Causal Representation Learning from Multiple Distributions: A General Setting

Authors: Kun Zhang, Shaoan Xie, Ignavier Ng, Yujia Zheng

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results verify our theoretical claims. and Simulation studies verified our theoretical findings.
Researcher Affiliation Collaboration 1Carnegie Mellon University 2Mohamed bin Zayed University of Artificial Intelligence. Acknowledgements: The authors would also like to acknowledge the support from NSF Grant 2229881, the National Institutes of Health (NIH) under Contract R01HL159805, and grants from Apple Inc., KDDI Research Inc., Quris AI, and Florin Court Capital.
Pseudocode No The paper describes the model and implementation details in text, but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statement about releasing open-source code or a link to a code repository for the methodology described.
Open Datasets No The paper states, 'we run experiments on the simulated data because the ground truth causal adjacency matrix and the latent variables across domains are available for simulated data.' However, it does not provide any specific access information (link, DOI, or citation to a public simulated dataset) for this data.
Dataset Splits No The paper mentions running experiments on simulated data but does not provide specific details on training, validation, or test dataset splits (e.g., percentages, sample counts, or cross-validation setup).
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions using frameworks like VAE and components like MLP, but it does not list any specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x, CUDA).
Experiment Setup No The paper describes general setup for simulations (e.g., 'noises are modulated with scaling random sampled from Unif[0.5, 2] and shifts are sampled from Unif[-2, 2]'), but it does not provide comprehensive details on specific hyperparameters (e.g., learning rate, batch size, number of epochs) or system-level training settings.