Solving graph compression via optimal transport
Name
NeurIPS-2019-solving-graph-compression-via-optimal-transport-Paper.pdf
Description
Published version
Size
420.33 KB
Format
Adobe PDF
Checksum (MD5)
72f086a10b75ca06069f63aa52ba39f7
Author(s)
Garg, Vikas
Jaakkola, Tommi S
Date Issued
December 2019
Journal
Advances in Neural Information Processing Systems
Publisher
Morgan Kaufmann Publishers
Citation
Garg, Vikas K. and Tommi Jaakkola. “Solving graph compression via optimal transport.” Advances in Neural Information Processing Systems, 32 (May 2019) © 2019 The Author(s)
Version
Final published version
Abstract
We propose a new approach to graph compression by appeal to optimal transport. The transport problem is seeded with prior information about node importance, attributes, and edges in the graph. The transport formulation can be setup for either directed or undirected graphs, and its dual characterization is cast in terms of distributions over the nodes. The compression pertains to the support of node distributions and makes the problem challenging to solve directly. To this end, we introduce Boolean relaxations and specify conditions under which these relaxations are exact. The relaxations admit algorithms with provably fast convergence. Moreover, we provide an exact O(d log d) algorithm for the subproblem of projecting a d-dimensional vector to transformed simplex constraints. Our method outperforms state-of-the-art compression methods on graph classification.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/2019/hash/8fc983a91396319d8c394084e2d749d7-Abstract.html
