ServiceNow Research

Continual Learning with self-selecting specialized modules through expansion and pruning


Continual learning (CL) aims to design algorithms that can learn from non-stationarystreams of stationary tasks without forgetting. Modularity is an appealing solution for this:given ameaningfuldecomposition of knowledge into modules, new tasks are learned throughrecombination of modules (compositionality), addition of modules, or/and updating theexisting modules. Forgetting can be mitigated through sparsity of module updates; transfercan be achieved through only updating relevant modules. Achieving modularity presents anumber of challenges, among others: (a) how to decompose task into re-usable modules –while related to sub-task discovery [3;11], this has a promise of increasing sample complexitythrough positive transfer and improved OOD generalization ability [6]; (b) how to routesamples through a set of modules when the routing mechanism can be subject to forgetting;(c) how to prune and add new modules to ensure enough capacity for learning new tasks.

Montreal AI Symposium (MAIS)
Alexandre Lacoste
Alexandre Lacoste
Research Scientist

Research Scientist at Human Decision Support located at Montreal, QC, Canada.