Tomoharu Iwata

Meta-Active Learning for Node Response Prediction in Graphs

2020 · arXiv (Cornell University)

Meta-learning is an important approach to improve machine learning performance with a limited number of observations for target tasks. However, when observations are unbalancedly obtained, it is difficult to improve the performance even with meta-learning …

Meta-learning for Out-of-Distribution Detection via Density Estimation in Latent Space

2022 · arXiv (Cornell University)

Many neural network-based out-of-distribution (OoD) detection methods have been proposed. However, they require many training data for each target task. We propose a simple yet effective meta-learning method to detect OoD with small in-distribution data …