Multi-Dimensional Classification via Decomposed Label Encoding
| Autor: | Min-Ling Zhang, Bin-Bin Jia |
|---|---|
| Rok vydání: | 2023 |
| Předmět: |
Computer science
business.industry Feature vector Pattern recognition Space (mathematics) Class (biology) Computer Science Applications Computational Theory and Mathematics Encoding (memory) Multi dimensional Decomposition (computer science) Artificial intelligence Benchmark data business Class variable Information Systems |
| Zdroj: | IEEE Transactions on Knowledge and Data Engineering. 35:1844-1856 |
| ISSN: | 2326-3865 1041-4347 |
| DOI: | 10.1109/tkde.2021.3100436 |
| Popis: | In multi-dimensional classification (MDC), a number of class variables are assumed in the output space with each of them specifying the class membership w.r.t. one heterogeneous class space. One major challenge in learning from MDC examples lies in the heterogeneity of class spaces, where the modeling outputs from different class spaces are not directly comparable. To tackle this problem, we propose a new strategy named decomposed label encoding which enables modeling alignment for MDC in an encoded label space derived from one-vs-one (OvO) decomposition. Specifically, the original MDC output space is transformed into a ternary encoded label space by conducting OvO decomposition w.r.t. each class space. Then, the manifold structure in the feature space is exploited to enrich the labeling information in the encoded label space. Finally, the predictive model is induced by fitting the metric-aligned modeling outputs with enriched labeling information. Extensive experiments over twenty benchmark data sets clearly show the superiority of the proposed MDC strategy against state-of-the-art approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|