A Fast Nonnegative Autoencoder-Based Approach to Latent Feature Analysis on High-Dimensional and Incomplete Data

Page view(s)
0
Checked on
A Fast Nonnegative Autoencoder-Based Approach to Latent Feature Analysis on High-Dimensional and Incomplete Data
Title:
A Fast Nonnegative Autoencoder-Based Approach to Latent Feature Analysis on High-Dimensional and Incomplete Data
Journal Title:
IEEE Transactions on Services Computing
Publication Date:
27 September 2023
Citation:
Bi, F., He, T., & Luo, X. (2024). A Fast Nonnegative Autoencoder-Based Approach to Latent Feature Analysis on High-Dimensional and Incomplete Data. IEEE Transactions on Services Computing, 17(3), 733–746. https://doi.org/10.1109/tsc.2023.3319713
Abstract:
High-Dimensional and Incomplete (HDI) data are frequently encountered in various Big Data-related applications. Despite its incompleteness, an HDI data repository contains rich knowledge and patterns concerning the complex interactions among numerous nodes. Recently, a Neural Network (NN)-based approach to Latent Feature Analysis (LFA) model becomes popular owing to its strong representation learning ability to HDI data. Nevertheless, existing NN-based LFA models neglect the inherent nonnegativity in most HDI data, resulting in representation accuracy loss. Motivated by this discovery, this study innovatively proposes a Fast Nonnegative Auto Encoder (FNAE)-based approach to LFA on HDI data, whose ideas are three-fold: a) constructing a multilayered autoencoder subject to nonnegativity constraints for high representation learning ability; b) incorporating the data density-oriented modeling mechanism into FNAE's input and output layers for high computational and storage efficiency; and c) implementing an Adam-based single latent factor-dependent, nonnegative and multiplicative update algorithm for efficient model training as well as fulfilling the nonnegativity constraints. Experimental results on eight commonly-adopted HDI matrices from industrial applications demonstrate that the proposed FNAE significantly outperforms several state-of-the-art NN-based LFA models in both estimation accuracy for missing links of an HDI matrix and computational efficiency.
License type:
Publisher Copyright
Funding Info:
This work was supported in part by the National Natural Science Foundation of China under Grants 62272078 and 62103200 and in part under A*STAR by the A*STAR RIE2025 Manufacturing, Trade and Connectivity (MTC) Industry Alignment Fund- Pre-Positioning (IAF-PP) under Grant M23L4a0001.
Description:
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1939-1374
2372-0204
Files uploaded: