English

BI-MAML: Balanced Incremental Approach for Meta Learning

Machine Learning 2020-06-16 v1 Computer Vision and Pattern Recognition Robotics Neurons and Cognition Machine Learning

Abstract

We present a novel Balanced Incremental Model Agnostic Meta Learning system (BI-MAML) for learning multiple tasks. Our method implements a meta-update rule to incrementally adapt its model to new tasks without forgetting old tasks. Such a capability is not possible in current state-of-the-art MAML approaches. These methods effectively adapt to new tasks, however, suffer from 'catastrophic forgetting' phenomena, in which new tasks that are streamed into the model degrade the performance of the model on previously learned tasks. Our system performs the meta-updates with only a few-shots and can successfully accomplish them. Our key idea for achieving this is the design of balanced learning strategy for the baseline model. The strategy sets the baseline model to perform equally well on various tasks and incorporates time efficiency. The balanced learning strategy enables BI-MAML to both outperform other state-of-the-art models in terms of classification accuracy for existing tasks and also accomplish efficient adaption to similar new tasks with less required shots. We evaluate BI-MAML by conducting comparisons on two common benchmark datasets with multiple number of image classification tasks. BI-MAML performance demonstrates advantages in both accuracy and efficiency.

Keywords

Cite

@article{arxiv.2006.07412,
  title  = {BI-MAML: Balanced Incremental Approach for Meta Learning},
  author = {Yang Zheng and Jinlin Xiang and Kun Su and Eli Shlizerman},
  journal= {arXiv preprint arXiv:2006.07412},
  year   = {2020}
}

Comments

Please see associated video at: https://youtu.be/4qlb-iG5SFo

R2 v1 2026-06-23T16:17:18.357Z