Stable Adversarial Learning under Distributional Shifts
Authors: Jiashuo Liu, Zheyan Shen, Peng Cui, Linjun Zhou, Kun Kuang, Bo Li, Yishi Lin8662-8670
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical studies on both simulation and real datasets validate the effectiveness of our method in terms of uniformly good performance across unknown distributional shifts.In this section, we validate the effectiveness of our method on simulation data and real-world data. |
| Researcher Affiliation | Collaboration | Jiashuo Liu1, Zheyan Shen1, Peng Cui1, Linjun Zhou1, Kun Kuang2, Bo Li1, Yishi Lin3 1Tsinghua University 2Zhejiang University 3 Tencent |
| Pseudocode | No | The paper describes the algorithm steps in text, such as 'Details of the algorithm are delineated below. We first will introduce the optimization of model s parameter in section , then the transportation cost function learning procedure in section .' but does not include a structured pseudocode or algorithm block. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code, nor does it include links to a code repository. |
| Open Datasets | Yes | In this task we use the Adult dataset(Dua and Graff 2017) which involves predicting personal income levels...In this experiment, we use a real-world regression dataset (Kaggle) of house sales prices from King County, USA... 1https://www.kaggle.com/c/house-prices-advanced-regressiontechniques/data |
| Dataset Splits | Yes | For fairness, we search the hyperparameter λ in {0.01, 0.1, . . . , 1e0, 1e1, . . . , 1e4} for IRM and the hyper-parameter ρ in {1, 5, 10, 20, 50, 80, 100} for WDRL, and select the best hyper-parameter according to the validation performance. In training, we train all methods on the first and second decade where built year [1900, 1910) and [1910, 1920) respectively and validate on 100 data points sampled from the second period. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU or CPU models, or any information about the computing resources used for experiments. |
| Software Dependencies | No | The paper does not provide specific software dependency details with version numbers, such as programming languages, libraries, or frameworks used for implementation. |
| Experiment Setup | Yes | For fairness, we search the hyperparameter λ in {0.01, 0.1, . . . , 1e0, 1e1, . . . , 1e4} for IRM and the hyper-parameter ρ in {1, 5, 10, 20, 50, 80, 100} for WDRL, and select the best hyper-parameter according to the validation performance. We first set the radius for WDRL and SAL to be 20.0 |