End-to-End Probabilistic Label-Specific Feature Learning for Multi-Label Classification

Authors: Jun-Yi Hang, Min-Ling Zhang, Yanghe Feng, Xiaocheng Song6847-6855

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments on 14 benchmark data sets show that our approach outperforms the state-of-the-art counterparts.
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 3College of Systems Engineering, National University of Defense Technology, Changsha 410073, China 4Department of Beijing Institute of Electronic Engineering, Beijing 100854, China
Pseudocode No The paper describes the proposed approach using text and mathematical equations but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes Code package is publicly available at: http://palm.seu.edu.cn/zhangml/files/PACA.rar
Open Datasets Yes Table 1: Characteristics of the experimental data sets. ... 1http://mulan.sourceforge.net/datasets.html 2http://palm.seu.edu.cn/zhangml/ 3http://lear.inrialpes.fr/people/guillaumin/data.php
Dataset Splits Yes We employ ten-fold cross validation to evaluate above approaches on the 14 data sets.
Hardware Specification No The paper states: 'We thank the Big Data Center of Southeast University for providing the facility support on the numerical calculations in this paper.' but does not specify any hardware details like GPU/CPU models or memory.
Software Dependencies No The paper mentions using 'Adam' for network optimization but does not provide specific software names with version numbers for libraries or frameworks (e.g., TensorFlow, PyTorch, scikit-learn).
Experiment Setup Yes We employ a fully-connected neural network with hidden dimensionality [256]...hidden dimensionalities of the encoder and the decoder are both set to [256, 512, 256]...Adam with a batch size of 128, weight decay of 10 5, momentums of 0.999 and 0.9 is employed.