TY - JOUR
T1 - Generalizing graph matching beyond quadratic assignment model
AU - Yu, Tianshu
AU - Yan, Junchi
AU - Wang, Yilin
AU - Liu, Wei
AU - Li, Baoxin
N1 - Funding Information:
This work was supported in part by a grant from ONR. Junchi Yan is supported in part by NSFC 61602176 and Tencent AI Lab Rhino-Bird Joint Research Program (No. JR201804). Any opinions expressed in this material are those of the authors and do not necessarily reflect the views of ONR.
Publisher Copyright:
© 2018 Curran Associates Inc..All rights reserved.
PY - 2018
Y1 - 2018
N2 - Graph matching has received persistent attention over several decades, which can be formulated as a quadratic assignment problem (QAP). We show that a large family of functions, which we define as Separable Functions, can approximate discrete graph matching in the continuous domain asymptotically by varying the approximation controlling parameters. We also study the properties of global optimality and devise convex/concave-preserving extensions to the widely used Lawler's QAP form. Our theoretical findings show the potential for deriving new algorithms and techniques for graph matching. We deliver solvers based on two specific instances of Separable Functions, and the state-of-the-art performance of our method is verified on popular benchmarks.
AB - Graph matching has received persistent attention over several decades, which can be formulated as a quadratic assignment problem (QAP). We show that a large family of functions, which we define as Separable Functions, can approximate discrete graph matching in the continuous domain asymptotically by varying the approximation controlling parameters. We also study the properties of global optimality and devise convex/concave-preserving extensions to the widely used Lawler's QAP form. Our theoretical findings show the potential for deriving new algorithms and techniques for graph matching. We deliver solvers based on two specific instances of Separable Functions, and the state-of-the-art performance of our method is verified on popular benchmarks.
UR - http://www.scopus.com/inward/record.url?scp=85064816710&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064816710&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85064816710
SN - 1049-5258
VL - 2018-December
SP - 853
EP - 863
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 32nd Conference on Neural Information Processing Systems, NeurIPS 2018
Y2 - 2 December 2018 through 8 December 2018
ER -