Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning
arXiv:2012.01227
Abstract
Active learning is widely used to reduce labeling effort and training time by repeatedly querying only the most beneficial samples from unlabeled data. In real-world problems where data cannot be stored indefinitely due to limited storage or privacy issues, the query selection and the model update should be performed as soon as a new data sample is observed. Various online active learning methods have been studied to deal with these challenges; however, there are difficulties in selecting representative query samples and updating the model efficiently without forgetting. In this study, we propose Message Passing Adaptive Resonance Theory (MPART) that learns the distribution and topology of input data online. Through message passing on the topological graph, MPART actively queries informative and representative samples, and continuously improves the classification performance using both labeled and unlabeled data. We evaluate our model in stream-based selective sampling scenarios with comparable query selection strategies, showing that MPART significantly outperforms competitive models.
arXiv commentAccepted to ICML 2021
References in corpus (6)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Bootstrap your own latent: A new approach to self-supervised Learning
- Graph Neural Networks: A Review of Methods and Applications
- Deep Bayesian Active Learning with Image Data
- Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
- Label Propagation Adaptive Resonance Theory for Semi-supervised Continuous Learning