Predicting Label Distribution from Ternary Labels
Authors: Yunan Lu, Xiuyi Jia
NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Both the theoretical and methodological studies are conducted for the proposed learning paradigm. In the theoretical part, we conduct a quantitative comparison of approximation error between ternary and binary labels to elucidate the superiority of ternary labels over binary labels. In the methodological part, we propose a Categorical distribution with monotonicity and orderliness to model the mapping from label description degrees to ternary labels, which can serve as a loss function or as a probability distribution, allowing most existing label enhancement methods to be adapted to our task. Finally, we experimentally demonstrate the effectiveness of our proposal. |
| Researcher Affiliation | Academia | Yunan Lu, Xiuyi Jia School of Computer Science and Engineering Nanjing University of Science and Technology, Nanjing 210094, China {luyn, jiaxy}@njust.edu.cn |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The authors state in the NeurIPS Paper Checklist that 'the implementation of our proposed Cate MO is so simple that no additional code files are needed to describe it,' implying no explicit code release for the methodology. |
| Open Datasets | Yes | Therefore, we select three real-world LDL datasets (i.e., JAFFE [18], Painting [19], and Music [9]), and manually re-annotate them with both binary labels and the ternary labels. The details of these datasets can be found in Appendix. |
| Dataset Splits | Yes | We randomly partition the whole dataset (70% for training and 30% for testing), and repeat the above process ten times and report the average and standard deviation of the results. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. The NeurIPS Paper Checklist (Q8) states that 'Computer resources have a negligible effect on both the experimental results and the main claims of this paper.' |
| Software Dependencies | No | The paper mentions software components like 'LDL-LRR [7]' but does not specify version numbers for any software, libraries, or dependencies used in the experiments. |
| Experiment Setup | Yes | The hyperparameter settings follow their respective literature. We set the parameters [λ, λ, λ] in Cate MO as [49, 48, 12]. LDL-LRR [7] is used as the LDL model in this paper, whose hyperparameters λ and β are selected from {10 6, 10 5, . . . , 10 1} and {10 3, 10 2, . . . , 102} as suggested [7]. |