Learning Robust Locality Preserving Projection via p-Order Minimization

Authors: Hua Wang, Feiping Nie, Heng Huang

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive empirical evaluations on the proposed r LPP method have been performed, in which our new method outperforms the related state-of-the-art methods in a variety of experimental settings and demonstrate its effectiveness in seeking better subspaces on both noiseless and noisy data.
Researcher Affiliation Academia Department of Electrical Engineering and Computer Science Colorado School of Mines, Golden, Colorado 80401, USA Department of Computer Science and Engineering University of Texas at Arlington, Arlington, Texas 76019, USA
Pseudocode Yes Algorithm 1: The algorithm to solve the problem (2).
Open Source Code No The paper does not provide any explicit statements or links indicating that its source code is publicly available.
Open Datasets Yes We evaluate the proposedmethods on five widely used benchmark data sets in machine learning studies. The data descriptions are summarized in Table 1. The first two data sets are obtained from the UCI machine learning data repository.
Dataset Splits No The paper describes the datasets used and how clustering was performed, but does not specify explicit training/validation/test splits, percentages, or absolute counts for data partitioning.
Hardware Specification No The paper mentions that "The algorithms are implemented in MATLAB" but does not provide any specific details about the hardware (e.g., CPU, GPU, memory) used for running the experiments.
Software Dependencies No The paper states, "The algorithms are implemented in MATLAB", but does not specify a version number for MATLAB or any other software dependencies.
Experiment Setup Yes For PCA, we reduce the dimensionality of the input data such that 90% of data variance is preserved. For r PCA, following (Wright et al. 2009), we set λ = d 1/2. We empirically select the reduced dimensionality of LPP method to be c 1 where c is the number of clusters of a data set... we construct the nearest-neighbor graph for each data set and set the neighborhood size for graph construction as 10 following (Niyogi 2004). ... we independently repeat the clustering procedures in the projected subspaces learned by all compared methods for 50 times with random initializations