Don't forget, there is more than forgetting: new metrics for Continual Learning
This addresses the problem of incomplete evaluation for researchers and practitioners in continual learning, though it is incremental as it builds on existing metrics.
The authors tackled the lack of consensus in evaluating continual learning algorithms by proposing new metrics beyond just forgetting, including accuracy over time and knowledge transfer, and demonstrated their approach on the iCIFAR-100 benchmark.
Continual learning consists of algorithms that learn from a stream of data/tasks continuously and adaptively thought time, enabling the incremental development of ever more complex knowledge and skills. The lack of consensus in evaluating continual learning algorithms and the almost exclusive focus on forgetting motivate us to propose a more comprehensive set of implementation independent metrics accounting for several factors we believe have practical implications worth considering in the deployment of real AI systems that learn continually: accuracy or performance over time, backward and forward knowledge transfer, memory overhead as well as computational efficiency. Drawing inspiration from the standard Multi-Attribute Value Theory (MAVT) we further propose to fuse these metrics into a single score for ranking purposes and we evaluate our proposal with five continual learning strategies on the iCIFAR-100 continual learning benchmark.