相关论文: Environment-Aware Dynamic Graph Learning for Out-o…

Graph neural networks (GNNs), especially dynamic GNNs, have become a research hotspot in spatio-temporal forecasting problems. While many dynamic graph construction methods have been developed, relatively few of them explore the causal…

Graph learning has been crucial to many real-world tasks, but they are often studied with a closed-world assumption, with all possible labels of data known a priori. To enable effective graph learning in an open and noisy environment, it is…

Most deep-learning-based image classification methods assume that all samples are generated under an independent and identically distributed (IID) setting. However, out-of-distribution (OOD) generalization is more common in practice, which…

Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these…

Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically when encountering out-of-distribution (OoD) data, i.e., when…

Accurately modelling human attention is essential for numerous computer vision applications, particularly in the domain of automotive safety. Existing methods typically collapse gaze into saliency maps or scanpaths, treating gaze dynamics…

Air quality prediction is a typical spatio-temporal modeling problem, which always uses different components to handle spatial and temporal dependencies in complex systems separately. Previous models based on time series analysis and…

Computer vision applications predict on digital images acquired by a camera from physical scenes through light. However, conventional robustness benchmarks rely on perturbations in digitized images, diverging from distribution shifts…

Improving the accuracy of deep neural networks (DNNs) on out-of-distribution (OOD) data is critical to an acceptance of deep learning (DL) in real world applications. It has been observed that accuracies on in-distribution (ID) versus OOD…

In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety and generalize to new domains. However, existing methods often struggle to distinguish between…

Industrial carbon emissions are a major driver of climate change, yet modeling these emissions is challenging due to multicollinearity among factors and complex interdependencies across sectors and time. We propose a novel graph-based deep…

Recent research on deep graph learning has shifted from static to dynamic graphs, motivated by the evolving behaviors observed in complex real-world systems. However, the temporal extension in dynamic graphs poses significant data…

Out-of-distribution detection (OOD) is a pivotal task for real-world applications that trains models to identify samples that are distributionally different from the in-distribution (ID) data during testing. Recent advances in AI,…

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these…

Out-of-distribution (OOD) detection aims to identify test examples that do not belong to the training distribution and are thus unlikely to be predicted reliably. Despite a plethora of existing works, most of them focused only on the…

Existing methods for graph out-of-distribution (OOD) detection typically depend on training graph neural network (GNN) classifiers using a substantial amount of labeled in-distribution (ID) data. However, acquiring high-quality labeled…

Temporal domain generalization is a promising yet extremely challenging area where the goal is to learn models under temporally changing data distributions and generalize to unseen data distributions following the trends of the change. The…

This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data…

Often, deep network models are purely inductive during training and while performing inference on unseen data. Thus, when such models are used for predictions, it is well known that they often fail to capture the semantic information and…

Detecting out-of-distribution (OOD) inputs is a principal task for ensuring the safety of deploying deep-neural-network classifiers in open-set scenarios. OOD samples can be drawn from arbitrary distributions and exhibit deviations from…