Hdmixer: Hierarchical dependency with extendable patch for multivariate time series forecasting
Multivariate time series (MTS) prediction has been widely adopted in various scenarios.
Recently, some methods have employed patching to enhance local semantics and improve …
Recently, some methods have employed patching to enhance local semantics and improve …
Maintaining the status quo: Capturing invariant relations for ood spatiotemporal learning
Spatiotemporal (ST) learning has become a crucial technique for urban digitalization. Due to
expansions and dynamics of cities, current spatiotemporal models are inclined to suffer …
expansions and dynamics of cities, current spatiotemporal models are inclined to suffer …
Extract and refine: Finding a support subgraph set for graph representation
Subgraph learning has received considerable attention in its capacity of interpreting
important structural information for predictions. Existing subgraph learning usually exploits …
important structural information for predictions. Existing subgraph learning usually exploits …
Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
Pre-training GNNs to extract transferable knowledge and apply it to downstream tasks has
become the de facto standard of graph representation learning. Recent works focused on …
become the de facto standard of graph representation learning. Recent works focused on …
A Multi-graph Fusion Based Spatiotemporal Dynamic Learning Framework
Spatiotemporal data forecasting is a fundamental task in the field of graph data mining.
Typical spatiotemporal data prediction methods usually capture spatial dependencies by …
Typical spatiotemporal data prediction methods usually capture spatial dependencies by …
Countering modal redundancy and heterogeneity: a self-correcting multimodal fusion
Fusing multimodal heterogeneous data plays a vital role in recognition and prediction tasks
in various fields, eg, action recognition and traffic accident forecast. Yet, there remain some …
in various fields, eg, action recognition and traffic accident forecast. Yet, there remain some …
[PDF][PDF] LeRet: Language-Empowered Retentive Network for Time Series Forecasting
Time series forecasting (TSF) plays a pivotal role in many real-world applications. Recently,
the utilization of Large Language Models (LLM) in TSF has demonstrated exceptional …
the utilization of Large Language Models (LLM) in TSF has demonstrated exceptional …
Correlation-driven multi-level learning for anomaly detection on multiple energy sources
T Kim, JS Jang, HY Kwon - Applied Soft Computing, 2024 - Elsevier
Advanced metering infrastructure (AMI) has been widely used as an intelligent energy
consumption measurement system. Electric power was the representative energy source …
consumption measurement system. Electric power was the representative energy source …
When Imbalance Meets Imbalance: Structure-driven Learning for Imbalanced Graph Classification
W Xu, P Wang, Z Zhao, B Wang, X Wang… - Proceedings of the ACM …, 2024 - dl.acm.org
Graph Neural Networks (GNNs) can learn representative graph-level features to achieve
efficient graph classification. But GNNs usually assume an environment where both class …
efficient graph classification. But GNNs usually assume an environment where both class …
A Novel Series-Concatenation Hybrid Prediction Model of Energy Consumption in Hot Strip Roughing Process With Multi-Step Rolling
The steel industry has received serious attention under the background of carbon
neutralization and carbon peaking. However, the traditional end-to-end energy consumption …
neutralization and carbon peaking. However, the traditional end-to-end energy consumption …