Feature Transformers: A Unified Representation Learning Framework for Lifelong Learning

Hariharan Ravishankar, Rahul Venkataramani, Saihareesh Anamandra, Prasad Sudhakar

Abstract:

Despite the recent advances in representation learning, lifelong learning continues
to be one of the most challenging and unconquered problems. Catastrophic forgetting
and data privacy constitute two of the important challenges for a successful
lifelong learner. Further, existing techniques are designed to handle only specific
manifestations of lifelong learning, whereas a practical lifelong learner is expected
to switch and adapt seamlessly to different scenarios. In this paper, we present a
single, unified mathematical framework for handling the myriad variants of lifelong
learning, while alleviating these two challenges. We utilize an external memory
to store only the features representing past data and learn richer and newer
representations incrementally through transformation neural networks - feature
transformers. We define, simulate and demonstrate exemplary performance on a
realistic lifelong experimental setting using the MNIST rotations dataset, paving
the way for practical lifelong learners. To illustrate the applicability of our method
in data sensitive domains like healthcare, we study the pneumothorax classification
problem from X-ray images, achieving near gold standard performance.
We also benchmark our approach with a number of state-of-the art methods on
MNIST rotations and iCIFAR100 datasets demonstrating superior performance.

Keywords: continual learning, deep learning, lifelong learning, new task learning, representation learning

TL;DR: Single generic mathematical framework for lifelong learning paradigms with data privacy