KerGM: Kernelized Graph Matching

Authors: Zhen Zhang, Yijian Xiang, Lingfei Wu, Bing Xue, Arye Nehorai

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments to evaluate our approach, and show that our algorithm significantly outperforms the state-of-the-art in both matching accuracy and scalability.
Researcher Affiliation Collaboration 1Washington University in St. Louis 2IBM Research
Pseudocode Yes Algorithm 1 The En FW optimization algorithm for minimizing Fα (15)
Open Source Code No The paper states "We implement all the algorithms using Matlab" but provides no information about public availability of the source code for the described methodology.
Open Datasets Yes The CMU House Sequence dataset has 111 frames of a house, each of which has 30 labeled landmarks. The Pascal dataset [26] has 20 pairs of motorbike images and 30 pairs of car images. The S.cerevisiae (yeast) PPI network [7] dataset is popularly used to evaluate PPI network aligners because it has known true node correspondences.
Dataset Splits No The paper does not explicitly provide details about training/validation/test splits used for its experiments. It evaluates "matching accuracy" on various datasets and pairs, but does not describe a formal data splitting process for training, validation, and testing.
Hardware Specification Yes We implement all the algorithms using Matlab on an Intel i7-7820HQ, 2.90 GHz CPU with 64 GB RAM.
Software Dependencies No The paper states "We implement all the algorithms using Matlab" but does not specify a version number for Matlab or any other software dependencies.
Experiment Setup Yes For our method, if not specified, we set the regularization parameter (see (15)) λ = 0.005 and the path following parameters α = 0 : 0.1 : 1. We use the Hungarian algorithm for final discretization. We set the parameter γ = 5 and the dimension D = 20.