BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Discrete Mathematics Group - ECPv5.7.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Discrete Mathematics Group
X-ORIGINAL-URL:https://dimag.ibs.re.kr
X-WR-CALDESC:Events for Discrete Mathematics Group
BEGIN:VTIMEZONE
TZID:Asia/Seoul
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:KST
DTSTART:20210101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Seoul:20210622T163000
DTEND;TZID=Asia/Seoul:20210622T173000
DTSTAMP:20210618T144442
CREATED:20210430T062352Z
LAST-MODIFIED:20210513T102156Z
UID:4028-1624379400-1624383000@dimag.ibs.re.kr
SUMMARY:Hongseok Yang (양홍석)\, DAG-symmetries and Symmetry-Preserving Neural Networks
DESCRIPTION:The preservation of symmetry is one of the key tools for designing data-efficient neural networks. A representative example is convolutional neural networks (CNNs); they preserve translation symmetries\, and this symmetry preservation is often attributed to their success in real-world applications. In the machine-learning community\, there is a growing body of work that explores a new type of symmetries\, both discrete and continuous\, and studies neural networks that preserve those symmetries. \nIn this talk\, I will explain what I call DAG-symmetries and our preliminary results on the shape of neural networks that preserve these symmetries. DAG-symmetries are finite variants of DAG-exchangeability developed by Jung\, Lee\, Staton\, and Yang (2020) in the context of probabilistic symmetries. Using these symmetries\, we can express that when a neural network works on\, for instance\, sets of bipartite graphs whose edges are labelled with reals\, the network depends on neither the order of elements in the set nor the identities of vertices of the graphs. I will explain how a group of specific DAG-symmetries is constructed by applying a form of wreath product over a given finite DAG. Then\, I will explain what linear layers of neural networks preserving these symmetries should look like. \nThis is joint work with Dongwoo Oh.
URL:https://dimag.ibs.re.kr/event/2021-06-22/
LOCATION:Room B232\, IBS (기초과학연구원)
CATEGORIES:Discrete Math Seminar
END:VEVENT
END:VCALENDAR