Unsupervised Disentangled Representation Learning with Analogical Relations
Authors: Zejian Li, Yongchuan Tang, Yongxing He
IJCAI 2018 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In Section 5 we demonstrate the experiment results and compare our method with other methods along the subspace score. In this section, we present the experiment results on five image datasets, including MNIST [Le Cun et al., 1998], Celeb A [Liu et al., 2015], Flower [Nilsback and Zisserman, 2008], CUB [Wah et al., 2011] and Chairs [Aubry et al., 2014]. Specifically, we compare our methods with other state-of-the-art methods along the subspace score. Table 1 reports the subspace score of models. |
| Researcher Affiliation | Academia | Zejian Li, Yongchuan Tang , Yongxing He College of Computer Science, Zhejiang University, Hangzhou 310027, China EMAIL |
| Pseudocode | No | The paper does not contain any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our source code will be available on https://github.com/Zejian Li/analogical-training. |
| Open Datasets | Yes | In this section, we present the experiment results on five image datasets, including MNIST [Le Cun et al., 1998], Celeb A [Liu et al., 2015], Flower [Nilsback and Zisserman, 2008], CUB [Wah et al., 2011] and Chairs [Aubry et al., 2014]. |
| Dataset Splits | No | The paper mentions usage of 'train' and 'test' in the context of models and results, but does not provide specific train/validation/test dataset splits with percentages, counts, or a clear splitting methodology. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running experiments. |
| Software Dependencies | No | The paper mentions 'Py Torch' and 'scikit-learn' but does not provide specific version numbers for these software dependencies. |
| Experiment Setup | Yes | For Ana GAN, we use the network architecture of DCGAN [Radford et al., 2015]. We use the WGAN-GP loss [Gulrajani et al., 2017] instead of the original GAN loss and the parameter num critic is set as 3. At the first 100 epoch, we only optimize V (D, G)... Both the noise and the code are sampled from the standard normal distribution. We use Adam optimizer [Kingma and Ba, 2014] with a learning rate of 0.00002 and a momentum of 0.5. The batch size is 32. Ana VAE shares most of the configuration in Ana GAN. The encoder network Q borrows the major structure of D in Ana GAN. The learning rate for the Adam optimizer is 0.0001... We add a dropout layer [Srivastava et al., 2014] after each nonlinear activation layer in R to avoid overfitting. To compute the subspace score, a cluster of ten sample sequences is generated for each factor and each sequence has five samples. The sequence is generated by varying the corresponding component of the code from -2 to 2 with the interval 1 but keeping other components fixed. We compute the subspace score over five different sets of generated samples to get the average. |