Task agnostic continual learning with Pairwise layer architecture
This addresses the challenge of continual learning for AI systems that need to adapt to streaming data without explicit task information, though it is incremental as it builds on existing static architecture methods.
The paper tackled the problem of task-agnostic continual learning without using memory replay, parameter isolation, or regularization techniques that rely on task boundaries, by proposing a static architecture with a pairwise interaction layer. The result showed competitive performance in MNIST and FashionMNIST-based continual image classification experiments in an online streaming setup without task labels or boundaries.
Most of the dominant approaches to continual learning are based on either memory replay, parameter isolation, or regularization techniques that require task boundaries to calculate task statistics. We propose a static architecture-based method that doesn't use any of these. We show that we can improve the continual learning performance by replacing the final layer of our networks with our pairwise interaction layer. The pairwise interaction layer uses sparse representations from a Winner-take-all style activation function to find the relevant correlations in the hidden layer representations. The networks using this architecture show competitive performance in MNIST and FashionMNIST-based continual image classification experiments. We demonstrate this in an online streaming continual learning setup where the learning system cannot access task labels or boundaries.