Distribution shifts over time are common in real-world machine-learning applications. This
scenario is formulated as Evolving Domain Generalization (EDG), where models aim to …

Temporal Domain Generalization (TDG) addresses the challenge of training predictive
models under temporally varying data distributions. Traditional TDG approaches typically …

Although recent advances in machine learning have shown its success to learn from
independent and identically distributed (IID) data, it is vulnerable to out-of-distribution (OOD) …

Enabling deep models to generalize in non-stationary environments is vital for real-world
machine learning, as data distributions are often found to continually change. Recently …

In many machine learning tasks, data is inherently sequential. Most existing algorithms learn
from sequential data in an auto-regressive manner, which predicts the next unseen data …