Cost-effectively Identifying Causal Effects When Only Response Variable is Observable
Authors: Tian-Zuo Wang, Xi-Zhu Wu, Sheng-Jun Huang, Zhi-Hua Zhou
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we apply our approach on both synthetic datasets and real-world data. |
| Researcher Affiliation | Academia | 1National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China 2College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China. |
| Pseudocode | Yes | Algorithm 1 Get the minimal parental back-door admissible set for (Xi, Y )... Algorithm 2 Update the Graph... Algorithm 3 ACI (Active Causal Effect Identification) |
| Open Source Code | No | The paper states 'The code is developed based on R package pcalg (Kalisch et al., 2012)' but does not provide a link or explicit statement for their own open-source code for the methodology. |
| Open Datasets | Yes | In this part, we apply our approach on a dataset used in causal discovery with both observational and interventional data (Sachs et al., 2005). |
| Dataset Splits | No | The paper mentions generating 2500 samples as observational data and 1000 samples for intervention, but it does not specify explicit training/validation/test splits for model evaluation. |
| Hardware Specification | No | The paper does not provide any specific hardware details used for running the experiments. |
| Software Dependencies | No | The paper mentions 'R package pcalg (Kalisch et al., 2012)' but does not provide a specific version number for the pcalg software itself. |
| Experiment Setup | Yes | We generate 100 linear structural equation models with the number of variables p = 30 and noise ϵ N(0, 1p). The variable with the maximum degree is set to be the response variable. For each model, we generate 2500 samples as observational data. Our experiments begin from the essential graph. In each intervention, we have 1000 samples with the intervention value set to 2. |