Meta-learning with an Adaptive Task Scheduler

Authors: Huaxiu Yao, Yu Wang, Ying Wei, Peilin Zhao, Mehrdad Mahdavi, Defu Lian, Chelsea Finn

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Under the setting of meta-learning with noise and limited budgets, ATS improves the performance on both mini Image Net and a real-world drug discovery benchmark by up to 13% and 18%, respectively, compared to state-of-the-art task schedulers. In this section, we empirically demonstrate the effectiveness of the proposed ATS through comprehensive experiments on both regression and classification problems.
Researcher Affiliation Collaboration 1Stanford University, 2University of Science and Technology, 3 Tencent AI Lab 4Pennsylvania State University, 5City University of Hong Kong
Pseudocode Yes Algorithm 1 Meta-training Process with ATS
Open Source Code No We will open-source the code once the paper is accepted.
Open Datasets Yes First, we use mini Imagenet as the classification dataset, where we apply the conventional N-way, Kshot setting to create tasks [4]. ... The second dataset aims to predict the activity of drug compounds [21]... These datasets are public datasets and we have cited the related reference.
Dataset Splits Yes There are 4,276 assays in total, and we split 4,100 / 76 / 100 tasks for meta-training / validation / testing, respectively.
Hardware Specification Yes All experiments are conducted on an NVIDIA RTX 2080 Ti GPU.
Software Dependencies No The paper mentions implementing the model using PyTorch but does not specify its version or any other software dependencies with version numbers.
Experiment Setup Yes We use the Adam optimizer with a learning rate of 0.001 and set the momentum to 0.9 and 0.999. The batch size is set to 4 tasks... The number of meta-training iterations is set to 60000. For the inner loop, we perform 5 gradient descent steps, and the learning rate α is set to 0.01. For the neural scheduler, the learning rate for φ is set to 0.001 and the number of layers of the MLP is 2, with hidden size 64.