Continual Feature Selection: Spurious Features in Continual Learning
This work addresses the problem of performance degradation in continual learning for AI researchers, offering a novel perspective by focusing on spurious features, though it is incremental in nature.
The paper investigates how spurious features affect continual learning algorithms, showing that these algorithms rely on non-generalizable features, with local spurious features being a major cause of performance decline alongside catastrophic forgetting.
Continual Learning (CL) is the research field addressing learning without forgetting when the data distribution is not static. This paper studies spurious features' influence on continual learning algorithms. We show that continual learning algorithms solve tasks by selecting features that are not generalizable. Our experiments highlight that continual learning algorithms face two related problems: (1) spurious features and (2) local spurious features. The first one is due to a covariate shift between training and testing data, while the second is due to the limited access to data at each training step. We study (1) through a consistent set of continual learning experiments varying spurious correlation amount and data distribution support. We show that (2) is a major cause of performance decrease in continual learning along with catastrophic forgetting. This paper presents a different way of understanding performance decrease in continual learning by highlighting the influence of (local) spurious features in algorithms capabilities.