The following schedule is a work in progress. Once we have the full seminar details including title, abstract and speaker bio, we will publish these talks under upcoming seminars.

Date Speaker Title Abstract
2024-07-25 11:00
2024-08-01 11:00 Hao (Allen) Zhu Effective and Scalable Representation Learning for Graphs: From Theory to Applications This presentation demonstrates critical challenges in graph-based machine learning, focusing on oversmoothing, effectiveness, and scalability. We introduce Simple Spectral Graph Convolution (S²GC), a variant of Graph Convolutional Networks with improved computational efficiency and performance. We then extend classical Laplacian Eigenmaps to develop Contrastive Laplacian Eigenmaps (COLES) and Generalized Laplacian EigeNmaps (GLEN) for unsupervised graph representation learning, offering scalable solutions for large-scale graph embedding with performance guarantees. Finally, we explore applications in few-shot learning and dynamic graph construction, introducing Unsupervised Discriminant Subspace Learning (EASE) and Prototype-based Label Propagation (ProtoLP). These innovations significantly advance the field of graph representation learning, offering improved performance and efficiency across various tasks including node classification, clustering, and transductive inference.
2024-08-08 11:00 Changsheng Lu
2024-08-15 11:00
2024-08-22 11:00
2024-08-29 11:00
2024-09-05 11:00
2024-09-12 11:00
2024-09-19 11:00
2024-09-26 11:00
2024-10-03 11:00
2024-10-10 11:00
2024-10-17 11:00
2024-10-24 11:00
2024-10-31 11:00
2024-11-07 11:00
2024-11-14 11:00
2024-11-21 11:00
2024-11-28 11:00
2024-12-05 11:00
2024-12-12 11:00
2024-12-19 11:00
2024-12-26 11:00
bars search times arrow-up