Papers › Matrix Shuffle-Exchange Networks for Hard 2D Tasks

Matrix Shuffle-Exchange Networks for Hard 2D Tasks

29 Jun 2020arXiv:2006.15892archive 2025-07-28

Emīls Ozoliņš, Kārlis Freivalds, Agris Šostaks

Convolutional neural networks have become the main tools for processing two-dimensional data. They work well for images, yet convolutions have a limited receptive field that prevents its applications to more complex 2D tasks. We propose a new neural model, called Matrix Shuffle-Exchange network, that can efficiently exploit long-range dependencies in 2D data and has comparable speed to a convolutional neural network. It is derived from Neural Shuffle-Exchange network and has 𝒪( logn) layers and 𝒪( n² logn) total time and space complexity for processing a n ×n data matrix. We show that the Matrix Shuffle-Exchange network is well-suited for algorithmic and logical reasoning tasks on matrices and dense graphs, exceeding convolutional and graph neural network baselines. Its distinct advantage is the capability of retaining full long-range dependency modelling when generalizing to larger instances - much larger than could be processed with models equipped with a dense attention mechanism.

PaperPDFConference PDFCode

Code

LUMII-Syslab/Matrix-SE officialmentioned in papermentioned on GitHubtf report
LUMII-Syslab/Switchblade officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph Neural NetworkImage ClassificationLogical Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Graph Neural NetworkSPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections