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.



There are no comments yet.


page 1

page 2

page 3

page 4


IS Attention All What You Need? – An Empirical Investigation on Convolution-Based Active Memory and Self-Attention

The key to a Transformer model is the self-attention mechanism, which al...

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...

Self-attention Does Not Need O(n^2) Memory

We present a very simple algorithm for attention that requires O(1) memo...

Multiscale Self Attentive Convolutions for Vision and Language Modeling

Self attention mechanisms have become a key building block in many state...

How Can Self-Attention Networks Recognize Dyck-n Languages?

We focus on the recognition of Dyck-n (𝒟_n) languages with self-attentio...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.