Related papers: Online Adaptation to Label Distribution Shift

Distribution shift, a change in the statistical properties of data over time, poses a critical challenge for deep learning anomaly detection systems. Existing anomaly detection systems often struggle to adapt to these shifts. Specifically,…

We consider the problem of online learning in the presence of distribution shifts that occur at an unknown rate and of unknown intensity. We derive a new Bayesian online inference approach to simultaneously infer these distribution shifts…

Machine learning society has witnessed the emergence of a myriad of Out-of-Distribution (OoD) algorithms, which address the distribution shift between the training and the testing distribution by searching for a unified predictor or…

Conversion rate prediction is critical to many online applications such as digital display advertising. To capture dynamic data distribution, industrial systems often require retraining models on recent data daily or weekly. However, the…

Out-of-distribution (OOD) detection is crucial to modern deep learning applications by identifying and alerting about the OOD samples that should not be tested or used for making predictions. Current OOD detection methods have made…

Data distribution shift is a common problem in machine learning-powered smart city applications where the test data differs from the training data. Augmenting smart city applications with online machine learning models can handle this issue…

When deployed in the real world, machine learning models inevitably encounter changes in the data distribution, and certain -- but not all -- distribution shifts could result in significant performance degradation. In practice, it may make…

Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…

The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be…

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…

When deploying modern machine learning-enabled robotic systems in high-stakes applications, detecting distribution shift is critical. However, most existing methods for detecting distribution shift are not well-suited to robotics settings,…

We revisit the fundamental problem of learning with distribution shift, in which a learner is given labeled samples from training distribution $D$, unlabeled samples from test distribution $D'$ and is asked to output a classifier with low…

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…

Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference. While label distributions often exhibit imbalances in real-world scenarios, most previous TTA approaches…

Model-based offline reinforcement learning trains policies using pre-collected datasets and learned environment models, eliminating the need for direct real-world environment interaction. However, this paradigm is inherently challenged by…

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…

Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representations. Recent CLIP-based test-time adaptation methods further improve detection performance…

Test-time adaptation (TTA) is an effective approach to mitigate performance degradation of trained models when encountering input distribution shifts at test time. However, existing TTA methods often suffer significant performance drops…

In real-world scenarios, tabular data often suffer from distribution shifts that threaten the performance of machine learning models. Despite its prevalence and importance, handling distribution shifts in the tabular domain remains…

Federated learning achieves joint training of deep models by connecting decentralized data sources, which can significantly mitigate the risk of privacy leakage. However, in a more general case, the distributions of labels among clients are…