Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition
Keywords: Catastrophic Forgetting, Continual Learning, Tensor Decomposition
TL;DR: We propose a tensor decomposition based study of learning and forgetting dynamics across multiple importance-based continual learning methods and model architectures
Abstract: Continual learning (CL) has spurred the
development of several methods aimed at
consolidating previous knowledge across
sequential learning. Yet, the evaluations of
these methods has primarily focused on the
final output, such as changes in the accuracy
of predicted classes, overlooking the issue
of representational forgetting within the
model. In this paper, we propose a novel
representation-based evaluation framework for
CL models. This approach involves gathering
internal representations from throughout the
continual learning process and formulating
three-dimensional tensors. The tensors are
formed by stacking representations, such as
layer activations, generated from several inputs
and model snapshots, throughout the learning
process. By conducting tensor component
analysis (TCA), we aim to uncover meaningful
patterns about how the internal representations
evolve, expecting to highlight the merits or
shortcomings of examined cl strategies. We
plan to conduct our analyses across different
model architectures and importance-based
continual learning strategies, with a curated task
selection, allowing us to gain insight whether
any observed patterns are consistently replicable.
Submission Number: 8
Loading