Skip to yearly menu bar Skip to main content

Workshop: The Symbiosis of Deep Learning and Differential Equations II

A Neural ODE Interpretation of Transformer Layers

Yaofeng Zhong · Tongtao Zhang · Amit Chakraborty · Biswadip Dey


Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections to avoid the problem of vanishing gradients, they can be viewed as the numerical integration of a differential equation. In this extended abstract, we build upon this connection and propose a modification of the internal architecture of a transformer layer. The proposed model places the multi-head attention sublayer and the MLP sublayer parallel to each other. Our experiments show that this simple modification improves the performance of transformer networks in multiple tasks. Moreover, for the image classification task, we show that using neural ODE solvers with a sophisticated integration scheme further improves performance.

Chat is not available.