본문 바로가기

ACML The First International Workshop
on Machine Learning
for Artificial Intelligence Platforms

Asian Conference on Machine Learning 2017
Seoul, Korea / 15 November 2017

Motivation and Goal

Recently, several successful AI systems such as Amazon Alexa, Google Assistant, and NAVER X LINE CLOVA are developed based on AI-assistant platforms. These AI platforms contain several common technologies including speech recognition/synthesis, natural language understanding, image recognition, and dialog recommendation.
Building a successful MLAIP is a challenging mission because it requires a novel combination of heterogeneous machine learning models in a unified framework with efficient data processing. The goals of this workshop are to investigate and advance important topics in Machine Learning for AI Platforms (MLAIPs) further. In addition, we expect to provide the collaboration opportunities to researchers on ML theory and diverse application domains as well as industrial engineers.

Important dates

Extended abstracts deadline Author Notification Workshop day
15 Oct 2017 20 Oct 2017 15 Nov 2017


Room 3, Baekyang Hall of Yonsei University campus, Seoul, Korea

Program Schedule

Time Contents Speaker Session Chairs
08:40 ~ 08:50 Opening Byoung-Tak Zhang
(Seoul National Univ.)
Jung-Woo Ha
08:50 ~ 09:20 Invited Talk
NSML: A Machine Learning Platform That Enables You to Focus on Your Models
Nako Sung
Jung-Woo Ha
09:20 ~ 10:10 Keynote Speech
Machine Learning from Weak Supervision: Towards Accurate Classification with Low Labeling Costs
Masashi Sugiyama
(RIKEN/The Univ. of Tokyo)
Jung-Woo Ha
10:10 ~ 10:30 Coffee break
10:30 ~ 11:00 Invited Talk
Efficient and Accurate Rumor Detection in Online Social Networks
Kyomin Jung
(Seoul National Univ.)
Jung-Woo Ha
11:00 ~ 11:30 Invited Talk
Visual Analytics for Explainable AI
Huamin Qu
Jung-Woo Ha
11:30 ~ 12:30 Lunch
12:30 ~ 13:00 Invited Talk
Interaction between Machine Learning and Multi-Agent System
Il Chul Moon
Jaesik Choi
13:00 ~ 13:30 Invited Talk
My model has higher BLEU, can I ship it?
Lucy Park
(Papago, NAVER)
Jaesik Choi
13:30 ~ 14:30 Poster Session Jaesik Choi
Jaesik Choi
14:30 ~ 15:20 Panel Discussion: Next-generation AI Platforms for AGI Byoung-Tak Zhang
(Seoul National Univ.)
Byoung-Tak Zhang
(Seoul National Univ.)
15:20 ~ 15:30 Wrap-up & Closing Byoung-Tak Zhang
(Seoul National Univ.)
Byoung-Tak Zhang
(Seoul National Univ.)

Keynote Speech

· Masashi Sugiyama (RIKEN/The University of Tokyo)

· Title: Machine Learning from Weak Supervision: Towards Accurate Classification with Low Labeling Costs
· Abstract

Machine learning from big training data is achieving great success. However, there are various application domains that prohibit the use of massive labeled data. In this talk, I will introduce our recent advances in classification from weak supervision, including classification from two sets of unlabeled data, classification from positive and unlabeled data, a novel approach to semi-supervised classification, and classification from complementary labels. Finally, I will briefly introduce the activities of RIKEN Center for Advanced Intelligence Project.

· Biography

Masashi Sugiyama received the PhD degree in Computer Science from Tokyo Institute of Technology, Japan in 2001. He has been Professor at the University of Tokyo as Professor since 2014 and was concurrently appointed as Director of RIKEN Center for Advanced Intelligence Project in 2016. His research interests include theory, algorithms, and applications of machine learning. He (co)-authored several books such as Density Ratio Estimation in Machine Learning (Cambridge University Press, 2012), Machine Learning in Non-Stationary Environments (MIT Press, 2012), Statistical Reinforcement Learning (Chapman and Hall, 2015), and Introduction to Statistical Machine Learning (Morgan Kaufmann, 2015). He served a Program co-chair and General co-chair of the Neural Information Processing Systems conference in 2015 and 2016, respectively. Masashi Sugiyama received the Japan Society for the Promotion of Science Award and the Japan Academy Medal in 2017.

Invited Speakers

  • · Nako Sung (CLAIR, NAVER Corp.)

    · Title: NSML: A Machine Learning Platform That Enables You to Focus on Your Models
    · Abstract

    Machine learning libraries such as TensorFlow and PyTorch simplify model implementation. However, researchers are still required to perform a non-trivial amount of manual tasks such as GPU allocation, training status tracking, and comparison of models with different hyperparameter settings. We propose a system to handle these tasks and help researchers focus on models. We present the requirements of the system based on a collection of discussions from an online study group comprising 25k members. These include automatic GPU allocation, learning status visualization, handling model parameter snapshots as well as hyperparameter modification during learning, and comparison of performance metrics between models via a leaderboard. We describe the system architecture that fulfills these requirements and present a proof-of-concept implementation, NAVER Smart Machine Learning (NSML). We test the system and confirm substantial efficiency improvements for model development.

    · Biography

    Nako Sung is a leader of CLOVA AI Research, NAVER Corp. He received the BS degree from the Department of Computer Science and Engineering, Seoul National University. He was experienced in the game AI and development fields including Neowiz and NC soft for 18 years field. He is interested in deep reinforcement learning, deep generative models, and their real-world applications.

  • · Kyomin Jung (Seoul National University)

    · Title: Efficient and Accurate Rumor Detection in Online Social Networks
    · Abstract

    The problem of identifying rumors is of practical importance especially in online social networks, since information can diffuse more rapidly and widely than the offline counterpart. In this talk, I will present our work that identifies characteristics of rumors in online social network by examining the following three aspects of diffusion: temporal, structural, and linguistic. For the temporal characteristics, we propose a new periodic time series model that considers daily and external shock cycles, where the model demonstrates that rumor likely have fluctuations over time. We also identify key structural and linguistic differences in the spread of rumors and non-rumors. Our selected features classify rumors with high precision and recall in the range of 87% to 92% on a Twitter data set. I will also present analysis of performance levels over varying time windows—from the first three days to nearly two months. Based on these findings, we suggest a new rumor classification algorithm that achieves competitive accuracy over both short and long time windows.

    · Biography

    Kyomin Jung is an associate professor in the Electrical and Computer Engineering department at Seoul National University (SNU), and has a joint appointment in the Mathematics department SNU. He worked at KAIST Computer Science department from 2009 to 2013. He received Ph.D. at MIT department of Mathematics in 2009, and B.Sc. at Seoul National University department of Mathematics in 2003. During his Ph.D., he worked at Microsoft Research Cambridge (2008), IBM T.J. Watson Research (2007), and Bell Labs (2006) as research internships. He was a recipient of Samsung Lee Kun Hee Scholarship for graduate study, and he was a gold medalist at the IMO (International Mathematical Olympiad) 1995. He is a recipient of the excellent new faculty funding from NRF Korea in 2012, and he is a member of SNU Big Data Institute. His research area includes machine learning and natural language processing with applications to social network analysis, recommendation systems, and machine translation. His work on machine learning and social network analysis have been published in major journals and conferences including IEEE PAMI, NIPS, ICML, AAAI, STOC, SODA, SIGMETRICS, ICDE and ICDM.

  • · Huamin Qu (HKUST)

    · Title: Visual Analytics for Explainable AI
    · Abstract

    Classification is a fundamental problem in machine learning. In practice, interpretability is a desirable property of classification models (classifiers) in critical areas, such as security, medicine and finance. For instance, a quantitative trader may prefer a more interpretable model with less expected return due to its predictability and low risk. Unfortunately, the best-performing classifiers in many applications (e.g., deep neural networks) are complex machines whose predictions are difficult to explain. Thus, there is a growing interest in using visualization to understand, diagnose and explain intelligent systems in both academia and in industry. Many challenges need to be addressed in the formalization of explainability, and the design principles and evaluation of explainable intelligent systems. In this talk, I will first briefly introduce the concept and background of explainable classifiers. After that I will present thee works done at HKUST which use visualization to help explain deep neural networks: 1) RNNVis, a visual analytics tool for understanding and comparing recurrent neural networks (RNNs) for text-based applications. 2) CNNComparator, a visual analytics method to compare two different snapshots of a trained CNN model taken after different numbers of epochs. 3) DeepTracker, a visual analytics solution to reveal the rich dynamics of CNN training processes and help machine learning experts better understand, debug, and optimize CNNs.

    · Biography

    Huamin Qu is a professor in the Department of Computer Science and Engineering (CSE) at the Hong Kong University of Science and Technology. He also serves as the coordinator of the newly founded Human-Computer Interaction (HCI) group at the CSE department. His main research interests are in visualization and human-computer interaction, with focuses on urban informatics, social network analysis, e-learning, and explainable artificial intelligence. He has co-authored more than 100 refereed papers including more than 40 papers in the IEEE Transactions on Visualization and Computer Graphics (TVCG). His research has been recognized by many awards including 7 best paper/honorable mention awards, 2009 IBM Faculty Award, 2014 Higher Education Scientific and Technological Progress Award (Second Class) from the Ministry of Education of China, 2015 HKICT Best Innovation (Innovative Technology) Silver Award from the Hong Kong Institution of Engineers, 2015 APICTA Merit Award in E-Learning from the Asia Pacific ICT Alliance, and 2016 Distinguished Collaborator Award from Huawei Nah's Ark Lab. He obtained a BS in Mathematics from Xi'an Jiaotong University, China, an MS and a PhD (2004) in Computer Science from the Stony Brook University.

  • · Il Chul Moon (KAIST)

    · Title: Interaction between Machine Learning and Multi-Agent System
    · Abstract

    Under the umbrella of artificial intelligence, the breakthroughs in the machine learning (ML) has been spread to the sibling disciplines, such as multi-agent system (MAS). This presentation introduces the recent theoretic interplay between ML and MAS. First, ML could be an automated controller to strengthen the operation and the validity of MAS, and we show this fusion through a case study of automatic calibration of MAS. Second, MAS could be a playground of individual ML instances to interact and compete between them, which we survey the researches, such as Gang of GANs.

    · Biography

    Il-Chul Moon received the Ph.D. degree from the School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA, in 2008. He is currently an Assistant Professor with the Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Korea. His research interests include the overlapping area of computer science, management, sociology, and operations research, and also military command and control analysis, counterterrorism analysis, intelligence analysis, and disaster management.

  • · Lucy Eunjung Park (Papago, NAVER Corp.)

    · Title: My model has higher BLEU, can I ship it?
    · Abstract

    In the real world, there is a discrepancy between AI research and actual AI services. It is not enough get higher scores with a machine learning model according to some performance measure such as BLEU -- there is much more to do before and after a model is delivered to actual users. In this talk, we explore what such discrepancies are, and share several ways to overcome them.

    · Biography

    Lucy is a research scientist at NAVER. During her Ph.D. studies at Seoul National University, she investigated better representations for text. Her current research area is machine translation -- focused on user log analysis and multilingual NMT.

Accepted Posters

Inzamam Anwar, Naeem Ul Islam (Sungkyunkwan Univ)
Learned Features are better for Ethnicity Classification
Hanchao Li (Coventry Univ)
Music Data Representation and Information Retrieval Using Vector-based Similarity Scores
Sang-Woo Lee, Yujeong Heo (Seoul National Univ)
Byoung-Tak Zhang (Seoul National Univ & Surromind Robotics)
Answerer in Questioner’s Mind for Goal-Oriented Visual Dialogue
Junghoon Seo, Seunghyun Jeon, Taegyun Jeon (Satrec Initiative)
Domain Adaptive Generation of Aircraft on Satellite Imagery via Simulated and Unsupervised Learning
Jinyeong Yim
Eunchung Noh (Seoul National Univ)
Linguistic Alignment in Quasi-spoken Corpus in Spanish and Marker List Extraction Modeling
Kyung-Min Kim, Seong-Ho Choi, Byoung-Tak Zhang (Seoul National Univ & Surromind Robotics)
MuSM: Multimodal Sequence Memory for Video Story Question Answering
Seunghyun Jeon, Junghoon Seo, Taegyun Jeon (Satrec Initiative)
Multi-task Learning for Fine-grained Visual Classification of Aircraft
Jaeyoon Yoo, Heonseok Ha, Jihun Yi (Seoul National Univ)
Jongha Ryu (UC San Diego)
Chanju Kim, Jung-Woo Ha (NAVER)
Young-Han Kim (UC San Diego)
Sungroh Yoon (Seoul National Univ)
Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning
Ahn Tong, Jaesik Choi (UNIST)
Accelerate learning GP for interpretable kernels via deterministic feature maps
Thanh T. Nguyen, Jaesik Choi (UNIST)
Exploiting Information Bottleneck to Optimize Stochastic Neural Networks
Kallol Roy, Jaesik Choi (UNIST)
Efficient Search of Local Symmetries with Topological Features
Jiyeon Han, Kyowoon Lee, Jaesik Choi (UNIST)
Detection of Covariance Changes in Gaussian Processes
Hyungjoo Cho, Sungbin Lim, Gunho Choi, Hyunseok Min
Neural Stain-Style Transfer Learning using GAN for Histopathological Images
Jimin Lee (Seoul National Univ)
Yujeong Lee (Seoul National Univ & Jeju Natl Univ Hospital)
Sung-Joon Ye (SNU & SNU Hospital)
Prediction of multi-leaf collimator positional errors using Deep Learning
Youjin Kim, Yun-Geun Lee (NAVER)
Jeong Whun Kim, Jinjoo Park, Borim Ryu (SNU Bundang Hospital)
Jung-Woo Ha (NAVER)
Highrisk Prediction from Electronic Medical Records via Deep Attention Networks
Nako Sung, Minkyu Kim, Hyunwoo Jo, Youngil Yang, Jinwoong Kim (NAVER)
Leonard Lausen (NAVER & HKUST)
Youngkwan Kim (NAVER)
Gayoung Lee (NAVER Webtoon)
Donghyun Kwak (Search Solution)
Jung-Woo Ha (NAVER)
Sung Kim (NAVER & HKUST)
NSML: A Machine Learning Platform That Enables You to Focus on Your Models
Adrian Kim, Soram Park, Jangyeon Park (NAVER)
Taekyun Kwon, Juhan Nam (KAIST)
Jung-Woo Ha (NAVER)
Automatic DJ mix generation using highlight detection
Jung-Woo Ha, Adrian Kim, Chanju Kim, Jangyeon Park (NAVER)
Sung Kim (NAVER & HKUST)
Automatic Music Highlight Extraction using Convolutional Recurrent Attention Networks
Donghyun Kwak (Search Solution)
Jung-Woo Ha, Sung Kim (NAVER)
Nako Sung (NAVER)
Movie Score Prediction from Korean Comment Reviews with Sub-Character Level BiLSTM Models


  • · Byoung-Tak Zhang (Seoul National University)
  • · Sungroh Yoon (Seoul National University)
  • · Dit-Yan Yeung (Hong Kong University of Science and Technology)
  • · Sung Kim (Hong Kong University of Science and Technology)
  • · Jaesik Choi (Ulsan National Institute of Science and Technology)
  • · Jung-Woo Ha (CLOVA, NAVER Corp.)