ICLR 2024poster5 citations
Entropy Coding of Unordered Data Structures
Julius Kunze, Daniel Severo, Giulio Zani, Jan-Willem van de Meent, James Townsend
Abstract
We present shuffle coding, a general method for optimal compression of sequences of unordered objects using bits-back coding. Data structures that can be compressed using shuffle coding include multisets, graphs, hypergraphs, and others. We release an implementation that can easily be adapted to different data types and statistical models, and demonstrate that our implementation achieves state-of-the-art compression rates on a range of graph datasets including molecular data.
graph compressionentropy codingneural compressionbits-back codinglossless compressiongenerative modelsinformation theoryprobabilistic modelsgraph neural networksmultiset compressionasymmetric numeral systemscompressionentropyshuffle coding
BibTeX
@inproceedings{
kunze2024entropy,
title={Entropy Coding of Unordered Data Structures},
author={Julius Kunze and Daniel Severo and Giulio Zani and Jan-Willem van de Meent and James Townsend},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=afQuNt3Ruh}
}