Balancing performance and complexity with adaptive graph coarsening

Authors: M. Dědič, L. Bajer, P. Procházka, Martin Holeňa
Publication year: 2024
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: The Second Tiny Papers Track at ICLR 2024
Bibliographic citation: DĚDIČ, M., BAJER, L., PROCHÁZKA, P., HOLEŇA, Martin. Balancing performance and complexity with adaptive graph coarsening. In: The Second Tiny Papers Track at ICLR 2024. OpenReview.net / ICLR, 2024, č. článku Submission Number: 223. Dostupné z: https://openreview.net/forum?id=DrHwIzz93C
ID: 585922
Online record: View online record

Abstract

We present a method for graph node classification that allows a user to precisely select the resolution at which the graph in question should be simplified and through this provides a way of choosing a suitable point in the performance-complexity trade-off. The method is based on refining a reduced graph in a targeted way following the node classification confidence for particular nodes.