Online Structured Meta-learning

Authors: Huaxiu Yao, Yingbo Zhou, Mehrdad Mahdavi, Zhenhui (Jessie) Li, Richard Socher, Caiming Xiong

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on three datasets demonstrate the effectiveness and interpretability of our proposed framework in the context of both homogeneous and heterogeneous tasks.
Researcher Affiliation Collaboration 1Pennsylvania State University, 2Salesforce Research
Pseudocode Yes Algorithm 1 Online Meta-learning Pipeline of OSML
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the described methodology.
Open Datasets Yes Here, we follow [10] and create a Rainbow MNIST dataset, which contains a sequence of tasks generated from the original MNIST dataset. ... The first dataset is generated from mini-Imagenet. ... We create the second dataset called Meta-dataset by following [37, 41].
Dataset Splits No The paper does not explicitly provide training/test/validation dataset splits. It mentions support and query sets within tasks, and a test set for evaluation, but no dedicated validation split.
Hardware Specification No No specific hardware details (like CPU/GPU models or memory) are provided for the experimental setup.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes Require: β1, β2, β3,β4, β5: learning rates ... We report hyperparameters and model structures in Appendix A.2.