Focus Your Attention (with Adaptive IIR Filters)

Shahar Lutati, Itamar Zimerman, Lior Wolf

Submission Type: Regular Long Paper

Submission Track: Efficient Methods for NLP

Submission Track 2: Machine Learning for NLP

Keywords: IIR Filters, dynamic Filtering, Transformers

TL;DR: We present a novel layer that leverage dynamic IIR filters to focus the attention mechanism, strengthening its long-range modeling capabilities.

Abstract:

We present a new layer in which dynamic (i.e., input-dependent) Infinite Impulse Response (IIR) filters of order two are used to process the input sequence prior to applying conventional attention. The input is split into chunks, and the coefficients of these filters are determined based on previous chunks to maintain causality. Despite their relatively low order, the causal adaptive filters are shown to focus attention on the relevant sequence elements. The new layer is grounded in control theory, and is shown to generalize diagonal state-space layers. The layer performs on-par with state-of-the-art networks, with a fraction of their parameters and with time complexity that is sub-quadratic with input size. The obtained layer is favorable
to layers such as Heyna, GPT2, and Mega, both with respect to the number of parameters and the obtained level of performance on multiple long-range sequence problems.

Submission Number: 2192