Posts by Collection

portfolio

publications

NetSight: Graph Attention Based Network Traffic Forecasting

Published in , 2025

The paper introduces NetSight, a model that captures global-local spatial-temporal dependencies through a data-driven fusion graph, node normalization, and multi-head attention, significantly improving network traffic forecasting accuracy.

talks

Fundamental Models of Graph Neural Networks and Their Applications

Published:

In this talk, titled “The Fundamental Models of Graph Neural Networks and Their Applications,” I will introduce recent advances in GNN foundation models and discuss their practical applications across domains including network performance optimization and data-driven system intelligence.

teaching