SOTAVerified

Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention

2021-02-07Code Available1· sign in to hype

Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, Vikas Singh

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the self-attention mechanism that encodes the influence or dependence of other tokens on each specific token. While beneficial, the quadratic complexity of self-attention on the input sequence length has limited its application to longer sequences -- a topic being actively studied in the community. To address this limitation, we propose Nystr\"omformer -- a model that exhibits favorable scalability as a function of sequence length. Our idea is based on adapting the Nystr\"om method to approximate standard self-attention with O(n) complexity. The scalability of Nystr\"omformer enables application to longer sequences with thousands of tokens. We perform evaluations on multiple downstream tasks on the GLUE benchmark and IMDB reviews with standard sequence length, and find that our Nystr\"omformer performs comparably, or in a few cases, even slightly better, than standard self-attention. On longer sequence tasks in the Long Range Arena (LRA) benchmark, Nystr\"omformer performs favorably relative to other efficient self-attention methods. Our code is available at https://github.com/mlpen/Nystromformer.

Tasks

Natural Language InferenceQuestion AnsweringSemantic Textual SimilaritySentiment Analysis

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
QNLINyströmformerAccuracy88.7—Unverified

Reproductions