AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

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

Karlis Freivalds, Emīls Ozoliņš, Agris Šostaks

NeurIPS 2019 · Architectures and efficiency › Attention and transformers · approach: State space and recurrent sequence models · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the Shuffle-Exchange network instead of the Gated-Attention ReaderLAMBADA word prediction · LAMBADA testaccuracy (%): 49.0 -> 52.28Improved
Use the Shuffle-Exchange network instead of the Universal TransformerLAMBADA word prediction · LAMBADA testaccuracy (%): 56.0 -> 52.28Hurt
Generalize the learned algorithm to sequences longer than the training examplesShuffle-Exchange network · Duplication and reversal, length 512accuracyImproved
Generalize the learned algorithm to sequences longer than the training examplesShuffle-Exchange network · MultiplicationaccuracyHurt
Add the fixed swapHalf operation rather than use identity (ablation)Shuffle-Exchange Switch Unit · Multiplication, LAMBADA, addition, and sortingtest accuracyImproved
Add residual connections between Beneš blocks (ablation)Shuffle-Exchange network · Multiplication, LAMBADA, addition, and sortingtest accuracyImproved
Use two shuffle directions as in the Beneš network (ablation)Shuffle-Exchange network · Multiplication, LAMBADA, addition, and sortingtest accuracyImproved
Use fixed swapHalf instead of an additional swap gate (ablation)Shuffle-Exchange Switch Unit · Multiplication, LAMBADA, addition, and sortingtest accuracyImproved
Keep the Switch Unit instead of replacing it with two fully connected layers (ablation)Shuffle-Exchange network · Multiplication, LAMBADA, addition, and sortingtest accuracyImproved
Keep the reset-gate portion instead of replacing it with two fully connected layers while retaining the update gate (ablation)Shuffle-Exchange Switch Unit · Multiplication, LAMBADA, addition, and sortingtest accuracyImproved
Retain the update gate (ablation)Shuffle-Exchange Switch Unit · Multiplication, LAMBADA, addition, and sortingtest accuracyImproved
Increase Beneš block count (ablation)Shuffle-Exchange network · Multiplication and LAMBADAtest accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy