Don't forget, there is more than forgetting: new metrics for Continual Learning

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download
Contributor : Natalia Díaz-Rodríguez <>
Submitted on : Tuesday, December 11, 2018 - 2:39:17 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on : Tuesday, March 12, 2019 - 3:19:48 PM


Files produced by the author(s)


  • HAL Id : hal-01951488, version 1


Natalia Díaz-Rodríguez, Vincenzo Lomonaco, David Filliat, Davide Maltoni. Don't forget, there is more than forgetting: new metrics for Continual Learning. Workshop on Continual Learning, NeurIPS 2018 (Neural Information Processing Systems, Dec 2018, Montreal, Canada. ⟨hal-01951488⟩



Record views


Files downloads