9月26日
4:30pm - 5:50pm
研討會, 演講, 講座
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
地點
Room 2405, Academic Building (near Lifts 17-18), HKUST
講者/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
主辦單位
Department of Mathematics
聯絡方法
mathseminar@ust.hk
付款詳情
對象
Alumni, Faculty and Staff, PG Students, UG Students
語言
英語
其他活動
11月22日
研討會, 演講, 講座
IAS / School of Science Joint Lecture - Leveraging Protein Dynamics Memory with Machine Learning to Advance Drug Design: From Antibiotics to Targeted Protein Degradation
Abstract
Protein dynamics are fundamental to protein function and encode complex biomolecular mechanisms. Although Markov state models have made it possible to capture long-timescale protein co...
11月8日
研討會, 演講, 講座
IAS / School of Science Joint Lecture - Some Theorems in the Representation Theory of Classical Lie Groups
Abstract
After introducing some basic notions in the representation theory of classical Lie groups, the speaker will explain three results in this theory: the multiplicity one theorem for classical...