Explanation Consistency Training: Facilitating Consistency-Based Semi-Supervised Learning with Interpretability
Authors: Tao Han, Wei-Wei Tu, Yu-Feng Li7639-7646
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on real-world data sets validate the highly competitive performance and better explanation of the proposed algorithms. |
| Researcher Affiliation | Collaboration | 1National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China 24Paradigm Inc., Beijing, China |
| Pseudocode | No | The paper describes the methods using mathematical formulations and descriptive text, but it does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any statement about making its source code publicly available or provide a link to a code repository. |
| Open Datasets | Yes | Datasets We test model performances on the benchmark datasets of MNIST (Le Cun, Cortes, and Burges 2010) and Fashion-MNIST (Xiao, Rasul, and Vollgraf 2017). ... We use the biographies texts collected by (De Arteaga et al. 2019) |
| Dataset Splits | Yes | Each experiment is repeated for 5 times with different labeled data numbers of {100, 200, 1,000} and 1,000 data for validation. |
| Hardware Specification | No | The paper states "All the experiments are conducted with Pytorch1." but does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used for these experiments. |
| Software Dependencies | No | The paper mentions that "All the experiments are conducted with Pytorch1." (with a footnote linking to pytorch.org) but does not specify the version number of PyTorch or any other software dependencies. |
| Experiment Setup | Yes | The optimizer is SGD with a decayed learning rate, 1 e 4 weight decay, and the momentum is 0.9. All the models are trained for 50 epochs on unlabeled data, so it is close to 30,000 batch iterations. The perturbation extend is set to ϵ = 2.0, and the value of α, λ are set according to the magnitude of their losses without heavy tuning. |