Graph Neural Networks and GraphRAG: Navigating Open-World Complexity in Finance

Graph Neural Networks (GNNs) and GraphRAG don’t “reason”—they navigate complex, open-world financial graphs with traceable, ...
IEEE

EvGNN: An Event-Driven Graph Neural Network Accelerator for Edge Vision

Abstract: Edge vision systems combining sensing and embedded processing promise low-latency, decentralized, and energy-efficient solutions that forgo reliance on the cloud. As opposed to conventional ...
GitHub

Subgraph-conditioned Graph Information Bottleneck

We aim to build a pre-trained Graph Neural Network (GNN) model on molecules without human annotations or prior knowledge. Although various attempts have been proposed to overcome limitations in ...
GitHub

CS 886: Graph Neural Networks

This is a 3-page paper, along with (if relevant) the source code of your project, including instructions on how to run it. You may use your midterm project as a foundation for your final project, ...
IEEE

Hypercomplex Graph Neural Network: Towards Deep Intersection of Multi-Modal Brain Networks

Abstract: The multi-modal neuroimage study has provided insights into understanding the heteromodal relationships between brain network organization and behavioral phenotypes. Integrating data from ...
Frontiers

Echo-ODE: A dynamics modeling network with neural ODE for temporally consistent segmentation of video echocardiograms

Introduction: Segmentation of echocardiograms plays a crucial role in clinical diagnosis. Beyond accuracy, a major challenge of video echocardiogram analysis is the temporal consistency of consecutive ...