Representational Strengths and Limitations of Transformers

Clayton Sanford, Daniel Hsu, Matus Telgarsky

Keywords: self-attention, approximation theory, communication complexity

TL;DR: We give function approximation tasks that demonstrate the advantages of transformers over RNNs and FNNs, the impact of the self-attention embedding dimension on expressivity, and the limitations of any bounded-size layer of self-attention.

Abstract: Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compared with other architectures. In this work we establish both positive and negative results on the representation power of attention layers, with a focus on intrinsic complexity parameters such as width, depth, and embedding dimension. On the positive side, we present a sparse averaging task, where recurrent networks and feedforward networks all have complexity scaling polynomially in the input size, whereas transformers scale merely logarithmically in the input size; furthermore, we use the same construction to show the necessity and role of a large embedding dimension in a transformer. On the negative side, we present a triple detection task, where attention layers in turn have complexity scaling linearly in the input size; as this scenario seems rare in practice, we also present natural variants that can be efficiently solved by attention layers. The proof techniques emphasize the value of communication complexity in the analysis of transformers and related models, and the role of sparse averaging as a prototypical attention task, which even finds use in the analysis of triple detection.

Submission Number: 15514