Search Results

The SARS-CoV-2 viruses and their triggered COVID-19 pandemic have fundamentally reshaped the world in almost every aspect, their evolution and influences remain. While over a million of literature have been produced on these unprecedented, overwhelming ...

A standard network pretrained on in-distribution (ID) samples could make high-confidence predictions on out-of-distribution (OOD) samples, leaving the possibility of failing to distinguish ID and OOD samples in the test phase. To address this over-...

Multivariate time series (MTS) forecasting penetrates various aspects of our economy and society, whose roles become increasingly recognized. However, often MTS forecasting is unfair, not only degrading their practical benefits but even incurring ...

Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media. Existing multimodal rumor detection has focused on mixing tokens among spatial and sequential locations for unimodal representation ...

Time series forecasting has played the key role in different industrial, including finance, traffic, energy, and healthcare domains. While existing literatures have designed many sophisticated architectures based on RNNs, GNNs, or Transformers, another ...

Multivariate time series (MTS) forecasting has shown great importance in numerous industries. Current state-of-the-art graph neural network (GNN)-based forecasting methods usually require both graph networks (e.g., GCN) and temporal networks (e.g., LSTM) ...

Real-life data are often non-IID due to complex distributions and interactions, and the sensitivity to the distribution of samples can differ among learning models. Accordingly, a key question for any supervised or unsupervised model is whether the ...

The discrepancy between in-distribution (ID) and out-of-distribution (OOD) samples can lead to <italic>distributional vulnerability</italic> in deep neural networks, which can subsequently lead to high-confidence predictions for OOD samples. This is ...

Users&#x2019; purchase behaviors are complex and dynamic, which are usually driven by various personal demands evolving with time. According to psychology and economic theories, user demands can be satisfied with a sequence of purchase behaviors, ...

Federated learning (FL) demonstrates its advantages in integrating distributed infrastructure, communication, computing and learning in a privacy-preserving manner. However, the robustness and capabilities of existing FL methods are challenged by limited ...

In deep neural learning, a discriminator trained on in-distribution (ID) samples may make high-confidence predictions on out-of-distribution (OOD) samples. This triggers a significant matter for robust, trustworthy and safe deep learning. The issue is ...

Mortality prediction is crucial to evaluate the severity of illness and assist in improving the prognosis of patients. In clinical settings, one way is to analyze the multivariate time series (MTSs) of patients based on their medical data, such ...

Display Omitted

• Propose a deep learning model, BiT-MAC, for clinical data-based mortality prediction.
• Explore intra- and inter-time series couplings for missing value imputation.
• Provide the interpretability of the coupling relationships between ...

In the current digital world, web search engines and recommendation systems are continuously evolving, opening up new potential challenges every day which require more sophisticated and efficient data mining and machine learning solutions to satisfy the ...

The prediction of express delivery sequence, i.e., modeling and estimating the volumes of daily incoming and outgoing parcels for delivery, is critical for online business, logistics, and positive customer experience, and specifically for resource ...

The detection of, explanation of, and accommodation to anomalies and novelties are active research areas in multiple communities, including data mining, machine learning, and computer vision. They are applied in various guises including anomaly detection,...

Non-IID (i.i.d.) data holds complex non-IIDness, e.g., couplings and interactions (non-independent) and heterogeneities (not IID drawn from a given distribution). Non-IID learning emerges as a major challenge to shallow and deep learning, including ...

Artificial intelligence (AI)’s rapid development has produced a variety of state-of-the-art models and methods that rely on network architectures and features engineering. However, some AI approaches achieve high accurate results only at the expense of ...

Real-life AI systems are non-IID, i.e., their variables are unlikely independent and drawn from the same distribution. Instead, non-IIDness is a common characteristic and complexity of real-life systems, where variables, objects, and subsystems are ...

In science, technology, engineering, and their applications, a ubiquitous assumption is independent and identically distributed (i.i.d. or IID). IID simplifies the intricate realities and complexities of the real world for their approximate ...

With the growth of 5G networks, the Internet-of-Things is becoming a reality. The advances in networking, machine learning, data analytics, and robotics largely improve industrial processes. Industry 4.0 is a term for the fourth industrial revolution: the ...