Actively Identifying Causal Effects with Latent Variables Given Only Response Variable Observable

Authors: Tian-Zuo Wang, Zhi-Hua Zhou

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Theoretical analysis and empirical studies validate the effectiveness and efficiency of our proposed approach. In this section, we apply our method on synthetic dataset to validate the effectiveness and efficiency of the proposed method.
Researcher Affiliation Academia Tian-Zuo Wang1,2 and Zhi-Hua Zhou1 1 National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China, 2 Pazhou Lab, Guangzhou, 510330, China. {wangtz, zhouzh}@lamda.nju.edu.cn
Pseudocode Yes Algorithm 1 Find all possible MCSs in P and Algorithm 2 ACIC (ACtive target effect Identification with latent Confounding)
Open Source Code No The paper states 'The code is developed based on R package pcalg [21]' but does not explicitly state that their own implementation code is being made available or provide a link to it.
Open Datasets No The paper states 'We generate 100 random causal graphs... We generate linear Gaussian data according to the causal graph.' indicating synthetic data is used, but does not provide concrete access information (link, DOI, specific citation for a public dataset) for this data.
Dataset Splits No The paper uses a 'synthetic dataset' and describes generating data but does not provide specific details on how the data is split into training, validation, or test sets for reproduction.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments.
Software Dependencies No The paper states 'The code is developed based on R package pcalg [21]' but does not provide a specific version number for the pcalg package or any other software dependency.
Experiment Setup Yes In each graph, there are p = 15 variables and an edge occurs between two variables with probability 0.3. We randomly take 3 variables as latent confounders. And the last observed variable in the causal order is set to the response variable. In our method, we adopt a greedy strategy to select the intervention variable. τ is a pre-set threshold.