Multi-view Spectral Clustering Network

Authors: Zhenyu Huang, Joey Tianyi Zhou, Xi Peng, Changqing Zhang, Hongyuan Zhu, Jiancheng Lv

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on four challenging datasets demonstrate the effectiveness of our method compared with 10 state-of-the-art approaches in terms of three evaluation metrics.
Researcher Affiliation Academia 1College of Computer Science, Sichuan University, China 2Institute of High Performance Computing, A*STAR, Singapore 3School of Computer Science and Technology, Tianjin University, China 4Institute for Infocomm Research, A*STAR, Singapore
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The experiment code will be soon released on Github.
Open Datasets Yes Noisy MNIST1: We adopt the setting used in [Wang et al., 2015]. ... 1http://ttic.uchicago.edu/ wwang5/dccae.html, create MNIST.m; Caltech101-20 (A subset of Caltech1012): ... 2http://www.vision.caltech.edu/Image Datasets/Caltech101/; Reuters3: ... 3https://archive.ics.uci.edu/ml/datasets.html; NUS-WIDE-OBJ4 : ... 4http://lms.comp.nus.edu.sg/research/NUS-WIDE.htm
Dataset Splits No For a fair comparison, we randomly split the dataset into two partitions with equal size, one partition is used to tune parameters for all the methods and the other partition is used for evaluation.
Hardware Specification Yes All the experiments are implemented using Keras+Tensorflow on a standard Ubuntu-16.04 OS with an NVIDIA 1080Ti GPU.
Software Dependencies No The paper mentions "Keras+Tensorflow" and "Ubuntu-16.04 OS" but does not provide specific version numbers for Keras or TensorFlow, which are key software components.
Experiment Setup Yes In this section, we investigate the influence of the parameters λ and k of our method.