Evolving Domain Generalization
This work addresses domain generalization for scenarios with non-stationary task distributions, which is incremental as it builds on prior methods by incorporating task evolution.
The paper tackles the problem of domain generalization in evolving environments, where existing methods fail due to ignoring task relationships, and proposes a new formulation and method that achieves effective generalization to unseen tasks by modeling evolving patterns.
Domain generalization aims to learn a predictive model from multiple different but related source tasks that can generalize well to a target task without the need of accessing any target data. Existing domain generalization methods ignore the relationship between tasks, implicitly assuming that all the tasks are sampled from a stationary environment. Therefore, they can fail when deployed in an evolving environment. To this end, we formulate and study the \emph{evolving domain generalization} (EDG) scenario, which exploits not only the source data but also their evolving pattern to generate a model for the unseen task. Our theoretical result reveals the benefits of modeling the relation between two consecutive tasks by learning a globally consistent directional mapping function. In practice, our analysis also suggests solving the DDG problem in a meta-learning manner, which leads to \emph{directional prototypical network}, the first method for the DDG problem. Empirical evaluation of both synthetic and real-world data sets validates the effectiveness of our approach.