Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to Adapt

An increasing interest in learning to forecast for time-series of high-dimensional observations is the ability to adapt to systems with diverse underlying dynamics. Access to observations that define a stationary distribution of these systems is often unattainable, as the underlying dynamics may change over time. Naively training or retraining models at each shift may lead to catastrophic forgetting about previously-seen systems. We present a new continual meta-learning (CML) framework to realize continual slow-and fast adaptation of latent dynamics (CoS-Fan). We leverage a feed-forward meta-model to infer what the current system is and how to adapt a latent dynamics function to it, enabling fast adaptation to specific dynamics. We then develop novel strategies to automatically detect when a shift of data distribution occurs, with which to identify its underlying dynamics and its relation with previously-seen dynamics. In combination with fixed-memory experience replay mechanisms, this enables continual slow update of the what-how meta-model. Empirical studies demonstrated that both the metaand continual-learning component was critical for learning to forecast across nonstationary distributions of diverse dynamics systems, and the feed-forward metamodel combined with task-aware/-relational continual learning strategies significantly outperformed existing CML alternatives.

CoSFan breaks through the reliance of mainstream CML methods on MAML-variants, demonstrating the effectiveness of feed-forward meta-models, combined with automatic task identification and task-relation modeling, in fully leveraging bi-level meta-optimization over non-stationary task distributions. We position our work against prior CML works in Fig. 1B. Discussion of other related areas, e.g., CL and meta-continual-learning, and other algorithmic priors is included in Appendix A.