Continuous Invariance Learning

Authors: LIN Yong, Fan Zhou, Lu Tan, Lintao Ma, Jianmeng Liu, Yansu HE, Yuan Yuan, Yu Liu, James Y. Zhang, Yujiu Yang, Hao Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results on both synthetic and real-world datasets (including data collected from production systems) show that CIL consistently outperforms strong baselines among all the tasks.
Researcher Affiliation Collaboration 1The Hong Kong University of Science and Technology, 2Ant Group, 3Rutgers University, 4Tsinghua University, 5Chinese University of Hong Kong, 6MIT CSAIL, 7Boston College
Pseudocode Yes Algorithm 1 CIL: Continuous Invariance Learning
Open Source Code No The paper does not provide an explicit statement about releasing source code or a direct link to a code repository.
Open Datasets Yes We conduct experiments on CMNIST (Arjovsky et al., 2019); House Price dataset from Kaggle; Insurance Fraud dataset on Kaggle; Wildtime-Yearbook (Yao et al., 2022).
Dataset Splits Yes The dataset is partitioned according to the built year, with the training dataset in the period [1900, 1950] and the test dataset in the period (1950, 2000].
Hardware Specification Yes All experiments are done on a server base on Alibaba Group Enterprise Linux Server release 7.2 (Paladin) system which has 2 GP100GL [Tesla P100 PCIe 16GB] GPU devices.
Software Dependencies No The paper specifies experimental parameters such as learning rates and epochs, but it does not list specific software dependencies with their version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes In this section, we provide the training and hyperparameter details for the experiments. All experiments are done on a server base on Alibaba Group Enterprise Linux Server release 7.2 (Paladin) system which has 2 GP100GL [Tesla P100 PCIe 16GB] GPU devices. LR: learning rate of the classification model Φ(x)), e.g. 1e-3. OLR: learning rate of the penalty model h(Φ(x)), g(Φ(x), y), e.g. 0.001. Steps: total number of epochs for the training process, e.g. 1500. Penalty Step: number of epochs when to introduce penalty, e.g. 500. Penalty Weight: the invariance penalty weight, e.g. 1000. We show the parameter values used for each dataset in Table 11.