相关论文: Scaling Up Temporal Domain Generalization via Temp…

Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image classification tasks, its application to time-series…

We derive generalization error bounds for traditional time-series forecasting models. Our results hold for many standard forecasting tools including autoregressive models, moving average models, and, more generally, linear state-space…

Entity alignment (EA) aims to find entities in different knowledge graphs (KGs) that refer to the same object in the real world. Recent studies incorporate temporal information to augment the representations of KGs. The existing methods for…

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…

Despite their immense success in numerous fields, machine and deep learning systems have not yet been able to firmly establish themselves in mission-critical applications in healthcare. One of the main reasons lies in the fact that when…

Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. Existing approaches have achieved notable advancements in…

Traditional test-time adaptation (TTA) methods face significant challenges in adapting to dynamic environments characterized by continuously changing long-term target distributions. These challenges primarily stem from two factors:…

Recent studies have proven that DNNs, unlike human vision, tend to exploit texture information rather than shape. Such texture bias is one of the factors for the poor generalization performance of DNNs. We observe that the texture bias…

Supervised learning results typically rely on assumptions of i.i.d. data. Unfortunately, those assumptions are commonly violated in practice. In this work, we tackle such problem by focusing on domain generalization: a formalization where…

Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation.…

We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs. TGB datasets are of large scale,…

This paper proposes a novel batch normalization strategy for test-time adaptation. Recent test-time adaptation methods heavily rely on the modified batch normalization, i.e., transductive batch normalization (TBN), which calculates the mean…

Data augmentation is a popular tool for single source domain generalization, which expands the source domain by generating simulated ones, improving generalization on unseen target domains. In this work, we show that the performance of such…

Despite significant advances in deep learning, models often struggle to generalize well to new, unseen domains, especially when training data is limited. To address this challenge, we propose a novel approach for distribution-aware latent…

Domain Generalization (DG) is a fundamental challenge for machine learning models, which aims to improve model generalization on various domains. Previous methods focus on generating domain invariant features from various source domains.…

Machine learning models often struggle to generalize across domains with varying data distributions, such as differing noise levels, leading to degraded performance. Traditional strategies like personalized training, which trains separate…

Test-time domain adaptation aims to adapt a source pre-trained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems…

Given that Neural Networks generalize unreasonably well in the IID setting (with benign overfitting and betterment in performance with more parameters), OOD presents a consistent failure case to better the understanding of how they learn.…

Predicting missing facts for temporal knowledge graphs (TKGs) is a fundamental task, called temporal knowledge graph completion (TKGC). One key challenge in this task is the imbalance in data distribution, where facts are unevenly spread…

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained…