On Learning Invariant Representations for Domain Adaptation
Authors: Han Zhao, Remi Tachet Des Combes, Kun Zhang, Geoffrey Gordon
ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we conduct experiments on real-world datasets that corroborate our theoretical findings. |
| Researcher Affiliation | Collaboration | 1Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA, USA 2Microsoft Research, Montreal, Canada. |
| Pseudocode | No | The paper does not contain any sections or figures explicitly labeled as 'Pseudocode' or 'Algorithm'. |
| Open Source Code | No | The paper does not include any statement about making its source code publicly available or provide a link to a code repository. |
| Open Datasets | Yes | The task is digit classification on three datasets of 10 classes: MNIST, USPS and SVHN. |
| Dataset Splits | No | The paper specifies train/test splits for MNIST, USPS, and SVHN datasets (e.g., 'MNIST contains 60,000/10,000 train/test instances'), but does not explicitly state the use or size of a separate validation set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running its experiments (e.g., GPU/CPU models, memory specifications). |
| Software Dependencies | No | The paper mentions using 'neural networks' and 'DANN (Ganin et al., 2016)' but does not provide specific software dependencies with version numbers (e.g., Python, TensorFlow/PyTorch versions). |
| Experiment Setup | Yes | In our experiments, to ensure a fair comparison, we use the same network structure for all the experiments: 2 convolutional layers, one fully connected hidden layer, followed by a softmax output layer with 10 units. The convolution kernels in both layers are of size 5 5, with 10 and 20 channels, respectively. The hidden layer has 1280 units connected to 100 units before classification. For domain adaptation, we use the original DANN (Ganin et al., 2016) with gradient reversal implementation. The discriminator in DANN takes the output of convolutional layers as its feature input, followed by a 500 100 fully connected layer, and a one-unit binary classification output. |