제목: Machine Learning for Graph Optimization
강사: 안성수 박사 (https://sites.google.com/view/sungsooahn0215/home)
일시: 2021년 5월 6일 (목요일) 오후 5시
링크: https://yonsei.zoom.us/j/86142532046?pwd=ZitvSWlsNU1QOW5RM3g4RzNQUWpIUT09* 회의 ID및 PW 각 연구실 방장들에게 공지
Abstract:
Optimization of a graph-structured solution appears ubiquitously in many important applications (e.g., drug discovery and program synthesis). This talk will introduce how one can use machine learning to solve such optimization problems, with the focus on deep neural network (DNN)-based solvers. Especially, I will introduce my work based on the questions of how DNN-based solvers can be compared or combined with the more classic solvers. The first part will be about the maximum independent set problem; I will introduce a scalable structured prediction framework that bridges the performance gap between DNN-based and classic solvers. The next part will be about the optimization of molecular structures. I will demonstrate a training scheme for DNNs based on the guidance of classic genetic algorithms, significantly improving over the state-of-the-art results.