A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2110.09419v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Compositional Attention: Disentangling Search and Retrieval
[article]
<span title="2022-02-13">2022</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2021-10-18">2021</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.09419v1">arXiv:2110.09419v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ikwtvmxgp5bozmgmw3ghcnt7lm">fatcat:ikwtvmxgp5bozmgmw3ghcnt7lm</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.09419v1">arXiv:2110.09419v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ikwtvmxgp5bozmgmw3ghcnt7lm">fatcat:ikwtvmxgp5bozmgmw3ghcnt7lm</a> </span>
Multi-head, key-value attention is the backbone of the widely successful Transformer model and its variants. This attention mechanism uses multiple parallel key-value attention blocks (called heads), each performing two fundamental computations: (1) search - selection of a relevant entity from a set via query-key interactions, and (2) retrieval - extraction of relevant features from the selected entity via a value matrix. Importantly, standard attention heads learn a rigid mapping between
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.09419v2">arXiv:2110.09419v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zkwt2m4nt5h6tfz3zrcrpyqwd4">fatcat:zkwt2m4nt5h6tfz3zrcrpyqwd4</a>
</span>
more »
... and retrieval. In this work, we first highlight how this static nature of the pairing can potentially: (a) lead to learning of redundant parameters in certain tasks, and (b) hinder generalization. To alleviate this problem, we propose a novel attention mechanism, called Compositional Attention, that replaces the standard head structure. The proposed mechanism disentangles search and retrieval and composes them in a dynamic, flexible and context-dependent manner through an additional soft competition stage between the query-key combination and value pairing. Through a series of numerical experiments, we show that it outperforms standard multi-head attention on a variety of tasks, including some out-of-distribution settings. Through our qualitative analysis, we demonstrate that Compositional Attention leads to dynamic specialization based on the type of retrieval needed. Our proposed mechanism generalizes multi-head attention, allows independent scaling of search and retrieval, and can easily be implemented in lieu of standard attention heads in any network architecture.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220218040617/https://arxiv.org/pdf/2110.09419v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/b8/b8/b8b813111c411ae61881ab9cd25707d9de6444ec.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.09419v2" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>