iTAML: An Incremental Task-Agnostic Meta-learning Approach

03/25/2020
by   Jathushan Rajasegaran, et al.
4

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be avoided by learning a set of generalized parameters, that are neither specific to old nor new tasks. In this pursuit, we introduce a novel meta-learning approach that seeks to maintain an equilibrium between all the encountered tasks. This is ensured by a new meta-update rule which avoids catastrophic forgetting. In comparison to previous meta-learning techniques, our approach is task-agnostic. When presented with a continuum of data, our model automatically identifies the task and quickly adapts to it with just a single update. We perform extensive experiments on five datasets in a class-incremental setting, leading to significant improvements over the state of the art methods (e.g., a 21.3 Specifically, on large-scale datasets that generally prove difficult cases for incremental learning, our approach delivers absolute gains as high as 19.1 7.4

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/17/2020

Incremental Object Detection via Meta-Learning

In a real-world setting, object instances from new classes may be contin...
research
06/12/2020

BI-MAML: Balanced Incremental Approach for Meta Learning

We present a novel Balanced Incremental Model Agnostic Meta Learning sys...
research
09/20/2018

Learning Quickly to Plan Quickly Using Modular Meta-Learning

Multi-object manipulation problems in continuous state and action spaces...
research
08/27/2022

Anti-Retroactive Interference for Lifelong Learning

Humans can continuously learn new knowledge. However, machine learning m...
research
10/07/2020

A Survey of Deep Meta-Learning

Deep neural networks can achieve great successes when presented with lar...
research
06/16/2023

DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting

Stock trend forecasting is a fundamental task of quantitative investment...
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...

Please sign up or login with your details

Forgot password? Click here to reset