Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Ising on the Graph: Task-specific Graph Subsampling via the Ising Model
Uppsala University; RISE.ORCID iD: 0009-0007-5465-7170
Uppsala University.ORCID iD: 0000-0002-6811-2776
Linköping University, Department of Computer and Information Science, The Division of Statistics and Machine Learning. Linköping University, Faculty of Science & Engineering. Uppsala University.ORCID iD: 0000-0003-2949-8781
Uppsala University.ORCID iD: 0000-0002-9099-3522
2024 (English)In: The Third Learning on Graphs Conference, 2024Conference paper, Published paper (Refereed)
Abstract [en]

Reducing a graph while preserving its overall properties is an important problem with many applications. Typically, reduction approaches either remove edges (sparsification) or merge nodes (coarsening) in an unsupervised way with no specific downstream task in mind. In this paper, we present an approach for subsampling graph structures using an Ising model defined on either the nodes or edges and learning the external magnetic field of the Ising model using a graph neural network. Our approach is task-specific as it can learn how to reduce a graph for a specific downstream task in an end-to-end fashion without requiring a differentiable loss function for the task. We showcase the versatility of our approach on four distinct applications: image segmentation, explainability for graph classification, 3D shape sparsification, and sparse approximate matrix inverse determination.

Place, publisher, year, edition, pages
2024.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:liu:diva-212078OAI: oai:DiVA.org:liu-212078DiVA, id: diva2:1942154
Conference
Learning on Graphs Conference
Funder
Wallenberg AI, Autonomous Systems and Software Program (WASP)Available from: 2025-03-04 Created: 2025-03-04 Last updated: 2025-03-04

Open Access in DiVA

fulltext(11119 kB)5215 downloads
File information
File name FULLTEXT01.pdfFile size 11119 kBChecksum SHA-512
7a0c4437b55cc2279003d2f0c6ffcc52f789a3016efd62054c3bdac268c4ee891a93dfba5d093950b96ad118ba6f7a45b22752e117a24ebe735e589e9ad4b360
Type fulltextMimetype application/pdf

Other links

https://openreview.net/forum?id=HFRCBCHHz4https://logconference.org/

Search in DiVA

By author/editor
Bånkestad, MariaAndersson, JenniferMair, SebastianSjölund, Jens
By organisation
The Division of Statistics and Machine LearningFaculty of Science & Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 5215 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 589 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf