Robust Multi-view Learning via Half-quadratic Minimization

Authors: Yonghua Zhu, Xiaofeng Zhu, Wei Zheng

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on both synthetic and real datasets demonstrate that our method outperforms the state-of-the-art methods.
Researcher Affiliation Academia Yonghua Zhu1,2, Xiaofeng Zhu1, , Wei Zheng1 1 Guangxi Key Lab of Multi-source Information Mining & Security, Guangxi Normal University, Guilin, 541004, China 2 Guangxi University, Nanning, 530004, China
Pseudocode No The paper describes an optimization strategy but does not present it in a structured pseudocode or algorithm block.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the methodology is openly available.
Open Datasets Yes We used four real multi-view datasets to evaluate the practical clustering performance of our proposed method. The details of the used datasets are reported in Table 2
Dataset Splits No The paper does not explicitly provide details about training, validation, and test dataset splits.
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependency details, such as library or solver names with version numbers.
Experiment Setup Yes We repeated k-means clustering 20 times and reported their average value for single view clustering and Con KM, and set the value of k as [10, 15, ..., 40] in k-nearest neighbor for the methods such as our proposed method. We also set the number of clusters as the number of real classes for all comparison methods, while our method automatically generates the number of clusters. The ranges of parameters of every method were set by strictly following the corresponding literature. We set the range of parameter λ in our method as λ [10-3, 10-2, ..., 103] and set the stop criteria of the iterative optimization as obj(t+1) obj(t) 2 2 obj(t) 10-6, where obj(t) stands for the objective value in the t-th iteration.