Neural Shuffle-Exchange Networks -- Sequence Processing in O(n log n) Time

Abstract

A key requirement in sequence to sequence processing is the modeling of long range dependencies. To this end, a vast majority of the state-of-the-art models use attention mechanism which is of O($n^2$) complexity that leads to slow execution for long sequences. We introduce a new Shuffle-Exchange neural network model for sequence to sequence tasks which have O(log n) depth and O(n log n) total complexity. We show that this model is powerful enough to infer efficient algorithms for common algorithmic benchmarks including sorting, addition and multiplication. We evaluate our architecture on the challenging LAMBADA question answering dataset and compare it with the state-of-the-art models which use attention. Our model achieves competitive accuracy and scales to sequences with more than a hundred thousand of elements. We are confident that the proposed model has the potential for building more efficient architectures for processing large interrelated data in language modeling, music generation and other application domains.

33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

References in corpus (6)

• WaveNet: A Generative Model for Raw Audio
• Convolutional Sequence to Sequence Learning
• Generating Long Sequences with Sparse Transformers
• Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
• Improving the Neural GPU Architecture for Algorithm Learning
• Recent Advances in Neural Program Synthesis

Cited by in corpus (5)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers
• Persistent Message Passing
• Learning Algebraic Recombination for Compositional Generalization