Leveraged Weighted Loss for Partial Label Learning
Authors: Hongwei Wen, Jingyi Cui, Hanyuan Hang, Jiabin Liu, Yisen Wang, Zhouchen Lin
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this part, we empirically verify the effectiveness of our proposed algorithm through performance comparisons as well as other empirical understandings. ... In this section, we conduct empirical comparisons with other state-of-the-art partial label learning algorithms on both benchmark and real datasets. |
| Researcher Affiliation | Collaboration | 1 Key Lab. of Machine Perception (Mo E), School of EECS, Peking University, China 2 Department of Applied Mathematics, University of Twente, The Netherlands 3 Samsung Research China-Beijing, Beijing, China 4 Pazhou Lab, Guangzhou, China. |
| Pseudocode | Yes | Algorithm 1 LW Loss for Partial Label Learning |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the methodology described. |
| Open Datasets | Yes | We base our experiments on four benchmark datasets: MNIST (Le Cun et al., 1998), Kuzushiji-MNIST (Clanuwat et al., 2018), Fashion-MNIST (Xiao et al., 2017), and CIFAR-10 (Krizhevsky et al., 2009). ... In this part we base our experimental comparisons on 5 real-world datasets including: Lost (Cour et al., 2011), MSRCv2 (Liu & Dietterich, 2012), Bird Song (Briggs et al., 2012), Soccer Player (Zeng et al., 2013), and Yahoo! News (Guillaumin et al., 2010). |
| Dataset Splits | Yes | Hyper-parameters are searched to maximize the accuracy on a validation set containing 10% of the partially labeled training samples. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions 'Py Torch (Paszke et al., 2019)' but does not provide a specific version number for it or any other software dependency. |
| Experiment Setup | Yes | For our proposed method, we search the initial learning rate from {0.001, 0.005, 0.01, 0.05, 0.1} and weight decay from {10 6, 10 5, . . . , 10 2}, with the exponential learning rate decay halved per 50 epochs. We search β {1, 2} according to the theoretical guidance discussed in Section 3.3. For computational implementations, we use Py Torch (Paszke et al., 2019) and the stochastic gradient descent (SGD) (Robbins & Monro, 1951) optimizer with momentum 0.9. For all methods, we set the mini-batch size as 256 and train each model for 250 epochs. |