Loading Events

« All Events


Hongseok Yang (양홍석), DAG-symmetries and Symmetry-Preserving Neural Networks

June 22 Tuesday @ 4:30 PM - 5:30 PM KST

Room B232, IBS (기초과학연구원)

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.

In 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.

This is joint work with Dongwoo Oh.


June 22 Tuesday
4:30 PM - 5:30 PM KST
Event Category:
Event Tags:


Room B232
IBS (기초과학연구원)


Sang-il Oum (엄상일)
View Organizer Website
IBS 이산수학그룹 Discrete Mathematics Group
기초과학연구원 수리및계산과학연구단 이산수학그룹
대전 유성구 엑스포로 55 (우) 34126
IBS Discrete Mathematics Group (DIMAG)
Institute for Basic Science (IBS)
55 Expo-ro Yuseong-gu Daejeon 34126 South Korea
E-mail: dimag@ibs.re.kr, Fax: +82-42-878-9209
Copyright © IBS 2018. All rights reserved.