Maintaining and restoring network functionality under structural disturbances or malicious attacks represents a core challenge in network science and graph learning. This capability, known as network robustness, is critical for systems such as transportation, power grids, and biological networks, where failures can lead to severe consequences. Research in this area focuses on developing robustness metrics, performing vulnerability analysis, and designing optimization strategies to enhance resilience. Graph learning plays a pivotal role by enabling data-driven approaches that complement analytical and statistical methods. This talk presents our recent state-of-the-art advances in measuring, analyzing, and optimizing network robustness through graph-based techniques, demonstrating their effectiveness in improving reliability

Dr. Yang Lou is currently an Associate Professor at the Graduate School of Advanced Science and Engineering, Hiroshima University, Japan. He received his B.E. degree in Electronic and Information Engineering from Xidian University, China, in 2008, and his Ph.D. degree from the Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR China, in 2017. From 2017 to 2025, he held research and academic positions at City University of Hong Kong, Lingnan University, The University of Osaka (Japan), and National Yang Ming Chiao Tung University (Taiwan, China). He has authored more than forty peer reviewed papers in leading IEEE magazines (CIM, CSM) and transactions (TCYB, TNNLS, TNSE, TCASI/II), as well as in international conferences such as ICLR, GECCO, and IJCNN. His h-index is 21 according to Google Scholar. He is a Senior Member of the IEEE and a Fellow of the Higher Education Academy. His research interests include network science, graph learning, and optimization.