Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
It addresses the problem of evaluating and improving incremental learning algorithms for machine learning practitioners, though it is incremental as it builds on existing methods like EWC and Path Integral.
The paper tackles the lack of precise definitions and metrics in incremental learning (IL) by introducing two new metrics to quantify forgetting and intransigence, and presents RWalk, which achieves superior accuracy and better trade-offs on MNIST and CIFAR-100 datasets.
Incremental learning (IL) has received a lot of attention recently, however, the literature lacks a precise problem definition, proper evaluation settings, and metrics tailored specifically for the IL problem. One of the main objectives of this work is to fill these gaps so as to provide a common ground for better understanding of IL. The main challenge for an IL algorithm is to update the classifier whilst preserving existing knowledge. We observe that, in addition to forgetting, a known issue while preserving knowledge, IL also suffers from a problem we call intransigence, inability of a model to update its knowledge. We introduce two metrics to quantify forgetting and intransigence that allow us to understand, analyse, and gain better insights into the behaviour of IL algorithms. We present RWalk, a generalization of EWC++ (our efficient version of EWC [Kirkpatrick2016EWC]) and Path Integral [Zenke2017Continual] with a theoretically grounded KL-divergence based perspective. We provide a thorough analysis of various IL algorithms on MNIST and CIFAR-100 datasets. In these experiments, RWalk obtains superior results in terms of accuracy, and also provides a better trade-off between forgetting and intransigence.