Deep Latent Low-Rank Fusion Network for Progressive Subspace Discovery

Authors: Zhao Zhang, Jiahuan Ren, Zheng Zhang, Guangcan Liu

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive results show that our network can deliver enhanced performance over other related frameworks. ... 6 Experimental Results and Analysis
Researcher Affiliation Academia Zhao Zhang1,2, Jiahuan Ren2, Zheng Zhang3 and Guangcan Liu4 1 Key Laboratory of Knowledge Engineering with Big Data, Hefei University of Technology, China 2 School of Computer Science and Technology, Soochow University, China 3 Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen, China 4 School of Information and Control, Nanjing University of Information Science and Technology, China
Pseudocode Yes Algorithm 1 Solving Eq.(9) by Inexact ALM (l-th layer)
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the described methodology.
Open Datasets Yes Three real image databases are involved, including two face datasets (i.e., CMU PIE [Sim et al., 2003], UMIST [Graham et al., 1998]) and the Fashion MNIST database [Xiao et al., 2017]. The details of used databases are described in Table 1.
Dataset Splits No The paper describes evaluation procedures for clustering on existing datasets but does not specify distinct training, validation, and test splits for the DLRF-Net model itself in a way that allows reproduction of data partitioning for model training. It mentions 'For each number K of clusters, we choose K categories randomly and the results are averaged over 30 initializations.'
Hardware Specification Yes We perform all experiments on a PC with Intel (R) Core (TM) i7-7700 CPU @ 3.6 GHz 8G.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup Yes DLRF-Net has one parameter , so we can select the most important one by a linear search from 10^-8, 10^-6, ..., 10^6, 10^8. ... To evaluate the robustness properties, random Gaussian noise with variance 500 is included into the image data. ... For each setting, we average the result over 30 random initialization for NCut.