Rethinking Attention with Performers

TL;DR

Performers introduce a scalable Transformer architecture that approximates softmax attention with linear complexity using a novel kernel approximation method, enabling large-scale applications and detailed kernel comparisons.

Contribution

The paper presents a new linear attention mechanism, FAVOR+, that accurately approximates softmax attention without priors, with strong theoretical guarantees and broad applicability.

Findings

Performers achieve competitive results on diverse tasks.

FAVOR+ efficiently models kernelizable attention mechanisms.

The method offers provable accuracy with linear complexity.

Abstract

We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on any priors such as sparsity or low-rankness. To approximate softmax attention-kernels, Performers use a novel Fast Attention Via positive Orthogonal Random features approach (FAVOR+), which may be of independent interest for scalable kernel methods. FAVOR+ can be also used to efficiently model kernelizable attention mechanisms beyond softmax. This representational power is crucial to accurately compare softmax with other kernels for the first time on large-scale tasks, beyond the reach of regular Transformers, and investigate optimal attention-kernels. Performers are linear architectures fully compatible with regular Transformers and with strong theoretical guarantees: unbiased or nearly-unbiased estimation of the attention matrix, uniform convergence and low estimation variance. We tested Performers on a rich set of tasks stretching from pixel-prediction through text models to protein sequence modeling. We demonstrate competitive results with other examined efficient sparse and dense attention methods, showcasing effectiveness of the novel attention-learning paradigm leveraged by Performers.