Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2309.13855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918007689707520 |
|---|---|
| author | Shen, Binrui Niu, Qiang Zhu, Shengxin |
| author_facet | Shen, Binrui Niu, Qiang Zhu, Shengxin |
| contents | 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 efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_13855 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Adaptive Softassign via Hadamard-Equipped Sinkhorn Shen, Binrui Niu, Qiang Zhu, Shengxin Optimization and Control Combinatorics 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 efficiency. |
| title | Adaptive Softassign via Hadamard-Equipped Sinkhorn |
| topic | Optimization and Control Combinatorics |
| url | https://arxiv.org/abs/2309.13855 |