Related papers: Rethinking Time Series Domain Generalization via S…
Unsupervised domain adaptation methods seek to generalize effectively on unlabeled test data, especially when encountering the common challenge in time series data that distribution shifts occur between training and testing datasets. In…
We propose Domain Adaptation via Feature Refinement (DAFR2), a simple yet effective framework for unsupervised domain adaptation under distribution shift. The proposed method synergistically combines three key components: adaptation of…
The recent development of foundation models for time series data has generated considerable interest in using such models across a variety of applications. Although foundation models achieve state-of-the-art predictive performance, their…
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source…
This paper focuses on the problem of semi-supervised domain adaptation for time-series forecasting, which is underexplored in literatures, despite being often encountered in practice. Existing methods on time-series domain adaptation mainly…
To facilitate a wide-spread acceptance of AI systems guiding decision making in real-world applications, trustworthiness of deployed models is key. That is, it is crucial for predictive models to be uncertainty-aware and yield…
Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…
Intelligent medical diagnosis has shown remarkable progress based on the large-scale datasets with precise annotations. However, fewer labeled images are available due to significantly expensive cost for annotating data by experts. To fully…
The assumption that training and testing samples are generated from the same distribution does not always hold for real-world machine-learning applications. The procedure of tackling this discrepancy between the training (source) and…
Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize…
Domain generalization (DG) aims to learn domain-generalizable models from one or multiple source domains that can perform well in unseen target domains. Despite its recent progress, most existing work suffers from the misalignment between…
Heterogeneity in time series data is more pronounced than in vision or language, as temporal dynamics vary substantially across domains and tasks. Existing efforts on training time series foundation models (TSFMs) from scratch are often…
Pre-training on time series poses a unique challenge due to the potential mismatch between pre-training and target domains, such as shifts in temporal dynamics, fast-evolving trends, and long-range and short-cyclic effects, which can lead…
Distribution shifts between training and testing samples frequently occur in practice and impede model generalization performance. This crucial challenge thereby motivates studies on domain generalization (DG), which aim to predict the…
A key aspect of temporal domains is the ability to make predictions multiple time steps into the future, a process known as multi-step forecasting (MSF). At the core of this process is selecting a forecasting strategy, however, with no…
Astronomical time-series analysis faces a critical limitation: the scarcity of labeled observational data. We present a pre-training approach that leverages simulations, significantly reducing the need for labeled examples from real…
Geographic distribution shift arises when the distribution of locations on Earth in a training dataset is different from what is seen at inference time. Using standard empirical risk minimization (ERM) in this setting can lead to uneven…
Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in…
Why do deep networks generalize well? In contrast to classical generalization theory, we approach this fundamental question by examining not only inputs and outputs, but the evolution of internal features. Our study suggests a phenomenon of…
Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often…