Novelty detection in data streams is the task of detecting concepts that were not known prior,
in streams of data. Many machine learning algorithms have been proposed to detect these …

Composed image retrieval (CIR) is a new and flexible image retrieval paradigm, which can
retrieve the target image for a multimodal query, including a reference image and its …

Lifelong machine learning concerns the development of systems that continuously learn
from diverse tasks, incorporating new knowledge without forgetting the knowledge they have …

Seq2seq language generation models that are trained offline with multiple domains in a
sequential fashion often suffer from catastrophic forgetting. Lifelong learning has been …

Incremental learning plays a pivotal role in the context of online knowledge discovery, as it
encourages large models (LM) to learn and refresh knowledge continuously. Many …

Lifelong seq2seq language generation models are trained with multiple domains in a
lifelong learning manner, with data from each domain being observed in an online fashion. It …

When we execute the typical fine-tuning paradigm on continuously sequential tasks, the
model will suffer from the catastrophic forgetting problem (ie, the model tends to adjust old …

Abstract Multi-Label Stream Classification (MLSC) is the classification streaming examples
into multiple classes simultaneously. Since new classes may emerge during the streaming …

The ability to detect out-of-distribution (OOD) inputs is essential for safely deploying machine
learning models in an open world. Most existing research on OOD detection, and more …

Catastrophic forgetting poses a major challenge in continual learning where the old
knowledge is forgotten when the model is updated on new tasks. Existing solutions tend to …