BI-MAML: Balanced Incremental Approach for Meta Learning

06/12/2020
by   Yang Zheng, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/25/2020

iTAML: An Incremental Task-Agnostic Meta-learning Approach

Humans can continuously learn new knowledge as their experience grows. I...
research
02/11/2020

Incremental Learning for Metric-Based Meta-Learners

Majority of the modern meta-learning methods for few-shot classification...
research
03/17/2020

Incremental Object Detection via Meta-Learning

In a real-world setting, object instances from new classes may be contin...
research
06/17/2022

TKIL: Tangent Kernel Approach for Class Balanced Incremental Learning

When learning new tasks in a sequential manner, deep neural networks ten...
research
06/07/2023

Meta-Learning in Spiking Neural Networks with Reward-Modulated STDP

The human brain constantly learns and rapidly adapts to new situations b...
research
12/08/2020

Continual Adaptation of Visual Representations via Domain Randomization and Meta-learning

Most standard learning approaches lead to fragile models which are prone...
research
08/27/2022

Anti-Retroactive Interference for Lifelong Learning

Humans can continuously learn new knowledge. However, machine learning m...

Please sign up or login with your details

Forgot password? Click here to reset