Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms
Authors: Aneesh Komanduri, Yongkai Wu, Feng Chen, Xintao Wu
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically demonstrate that our framework induces highly disentangled causal factors, improves interventional robustness, and is compatible with counterfactual generation. |
| Researcher Affiliation | Academia | Aneesh Komanduri1 , Yongkai Wu2 , Feng Chen3 and Xintao Wu1 1University of Arkansas 2Clemson University 3University of Texas at Dallas {akomandu, xintaowu}@uark.edu, yongkaw@clemson.edu, feng.chen@utdallas.edu |
| Pseudocode | No | The paper describes the proposed framework and its components but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/Akomand/ICM-VAE. |
| Open Datasets | Yes | The Pendulum dataset [Yang et al., 2021] consists of causal variables with causal graph (pendulum angle shadow length, shadow position) and (light position shadow length, shadow position). The Flow dataset [Yang et al., 2021] consists of variables with causal graph (ball size water height), (hole position water flow), and (water height water flow). We also show experiments on a more complex 3D dataset of a robot arm interacting with colored buttons called Causal Circuit [Brehmer et al., 2022]... |
| Dataset Splits | No | For the Pendulum (6K training and 1K testing) and Flow (6K training and 2K testing) datasets... For the Causal Circuit dataset (35K training and 10K testing)... The paper specifies training and testing set sizes but does not explicitly mention a separate validation set. |
| Hardware Specification | No | No specific hardware details (e.g., GPU or CPU models, memory) used for running experiments were provided in the paper. |
| Software Dependencies | No | The paper describes the neural network architectures and hyperparameters but does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | For the Pendulum (6K training and 1K testing) and Flow (6K training and 2K testing) datasets, we linearly increase the β parameter throughout training from 0 to 1. We train for 9 × 10^3 steps using a batch size of 64. ... We set the learning rate to 0.001 for all experiments. |