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

By Kārlis Freivalds, Emils Ozolins, Agris Sostaks. 2019

Subfields: Model Architectures, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

1. Andrea Lodi
2. Kevin Swersky
3. Parthasarathy Ranganathan
4. Didier Chételat
5. Danai Koutra
6. Milad Hashemi
7. Petar Velickovic
8. Elias Boutros Khalil

Citations in the corpus

• Neural Execution Engines: Learning to Execute Subroutines (2020, background): “[8] develops a custom architecture that is tested on performing arithmetic, but trains on symbols in the range of [1 , 12] and does not demonstrate strong generalization.”
• Combinatorial optimization and reasoning with graph neural networks (2021, background): “Neural Shuffle-exchange Networks [ Freivalds et al. , 2019; Draguns et al. , 2020] directly fix connectivity patterns between nodes based on results from routing theory, allowing them to efficiently align with O ( n log n ) sequence processing algorithms.”