Related papers: Generative AI Enabled Robust Sensor Placement in C…
We consider the following problem: a team of robots is deployed in an unknown environment and it has to collaboratively build a map of the area without a reliable infrastructure for communication. The backbone for modern mapping techniques…
Feature selection is fundamental to robust data-centric AI, but most existing methods optimize predictive performance under a single data distribution. This often selects spurious features that fail under distribution shifts. Motivated by…
Accurate online transient stability prediction is critical for ensuring power system stability when facing disturbances. While traditional transient stablity analysis replies on the time domain simulations can not be quickly adapted to the…
A distinguishing characteristic of wireless sensor networks is the opportunity to exploit characteristics of the application at lower layers. This paper reports on the results of a simulation comparison of proposed data dissemination…
Multi-agent robotic manipulation remains challenging due to the combined demands of coordination, grasp stability, and collision avoidance in shared workspaces. To address these challenges, we propose the Adaptive Dynamic Modality Diffusion…
Influenced by deep penetration of the new generation of information technology, power systems have gradually evolved into highly coupled cyber-physical systems (CPS). Among many possible power CPS network attacks, a false data injection…
Graph Neural Networks (GNNs) are highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this issue by filtering attacked graphs. However, they struggle…
The experiments at the Large Hadron Collider at CERN generate vast amounts of complex data from high-energy particle collisions. This data presents significant challenges due to its volume and complex reconstruction, necessitating the use…
Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sensitive areas such as medical imaging. Medical images feature…
Power distribution systems (PDS) serve as the backbone of our modern society, ensuring electricity reaches homes, businesses, and critical infrastructure. However, the increasing digitization and interconnectivity of these systems have…
Parameter Estimation (PE) and State Estimation (SE) are the most wide-spread tasks in the system engineering. They need to be done automatically, fast and frequently, as measurements arrive. Deep Learning (DL) holds the promise of tackling…
Cyber-Physical Systems (CPSs) are vastly used in today's cities critical infrastructure. The cyber part of these systems usually has a network component through which cyber attacks can be launched. In this paper, we first design an…
The Dissemination Process Classification (DPC) is a popular application of temporal graph classification. The aim of DPC is to classify different spreading patterns of information or pestilence within a community represented by…
Distributed power allocation is important for interference-limited wireless networks with dense transceiver pairs. In this paper, we aim to design low signaling overhead distributed power allocation schemes by using graph neural networks…
We consider the problem of maximum likelihood estimation in linear models represented by factor graphs and solved via the Gaussian belief propagation algorithm. Motivated by massive internet of things (IoT) networks and edge computing, we…
Parameter-Efficient Fine-Tuning (PEFT) method has emerged as a dominant paradigm for adapting pre-trained GNN models to downstream tasks. However, existing PEFT methods usually exhibit significant vulnerability to various noise and attacks…
Federated Graph Learning (FGL) is an emerging technology that enables clients to collaboratively train powerful Graph Neural Networks (GNNs) in a distributed manner without exposing their private data. Nevertheless, FGL still faces the…
Design of cyber-physical systems (CPSs) is a challenging task that involves searching over a large search space of various CPS configurations and possible values of components composing the system. Hence, there is a need for…
Exact subgraph matching on large-scale graphs remains a challenging problem due to high computational complexity and distributed system constraints. Existing GNN-based path embedding (GNN-PE) frameworks achieve efficient exact matching on…
We introduce the Fixed Point Diffusion Model (FPDM), a novel approach to image generation that integrates the concept of fixed point solving into the framework of diffusion-based generative modeling. Our approach embeds an implicit fixed…