Related papers: Online Feature Updates Improve Online (Generalized…

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution…

We study the well-motivated problem of online distribution shift in which the data arrive in batches and the distribution of each batch can change arbitrarily over time. Since the shifts can be large or small, abrupt or gradual, the length…

Feature evolvable learning has been widely studied in recent years where old features will vanish and new features will emerge when learning with streams. Conventional methods usually assume that a label will be revealed after prediction at…

Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched label distribution. Existing approaches that seek to repair the…

Real-world data sets often exhibit temporal dynamics characterized by evolving data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can significantly diminish a model's predictive accuracy. Furthermore,…

Models trained with offline data often suffer from continual distribution shifts and expensive labeling in changing environments. This calls for a new online learning paradigm where the learner can continually adapt to changing environments…

In many real-world applications, researchers aim to deploy models trained in a source domain to a target domain, where obtaining labeled data is often expensive, time-consuming, or even infeasible. While most existing literature assumes…

We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy, which measures the accuracy of the model on the immediate next few samples. However, we show that…

With the development of generative artificial intelligence, new forgery methods are rapidly emerging. Social platforms are flooded with vast amounts of unlabeled synthetic data and authentic data, making it increasingly challenging to…

We consider the problem of user-adaptive 3D gaze estimation. The performance of person-independent gaze estimation is limited due to interpersonal anatomical differences. Our goal is to provide a personalized gaze estimation model…

Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from performance…

Online continual learning, the process of training models on streaming data, has gained increasing attention in recent years. However, a critical aspect often overlooked is the label delay, where new data may not be labeled due to slow and…

Multi-label data stream usually contains noisy labels in the real-world applications, namely occuring in both relevant and irrelevant labels. However, existing online multi-label classification methods are mostly limited in terms of label…

Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. We propose a surprisingly simple algorithm that adaptively balances its regret and its number of label queries in…

Distributed and federated learning are important tools for high-dimensional classification of large datasets. To reduce computational costs and overcome the curse of dimensionality, feature screening plays a pivotal role in eliminating…

A self-adaptive system can modify its own structure and behavior at runtime based on its perception of the environment, of itself and of its requirements. To develop a self-adaptive system, software developers codify knowledge about the…

Out-of-distribution (OOD) detection, which aims to distinguish unknown classes from known classes, has received increasing attention recently. A main challenge within is the unavailable of samples from the unknown classes in the training…

Traditional feature selections need to know the feature space before learning, and online streaming feature selection (OSFS) is proposed to process streaming features on the fly. Existing methods divide features into relevance or…

Semi-supervised multi-label feature selection has recently been developed to solve the curse of dimensionality problem in high-dimensional multi-label data with certain samples missing labels. Although many efforts have been made, most…

The loss function plays an important role in optimizing the performance of a learning system. A crucial aspect of the loss function is the assignment of sample weights within a mini-batch during loss computation. In the context of continual…