Partial Multi-Label Learning via Credible Label Elicitation
Authors: Jun-Peng Fang, Min-Ling Zhang3518-3525
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on synthetic as well as real-world data sets clearly validate the effectiveness of credible label elicitation in learning from PML examples. |
| Researcher Affiliation | Academia | 1School of Computer Science and Engineering, Southeast University, Nanjing 210096, China 2Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China 3Collaborative Innovation Center of Wireless Communications Technology, China |
| Pseudocode | Yes | Table 1: The pseudo-code of PARTICLE. |
| Open Source Code | No | The paper does not provide any links to source code for the described methodology, nor does it state that the code is available in supplementary materials or upon request. It mentions using 'Libsvm (Chang and Lin 2011)' which is a third-party tool. |
| Open Datasets | Yes | six benchmark multi-label data sets (Zhang and Zhou 2014) are used to generate synthetic PML data sets, including image, emotions, scene, yeast, eurlex dc, and eurlex sm. Furthermore, three real-world PML data sets including music emotion, music style and mirflickr (Huiskes and Lew 2008) are also employed in this paper. |
| Dataset Splits | Yes | On each data set, five-fold cross-validation is performed where the mean metric value as well as standard deviation are recorded for each comparing approach. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | The paper mentions 'Libsvm (Chang and Lin 2011)' as a base learner and binary training algorithm, but it does not specify a version number for Libsvm or any other key software components used in their experimental environment (e.g., Python version, specific libraries with versions). |
| Experiment Setup | Yes | As shown in Table 1, parameters k (number of nearest neighbors considered), α (balancing parameter) and thr (credible label elicitation threshold) for PARTICLE are set to be 10, 0.95 and 0.9 respectively. |