Log In Sign Up

Untangling tradeoffs between recurrence and self-attention in neural networks

by   Giancarlo Kerg, et al.

Attention and self-attention mechanisms, inspired by cognitive processes, are now central to state-of-the-art deep learning on sequential tasks. However, most recent progress hinges on heuristic approaches with limited understanding of attention's role in model optimization and computation, and rely on considerable memory and computational resources that scale poorly. In this work, we present a formal analysis of how self-attention affects gradient propagation in recurrent networks, and prove that it mitigates the problem of vanishing gradients when trying to capture long-term dependencies. Building on these results, we propose a relevancy screening mechanism, inspired by the cognitive process of memory consolidation, that allows for a scalable use of sparse self-attention with recurrence. While providing guarantees to avoid vanishing gradients, we use simple numerical experiments to demonstrate the tradeoffs in performance and computational resources by efficiently balancing attention and recurrence. Based on our results, we propose a concrete direction of research to improve scalability of attentive networks.


page 1

page 2

page 3

page 4


Memory Controlled Sequential Self Attention for Sound Recognition

In this paper we investigate the importance of the extent of memory in s...

Context-Aware Self-Attention Networks

Self-attention model have shown its flexibility in parallel computation ...

Shatter: An Efficient Transformer Encoder with Single-Headed Self-Attention and Relative Sequence Partitioning

The highly popular Transformer architecture, based on self-attention, is...

On The Computational Complexity of Self-Attention

Transformer architectures have led to remarkable progress in many state-...

Efficient Spiking Transformer Enabled By Partial Information

Spiking neural networks (SNNs) have received substantial attention in re...

A Lightweight Recurrent Network for Sequence Modeling

Recurrent networks have achieved great success on various sequential tas...

Attention and Self-Attention in Random Forests

New models of random forests jointly using the attention and self-attent...