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 …

As a special case of machine learning, incremental learning can acquire useful knowledge
from incoming data continuously while it does not need to access the original data. It is …

Dataset condensation aims at reducing the network training effort through condensing a
cumbersome training set into a compact synthetic one. State-of-the-art approaches largely …

State-of-the-art deep neural networks are still struggling to address the catastrophic
forgetting problem in continual learning. In this paper, we propose one simple paradigm …

Humans have a natural instinct to identify unknown object instances in their environments.
The intrinsic curiosity about these unknown instances aids in learning about them, when the …

Online continual learning for image classification studies the problem of learning to classify
images from an online stream of data and tasks, where tasks may include new classes …

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 …

Coreset selection, which aims to select a subset of the most informative training samples, is
a long-standing learning problem that can benefit many downstream tasks such as data …

Responding to user data deletion requests, removing noisy examples, or deleting corrupted
training data are just a few reasons for wanting to delete instances from a machine learning …

Continual learning on graph data, which aims to accommodate new tasks over newly
emerged graph data while maintaining the model performance over existing tasks, is …