| Autor: |
Keisuke Maeda, Masanao Matsumoto, Naoki Saito, Takahiro Ogawa, Miki Haseyama |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 12, Pp 127244-127258 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2024.3437328 |
| Popis: |
This paper presents a multi-modal Gaussian process latent variable model with semi-supervised label dequantization. In real-world applications, although user ratings are often attached to the content, they are roughly provided and are limited in number due to the manual provision. The roughness and small sample problems make it difficult to estimate the ratings of the content. To solve the problem, we newly derive the semi-supervised label dequantization scheme by combining the pseudo-labeling for unlabeled data based on soft-labeling and our previously proposed label dequantization scheme. This is the main contribution of this paper. By introducing the scheme into the optimization process of a Gaussian process-based generative model, we realize the multi-modal Gaussian process latent variable model with semi-supervised label dequantization, and highly accurate rating estimation becomes feasible. The effectiveness of our method is verified through several experiments using some open datasets. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
