Hacking Task Confounder in Meta-Learning

Authors: Jingyao Wang, Yi Ren, Zeen Song, Jianqi Zhang, Changwen Zheng, Wenwen Qiang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various benchmark datasets demonstrate that our work achieves state-of-the-art (SOTA) performance.
Researcher Affiliation Academia 1Institute of Software Chinese Academy of Sciences 2University of Chinese Academy of Sciences {wangjingyao23, renyi, songzeen, zhangjianqi, changwen, qiangwenwen}@iscas.ac.cn
Pseudocode Yes The pseudocode and pipeline of Meta CRL are shown in Appendix B.
Open Source Code Yes The code is provided in https://github. com/Wang Jingyao07/Meta CRL.
Open Datasets Yes Specifically, we first randomly sample 400 tasks from mini Image Net dataset [Vinyals et al., 2016] and divide them into a training set and a test set.
Dataset Splits No The paper mentions dividing tasks into a training set and a test set for mini ImageNet and does not explicitly state a separate validation split or its proportions.
Hardware Specification No The paper does not provide specific hardware details such as CPU, GPU models, or memory specifications used for running the experiments.
Software Dependencies No The paper mentions implementing methods and using datasets but does not list specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup Yes In this experiment, we set λ1 and λ2 to 0.4 and 0.2. (from Sinusoid Regression section) / In this experiment, we set λ1 and λ2 to 0.5 and 0.35, respectively. (from Image Classification section) / In this experiment, λ1 and λ2 are both set to 0.3 (from Drug Activity Prediction section) / In this experiment, the values of λ1 and λ2 are set to 0.3 and 0.2 (from Pose Prediction section).