Online Continual Learning for Embedded Devices
This work addresses the need for efficient continual learning in applications like home robots and smartphones, but it is incremental as it studies existing methods rather than proposing new ones.
The paper tackled the problem of enabling real-time continual learning on embedded devices by evaluating existing online continual learning methods against criteria for on-device use, measuring performance, memory, compute, and generalization.
Real-time on-device continual learning is needed for new applications such as home robots, user personalization on smartphones, and augmented/virtual reality headsets. However, this setting poses unique challenges: embedded devices have limited memory and compute capacity and conventional machine learning models suffer from catastrophic forgetting when updated on non-stationary data streams. While several online continual learning models have been developed, their effectiveness for embedded applications has not been rigorously studied. In this paper, we first identify criteria that online continual learners must meet to effectively perform real-time, on-device learning. We then study the efficacy of several online continual learning methods when used with mobile neural networks. We measure their performance, memory usage, compute requirements, and ability to generalize to out-of-domain inputs.