Exgc: Bridging efficiency and explainability in graph condensation
Graph representation learning on vast datasets, like web data, has made significant strides.
However, the associated computational and storage overheads raise concerns. In sight of …
However, the associated computational and storage overheads raise concerns. In sight of …
Spatiotemporal graph neural networks with uncertainty quantification for traffic incident risk prediction
Predicting traffic incident risks at granular spatiotemporal levels is challenging. The datasets
predominantly feature zero values, indicating no incidents, with sporadic high-risk values for …
predominantly feature zero values, indicating no incidents, with sporadic high-risk values for …
Towards unifying diffusion models for probabilistic spatio-temporal graph learning
Spatio-temporal graph learning is a fundamental problem in the Web of Things era, which
enables a plethora of Web applications such as smart cities, human mobility and climate …
enables a plethora of Web applications such as smart cities, human mobility and climate …
SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks
Quantifying uncertainty is crucial for robust and reliable predictions. However, existing
spatiotemporal deep learning mostly focuses on deterministic prediction, overlooking the …
spatiotemporal deep learning mostly focuses on deterministic prediction, overlooking the …
CreST: A Credible Spatiotemporal Learning Framework for Uncertainty-aware Traffic Forecasting
Spatiotemporal traffic forecasting plays a critical role in intelligent transportation systems,
which empowers diverse urban services. Existing traffic forecasting frameworks usually …
which empowers diverse urban services. Existing traffic forecasting frameworks usually …
Predicting human mobility flows in response to extreme urban floods: A hybrid deep learning model considering spatial heterogeneity
Resilient post-disaster recovery is crucial for the long-term sustainable development of
modern cities, and in this regard, predicting the unusual flows of human mobility when …
modern cities, and in this regard, predicting the unusual flows of human mobility when …
Uncertainty-aware evaluation of time-series classification for online handwriting recognition with domain shift
A Klaß, SM Lorenz, MW Lauer-Schmaltz… - arXiv preprint arXiv …, 2022 - arxiv.org
For many applications, analyzing the uncertainty of a machine learning model is
indispensable. While research of uncertainty quantification (UQ) techniques is very …
indispensable. While research of uncertainty quantification (UQ) techniques is very …
Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder
Origin-destination (OD) crowd flow, if more accurately inferred at a fine-grained level, has
the potential to enhance the efficacy of various urban applications. While in practice for …
the potential to enhance the efficacy of various urban applications. While in practice for …
Adaptive Modeling of Uncertainties for Traffic Forecasting
Deep neural networks (DNNs) have emerged as a dominant approach for developing traffic
forecasting models. These models are typically trained to minimize error on averaged test …
forecasting models. These models are typically trained to minimize error on averaged test …
Spatial–temporal uncertainty-aware graph networks for promoting accuracy and reliability of traffic forecasting
Providing both point estimation and uncertainty quantification for traffic forecasting is crucial
for supporting accurate and reliable services in intelligent transportation systems. However …
for supporting accurate and reliable services in intelligent transportation systems. However …