 2021, 00:32 (edited 24 Mar 2022)ICLR 2022 PosterReaders: Everyone
  • Keywords: Attention Modules, Transformers, Data-driven Model Design, Trainable Heads, Expressive Power, Tensor Methods.
  • Abstract: Transformers are neural network architectures that achieve remarkable performance in many areas. However, the core component of Transformers, multi-head self-attention (MHSA), is mainly derived from heuristics, and the interactions across its components are not well understood. To address the problem, we first introduce a mathematically rigorous and yet intuitive tensor diagram representation of MHSA. Guided by tensor diagram representations, we propose a novel design, namely Tunable Transformers (Tuformers), by allowing data-driven weights across heads, whereas MHSA adopts pre-defined and fixed weights across heads, as will be explained in our paper. Tuformers naturally reveal a flexible design space that a user, depending on the needs, can choose a structure that has either improved performance (generalization error) or higher model efficiency. Any pre-trained Transformer can be an initialization of the corresponding Tuformer with trainable number of heads for efficient training and fine-tuning. Tuformers universally outperform Transformers on various tasks across multiple domains under a wide range of model sizes.
  • One-sentence Summary: We propose Tuformer, a data-driven design of theoretically guaranteed expressive Transformer with trainable heads, inspired by Tucker tensor representation.
  • Supplementary Material: zip
22 Replies

Loading