更多科大概览
9月26日
4:30pm - 5:50pm
研讨会, 演讲, 讲座
The analysis of geometric (graph- and manifold-structured) data have recently gained prominence in the machine learning community. For the first part of the talk, I will introduce Lanczos network (LanczosNet), which uses the Lanczos algorithm to construct low rank approximations of the graph Laplacian for graph convolution. Relying on the tridiagonal decomposition of the Lanczos algorithm, we efficiently exploit multi-scale information via fast approximated computation of matrix power, and design learnable spectral filters. Being fully differentiable, LanczosNet facilitates both graph kernel learning as well as learning node embeddings. I will show the application of LanczosNet to citation networks and QM8 quantum chemistry dataset.
For the second part of the talk, I will introduce a novel multi-representation learning paradigm for manifolds naturally equipped with a group action. Utilizing a representation theoretic mechanism, multiple associated vector bundles can be constructed over the orbit space, providing multiple views for learning the geometry of the underlying manifold. The consistency across these associated vector bundles form a common base for unsupervised manifold learning, through the redundancy inherent to the algebraic relations across irreducible representations of the transformation group. I will demonstrate the efficacy of the proposed algorithmic paradigm through dramatically improved robust nearest neighbor search in cryo-electron microscopy image analysis.
For the second part of the talk, I will introduce a novel multi-representation learning paradigm for manifolds naturally equipped with a group action. Utilizing a representation theoretic mechanism, multiple associated vector bundles can be constructed over the orbit space, providing multiple views for learning the geometry of the underlying manifold. The consistency across these associated vector bundles form a common base for unsupervised manifold learning, through the redundancy inherent to the algebraic relations across irreducible representations of the transformation group. I will demonstrate the efficacy of the proposed algorithmic paradigm through dramatically improved robust nearest neighbor search in cryo-electron microscopy image analysis.
9月26日
4:30pm - 5:50pm
地点
Room 2405, Academic Building (near Lifts 17-18), HKUST
讲者/表演者
Prof. Zhizhen ZHAO
Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign
Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign
主办单位
Department of Mathematics
联系方法
mathseminar@ust.hk
付款详情
对象
Alumni, Faculty and Staff, PG Students, UG Students
语言
英语
其他活动
1月6日
研讨会, 演讲, 讲座
IAS / School of Science Joint Lecture - Innovations in Organo Rare-Earth and Titanium Chemistry: From Self-Healing Polymers to N2 Activation
Abstract
In this lecture, the speaker will introduce their recent studies on the development of innovative organometallic complexes and catalysts aimed at realizing unprecedented chemical trans...
12月5日
研讨会, 演讲, 讲座
IAS / School of Science Joint Lecture - Human B Cell Receptor-Epitope Selection for Pan-Sarbecovirus Neutralization
Abstract
The induction of broadly neutralizing antibodies (bnAbs) against viruses requires the specific activation of human B cell receptors (BCRs) by viral epitopes. Following BCR activation, ...