Related papers: PlugSI: Plug-and-Play Test-Time Graph Adaptation f…
In order to maintain stable grid operations, system monitoring and control processes require the computation of grid states (e.g. voltage magnitude and angles) at high granularity. It is necessary to infer these grid states from…
Modern edge AI applications increasingly rely on microservice architectures that integrate both AI services and conventional microservices into complex request chains with stringent latency requirements. Effectively orchestrating these…
Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most methods assume temporal locality, meaning that recent edges are more influential than earlier edges. However, for temporal changes in edges caused by random…
This paper proposes a novel graph-based framework for robust and interpretable multiclass fault diagnosis in rotating machinery. The method integrates entropy-optimized signal segmentation, time-frequency feature extraction, and…
Large language models have demonstrated promising performance across various software engineering tasks. While fine-tuning is a common practice to adapt these models for downstream tasks, it becomes challenging in resource-constrained…
Bridging the gap between data-rich training regimes and observation-sparse deployment conditions remains a central challenge in spatiotemporal field reconstruction, particularly when target domains exhibit distributional shifts,…
Industry is evolving towards Industry 4.0, which holds the promise of increased flexibility in manufacturing, better quality and improved productivity. A core actor of this growth is using sensors, which must capture data that can used in…
Graph embedding provides an efficient solution for graph analysis by converting the graph into a low-dimensional space which preserves the structure information. In contrast to the graph structure data, the i.i.d. node embedding can be…
Phasor measurement units (PMUs) are being widely installed on power systems, providing a unique opportunity to enhance wide-area situational awareness. One essential application is the use of PMU data for real-time event identification.…
We investigate a variational method for ill-posed problems, named $\texttt{graphLa+}\Psi$, which embeds a graph Laplacian operator in the regularization term. The novelty of this method lies in constructing the graph Laplacian based on a…
This paper proposes a new methodology in linear time-periodic (LTP) system identification. In contrast to previous methods that totally separate dynamics at different tag times for identification, the method focuses on imposing appropriate…
Use-cases in the Internet of Things (IoT) typically involve a high number of interconnected, heterogeneous devices. Due to the criticality of many IoT scenarios, systems and applications need to be tested thoroughly before rollout. Existing…
While current embodied policies exhibit remarkable manipulation skills, their execution remains unsatisfactorily slow as they inherit the tardy pacing of human demonstrations. Existing acceleration methods typically require policy…
Multiple Object Tracking (MOT) has long been a fundamental task in computer vision, with broad applications in various real-world scenarios. However, due to distribution shifts in appearance, motion pattern, and catagory between the…
Teaching Graph Neural Networks (GNNs) to accurately classify nodes under severely noisy labels is an important problem in real-world graph learning applications, but is currently underexplored. Although pairwise training methods have…
Recently, much exertion has been paid to design graph self-supervised methods to obtain generalized pre-trained models, and adapt pre-trained models onto downstream tasks through fine-tuning. However, there exists an inherent gap between…
Recently, there has been an increasing interest in (supervised) learning with graph data, especially using graph neural networks. However, the development of meaningful benchmark datasets and standardized evaluation procedures is lagging,…
Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predominantly optimize the model for each incoming test data batch…
Temporal graph link prediction aims to predict future interactions between nodes in a graph based on their historical interactions, which are encoded in node embeddings. We observe that heterogeneity naturally appears in temporal…
Graph neural networks have emerged as a specialized branch of deep learning, designed to address problems where pairwise relations between objects are crucial. Recent advancements utilize graph convolutional neural networks to extract…