Meta-learnt priors slow down catastrophic forgetting in neural networks

By Giacomo Spigler. 2019

11 citations recorded by the source corpus.

Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its (single-task) training distribution, and has thus no way to learn parameters (i.e., feature detectors or policies) that could be helpful to solve other tasks, and to limit future interference with the acquired knowledge, and thus catastrophic forgetting. Here we show that catastrophic forgetting can be mitigated in a meta-learning context, by exposing a neural network to multiple tasks in a sequential manner during training. Finally, we present SeqFOMAML, a meta-learning algorithm that implements these principles, and we evaluate it on sequential learning problems composed by Omniglot and MiniImageNet classification tasks.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “…for continual learning deployment at meta-test time by training the inner loop over a sequence of tasks (Kim et al., 2021a; Javed and White, 2019; Spigler, 2019; Beaulieu, Frati, Miconi, Lehman, Stanley, Clune, and Cheney, 2020; Caccia, Rodriguez, Ostapenko, Normandin, Lin, Caccia, Laradji,…”
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning (2020, methodology): “…for a dynamic Markov chain of other agent policies, we are leveraging an approach that has recently become popular for supervised learning called meta-continual learning (Riemer et al., 2019; Javed & White, 2019; Spigler, 2019; Beaulieu et al., 2020; Caccia et al., 2020; Gupta et al., 2020).”
Building a Subspace of Policies for Scalable Continual Learning (2022, background): “There is also a large body of work which leverages the shared structure of the tasks [50, 30, 25, 27, 1, 43], meta-learning [19, 44, 4, 8, 33, 52, 39], or generative models [35, 42, 41, 2] to improve CRL agents, but these are less related to CSP and not very competitive.”