Adversarial Partial Multi-Label Learning with Label Disambiguation

Authors: Yan Yan, Yuhong Guo10568-10576

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are conducted on both synthetic and real-world partial multi-label datasets, while the proposed model demonstrates the state-of-the-art performance.
Researcher Affiliation Academia 1 School of Computer Science and Engineering, Northwestern Polytechnical University, China 2 School of Computer Science, Carleton University, Canada
Pseudocode Yes Algorithm 1 Minibatch based stochastic gradient descent training algorithm for PML-GAN
Open Source Code No The paper does not provide an explicit statement or link indicating that the source code for the methodology is openly available.
Open Datasets Yes We conducted experiments on twelve multi-label classification datasets. Three of them have existing partial multi-label learning settings (mirflickr, music style and music emotion (Fang and Zhang 2019)). For each of the other nine datasets (Zhang and Zhou 2014), we transformed it into a PML dataset by randomly adding irrelevant labels into the candidate label set of each training instance.
Dataset Splits No For each dataset, we randomly select 80% of the data for training and use the remaining 20% for testing. There is no explicit mention of a separate validation split or its size.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper mentions using the Adam optimizer and designing networks as multilayer perceptrons, but does not specify any software dependencies (e.g., programming languages, libraries, frameworks) with version numbers.
Experiment Setup Yes The mini-batch size, m, is set to 64. The hyperparameters k (the number of steps for discriminator update) and n (the number of label vectors sampled) in Algorithm 1 are set to 1 and 210 respectively. The hyperparameter β is chosen from {0.001, 0.01, 0.1, 1, 10} based on the classification loss value Lc in the training objective function; that is, the β value that leads to the smallest training Lc loss will be chosen.