Deep Asymmetric Multi-task Feature Learning
Authors: Hae Beom Lee, Eunho Yang, Sung Ju Hwang
ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We extensively validate our method on a synthetic dataset as well as eight benchmark datasets for multi-task learning and image classification using both the shallow and the deep neural network models, on which our models obtain superior performances over existing symmetric feature-sharing multi-task learning model as well as the inter-task parameter regularization based asymmetric multi-task learning model. |
| Researcher Affiliation | Collaboration | 1UNIST, Ulsan, South Korea 2AItrics, Seoul, South Korea 3KAIST, Daejeon, South Korea. |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described in this paper. |
| Open Datasets | Yes | AWA-A: This is a classification dataset (Lampert et al., 2009)... MNIST: This is a standard dataset for classification (Le Cun et al., 1998)... School: This is a regression dataset... (Argyriou et al., 2008)... Room: This is a subset of the Image Net dataset (Deng et al., 2009) from (Lee et al., 2016)... MNIST-Imbalanced... CUB-200... AWA-C... Image Net-Small: This is a subset of the Image Net 22K dataset (Deng et al., 2009). |
| Dataset Splits | Yes | We generate five random train/val/test splits for each group 50/50/100 for easy tasks and 25/25/100 for hard tasks. The number of instances for train, validation, and test set for each task is 1080, 60, and 60, respectively. and 5 random 100/50/50 splits are used for each train/val/test. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | For the implementation of all the baselines and our deep models, we use Tensorflow (Abadi et al., 2016) and Caffe (Jia, 2013) framework. |
| Experiment Setup | Yes | We searched for α and γ in the range of {1, 0.1, 10 2, 10 3, 10 4}. For CUB dataset, we gradually increase α and γ from 0, which helps with stability of learning at the initial stage of the training. We set the number of hidden neurons to 1000 which is tuned on the base NN. We set the number of hidden neurons to 500. We set the number of hidden neurons to 10 or 15. |