NLP

Luna: Linear Unified Nested Attention

October 26, 2021

Abstract

The quadratic computational and memory complexities of the Transformer’s at-tention mechanism have limited its scalability for modeling long sequences. Inthis paper, we propose Luna, a linear unified nested attention mechanism thatapproximates softmax attention withtwo nested linear attention functions, yieldingonly linear (as opposed to quadratic) time and space complexity. As compared toa more traditional attention mechanism, Luna introduces an additional sequencewith a fixed length as input and an additional corresponding output, which allowsLuna to perform attention operation linearly, while also storing adequate contextualinformation. We perform extensive evaluations on three benchmarks of sequencemodeling tasks: long-context sequence modeling, neural machine translation andmasked language modeling for large-scale pretraining. Competitive or even betterexperimental results demonstrate both the effectiveness and efficiency of Lunacompared to a variety of strong baseline methods including the full-rank attentionand other efficient sparse and dense attention methods. The implementation of ourmodel is available at https://github.com/XuezheMax/fairseq-apollo

Download the Paper

AUTHORS

Written by

Xuezhe Ma

Xiang Kong

Sinong Wang

Chunting Zhou

Jonathan May

Hao Ma

Luke Zettlemoyer

Publisher

NeurIPS

Related Publications

November 16, 2022

RESEARCH

NLP

Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models

Kushal Tirumala, Aram H. Markosyan, Armen Aghajanyan, Luke Zettlemoyer

November 16, 2022

October 31, 2022

NLP

ML APPLICATIONS

AD-Drop: Attribution Driven Dropout for Robust Language Model Finetuning

Qifan Wang, Shaoliang Nie, Jinghao Deng, Tao Yang, Xiaojun Quan

October 31, 2022

October 31, 2022

RESEARCH

NLP

Autoregressive Search Engines: Generating Substrings as Document Identifiers

Fabio Petroni, Giuseppe Ottaviano, Michele Bevilacqua, Patrick Lewis, Scott Yih, Sebastian Riedel

October 31, 2022

July 07, 2022

NLP

CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training

Xilun Chen, Armen Aghajanyan, Barlas Oguz, Scott Yih, Sonal Gupta, Patrick Huber

July 07, 2022

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.