Adaptive Softassign via Hadamard-Equipped Sinkhorn
Binrui Shen, Qiang Niu, Shengxin Zhu

TL;DR
This paper introduces an adaptive softassign method for graph matching that automatically tunes parameters for improved accuracy and stability, utilizing Hadamard-Equipped Sinkhorn formulas to enhance efficiency and applicability to optimal transport problems.
Contribution
It presents a novel adaptive softassign algorithm with automatic parameter tuning and introduces Hadamard-Equipped Sinkhorn formulas for better efficiency and stability.
Findings
Achieves higher accuracy than previous large graph matching algorithms.
Maintains comparable efficiency with improved stability.
Extends applicability to optimal transport problems.
Abstract
Softassign is a pivotal method in graph matching and other learning tasks. Many softassign-based algorithms exhibit performance sensitivity to a parameter in the softassign. However, tuning the parameter is challenging and almost done empirically. This paper proposes an adaptive softassign method for graph matching by analyzing the relationship between the objective score and the parameter. This method can automatically tune the parameter based on a given error bound to guarantee accuracy. The Hadamard-Equipped Sinkhorn formulas introduced in this study significantly enhance the efficiency and stability of the adaptive softassign. Moreover, these formulas can also be used in optimal transport problems. The resulting adaptive softassign graph matching algorithm enjoys significantly higher accuracy than previous state-of-the-art large graph matching algorithms while maintaining comparable…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNetwork Packet Processing and Optimization · Complexity and Algorithms in Graphs · Machine Learning and Algorithms
