Deep Partial Multi-Label Learning with Graph Disambiguation

Authors: Haobo Wang, Shisong Yang, Gengyu Lyu, Weiwei Liu, Tianlei Hu, Ke Chen, Songhe Feng, Gang Chen

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various synthetic datasets and three real-world PML datasets demonstrate that PLAIN achieves significantly superior results to state-of-the-art methods.
Researcher Affiliation Academia 1Zhejiang University 2Beijing University of Technology 3Wuhan University 4Beijing Jiaotong University
Pseudocode Yes Algorithm 1 The pseudo-code of PLAIN
Open Source Code No No explicit statement or link providing concrete access to the source code for the methodology described in this paper was found. A footnote links to the arXiv pre-print of the paper itself, not to code.
Open Datasets Yes A total of nine benchmark multi-label datasets2 are used for synthetic PML datasets generation, including Emotions, Birds, Medical, Image, Bibtex, Corel5K, Eurlex-dc, Eurlex-sm, NUS-WIDE. ... 2http://mulan.sourceforge.net/datasets-mlc.html
Dataset Splits No The paper mentions 'ten-fold cross-validation' and 'training dataset' but does not specify explicit validation splits (e.g., percentages or counts for a separate validation set).
Hardware Specification No The paper mentions using 'GPUs' for computation but does not provide specific hardware details such as GPU models, CPU types, or memory amounts.
Software Dependencies No The paper mentions 'python package Faiss' and 'Scipy package' but does not specify their version numbers or versions for other key software components like Python itself or deep learning frameworks.
Experiment Setup Yes For our PLAIN method, the deep model is comprised of three fully-connected layers. The hidden sizes are set as [64, 64] for those datasets with less than 64 labels, and [256, 256] for those datasets with more than 64 and less than 256 labels. For the remaining datasets, we set the hidden sizes as [512, 512]. The trade-off parameters α and β are hand-tuned from {0.001, 0.01, 0.1}. η is selected from {0.1, 1, 10}. Following [Iscen et al., 2017], we set ρ = 3. We train our deep model via stochastic gradient descent and empirically set the learning rate as 0.01 for both propagation and deep model training procedures. The number of maximum iterations is set as T = 200 for small-scale datasets and T = 50 for the large-scale NUS-WIDE dataset. Besides, weight decay is applied with a rate of 5e-5 to avoid overfitting.