To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

In contrast to batch learning where all training data is available at once, continual learning
represents a family of methods that accumulate knowledge and learn continuously with data …

Continual learning aims to empower artificial intelligence with strong adaptability to the real
world. For this purpose, a desirable solution should properly balance memory stability with …

The staple of human intelligence is the capability of acquiring knowledge in a continuous
fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub …

Continual learning (CL) aims to develop techniques by which a single model adapts to an
increasing number of tasks encountered sequentially, thereby potentially leveraging …

In federated learning, a strong global model is collaboratively learned by aggregating
clients' locally trained models. Although this precludes the need to access clients' data …

Popular deep-learning models in the field of image classification suffer from catastrophic
forgetting—models will forget previously acquired skills when learning new ones …

The backpropagation networks are notably susceptible to catastrophic forgetting, where
networks tend to forget previously learned skills upon learning new ones. To address such …

Abstract Domain generalization is the task of learning models that generalize to unseen
target domains. We propose a simple yet effective method for domain generalization, named …

The goal of continual learning (CL) is to continuously learn new tasks without forgetting
previously learned old tasks. To alleviate catastrophic forgetting, gradient projection based …