Pay Attention to MLPs

Code

• github.com/labmlai/annotated_deep_learning_paper_implementations
  pytorch★ 66,103
• github.com/rwightman/pytorch-image-models
  pytorch★ 36,538
• github.com/xmu-xiaoma666/External-Attention-pytorch
  pytorch★ 12,169
• github.com/lucidrains/g-mlp-pytorch
  pytorch★ 430
• github.com/martinsbruveris/tensorflow-image-models
  tf★ 291
• github.com/liuruiyang98/Jittor-MLP
  jax★ 170
• github.com/radi-cho/gatedtabtransformer
  pytorch★ 101
• github.com/lucidrains/g-mlp-gpt
  pytorch★ 89
• github.com/lucidrains/mlp-gpt-jax
  jax★ 59
• github.com/jaketae/g-mlp
  pytorch★ 40

Abstract

Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and show that it can perform as well as Transformers in key language and vision applications. Our comparisons show that self-attention is not critical for Vision Transformers, as gMLP can achieve the same accuracy. For BERT, our model achieves parity with Transformers on pretraining perplexity and is better on some downstream NLP tasks. On finetuning tasks where gMLP performs worse, making the gMLP model substantially larger can close the gap with Transformers. In general, our experiments show that gMLP can scale as well as Transformers over increased data and compute.

Tasks

Benchmark Results

Reproductions