Robust Distance Metric Learning in the Presence of Label Noise

Authors: Dong Wang, Xiaoyang Tan

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments on several UCI datasets and a real dataset with unknown noise patterns show that the proposed RNCA is more tolerant to class label noise compared to the original NCA method.
Researcher Affiliation Academia Dong Wang, Xiaoyang Tan Department of Computer Science and Technology Nanjing University of Aeronautics and Astronautics #29 Yudao Street, Nanjing 210016, P.R.China {dongwang, x.tan}@nuaa.edu.cn
Pseudocode Yes Algorithm 1 Robust Neighbourhood Components Analysis.
Open Source Code No The paper does not provide any links to source code or explicitly state that code for their method is open-source or publicly available.
Open Datasets Yes We use 6 datasets from the UCI database, with 3 multi-class datasets (i.e., Iris, balance and wine) and 3 datasets with binary labels (i.e., Heart, vote and ionosphere).
Dataset Splits Yes All the parameters involved in these methods are either chosen through 5 cross validation or using the default settings.
Hardware Specification No The paper does not specify any hardware details (e.g., GPU/CPU models, memory, cloud computing instances) used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow, or specific library versions).
Experiment Setup No The paper mentions that parameters are chosen through "5 cross validation or using the default settings" and discusses tuning parameters like λ and ε, but it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed system-level training configurations used in their experiments.