Related papers: Boosting long-term forecasting performance for con…

Learning Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been proposed recently, we find that most message passing-,…

Temporal heterogeneous networks (THNs) are evolving networks that characterize many real-world applications such as citation and events networks, recommender systems, and knowledge graphs. Although different Graph Neural Networks (GNNs)…

Large language models (LLM) have prioritized expanding the context window from which models can incorporate more information. However, training models to handle long contexts presents significant challenges. These include the scarcity of…

Long-term time series forecasting (LTSF) offers broad utility in practical settings like energy consumption and weather prediction. Accurately predicting long-term changes, however, is demanding due to the intricate temporal patterns and…

Data augmentation has been widely used to improve generalizability of machine learning models. However, comparatively little work studies data augmentation for graphs. This is largely due to the complex, non-Euclidean structure of graphs,…

This paper explores the utilization of Temporal Graph Networks (TGN) for financial anomaly detection, a pressing need in the era of fintech and digitized financial transactions. We present a comprehensive framework that leverages TGN,…

Time-series forecasting is a critical task across many domains, from engineering to economics, where accurate predictions drive strategic decisions. However, applying advanced deep learning models in challenging, volatile domains like…

Dynamic graphs are formulated in continuous-time or discrete-time dynamic graphs. They differ in temporal granularity: Continuous-Time Dynamic Graphs (CTDGs) exhibit rapid, localized changes, while Discrete-Time Dynamic Graphs (DTDGs) show…

We study a recent class of models which uses graph neural networks (GNNs) to improve forecasting in multivariate time series. The core assumption behind these models is that there is a latent graph between the time series (nodes) that…

Inductive spatial temporal prediction can generalize historical data to predict unseen data, crucial for highly dynamic scenarios (e.g., traffic systems, stock markets). However, external events (e.g., urban structural growth, market crash)…

Temporal Graph Neural Networks (TGNNs) have gained growing attention for modeling and predicting structures in temporal graphs. However, existing TGNNs primarily focus on pairwise interactions while overlooking higher-order structures that…

Time-series data augmentation mitigates the issue of insufficient training data for deep learning models. Yet, existing augmentation methods are mainly designed for classification, where class labels can be preserved even if augmentation…

Recently, numerous deep models have been proposed to enhance the performance of multivariate time series (MTS) forecasting. Among them, Graph Neural Networks (GNNs)-based methods have shown great potential due to their capability to…

Recent advancements in Large Language Models (LLMs) have significantly improved text generation capabilities, but these systems are still known to hallucinate, and granular uncertainty estimation for long-form LLM generations remains…

Deep learning approaches have reached a celebrity status in artificial intelligence field, its success have mostly relied on Convolutional Networks (CNN) and Recurrent Networks. By exploiting fundamental spatial properties of images and…

Temporal Knowledge Graph (TKG) completion models traditionally assume access to the entire graph during training. This overlooks challenges stemming from the evolving nature of TKGs, such as: (i) the model's requirement to generalize and…

Graph Neural Networks (GNNs) are powerful machine learning prediction models on graph-structured data. However, GNNs lack rigorous uncertainty estimates, limiting their reliable deployment in settings where the cost of errors is…

Short-term water demand forecasting (StWDF) is the foundation stone in the derivation of an optimal plan for controlling water supply systems. Deep learning (DL) approaches provide the most accurate solutions for this purpose. However, they…

Continuous-time dynamic graphs (CTDGs) are essential for modeling interconnected, evolving systems. Traditional methods for extracting knowledge from these graphs often depend on feature engineering or deep learning. Feature engineering is…

The continuous expansion of the urban construction scale has recently contributed to the demand for the dynamics of traffic intersections that are managed, making adaptive modellings become a hot topic. Existing deep learning methods are…