Program

Wednesday, 15 November - Tutorials and Workshops/ Conference/ Exhibition

Time Workshops and Tutorials/ Conference/ Exhibition
8:00 am Registration Open - Foyer
8:30 am - 10:00 am Tutorial 1
High Dimensional Causation Analysis
Rm1 		Tutorial 4
Distributed Convex Optimization (I)
Rm2 		Workshop 1
The First International Workshop on Machine Learning for Artificial Intelligence Platforms (MLAIP) (I)
Rm3 		Workshop 2
The 2nd Asian Workshop on Reinforcement Learning (AWRL’17) (I)
B110
10:00 am - 11:30 am Tutorial 2
Statistical Relational Artificial Intelligence
Rm1 		Tutorial 4
Distributed Convex Optimization (II)
Rm2 		Workshop 1
The First International Workshop on Machine Learning for Artificial Intelligence Platforms (MLAIP) (II)
Rm3 		Workshop 2
The 2nd Asian Workshop on Reinforcement Learning (AWRL’17) (II)
B110 		Workshop 3
Korea AI Society Workshop (I)
Grand Ballroom
11:30 am - 12:30 pm Lunch Break at Cafeteria, Student Union
12:30 pm - 3:30 pm Tutorial 3
Deep learning for Biomedicine
Rm1 		Tutorial 5
Machine Learning for Industrial Predictive Analytics
Rm2 		Workshop 1
The First International Workshop on Machine Learning for Artificial Intelligence Platforms (MLAIP) (III)
Rm3 		Workshop 2
The 2nd Asian Workshop on Reinforcement Learning (AWRL’17) (III)
B110 		Workshop 3
Korea AI Society Workshop (II)
Grand Ballroom
3:30 pm - 4:00 pm Afternoon Break
4:00 pm - 6:00 pm Conference begins at Grand Ballroom
Session 1: Large-Scale Machine Learning
Chair: Jihun Hamm
  • #1.1: A Study on Trust Region Update Rules in Newton Methods for Large-scale Linear Classification
    Chih-Yang Hsia, National Taiwan University; Ya Zhu, New York University; Chih-Jen Lin, National Taiwan University
  • #1.2: Mini-batch Block-coordinate based Stochastic Average Adjusted Gradient Methods to Solve Big Data Problems
    Vinod Chauhan, Panjab University Chandigarh; Kalpana Dahiya, Panjab University Chandigarh; Anuj Sharma*, Panjab University Chandigarh
  • #1.3: Select-and-Evaluate: A Learning Framework for Large-Scale Knowledge Graph Search
    F A Rezaur Rahman Chowdhury, Washington State University; Chao Ma, Oregon State University; Md Rakibul Islam, Washington State University; Mohammad Hossein Namaki, Washington State University ; Mohammad Omar Faruk, Washington State University; Janardhan Rao Doppa, Washington State University
  • #1.4: Adaptive Sampling Scheme for Learning in Severely Imbalanced Large Scale Data
    Wei Zhang, Adobe; Said Kobeissi, Adobe; Scott Tomko, Adobe; Chris Challis, Adobe
  • #1.5: Using Deep Neural Networks to Automate Large Scale Statistical Analysis for Big Data Applications
    Rongrong Zhang, Purdue University; Wei Deng, Purdue University; Michael Yu Zhu, Purdue University / Tsinghua University
  • #1.6: Accumulated Gradient Normalization
    Joeri R. Hermans, Liège University; Gerasimos Spanakis, Maastricht University; Rico Möckel, Maastricht University
  • #1.7: Efficient Preconditioning for Noisy Separable NMFs by Successive Projection Based Low-Rank Approximations
    Tomohiko Mizutani, Tokyo Institute of Technology; Mirai Tanaka, The Institute of Statistical Mathematics
6:30 pm - 8:30 pm Welcome Reception - Grand Ballroom

Thursday, 16 November - Conference / Exhibition

Time Conference at Grand Ballroom / Exhibition at Foyer
8:20 am - 8:30 am Opening Ceremony
8:30 am - 9:15 am Invited Talk: Beyond Gaussian/ Ising Graphical Models
by Eunho Yang, KAIST, Korea
Chair: Yung-Kyun Noh
9:15 am - 9:35 am Morning Break
9:35 am - 11:35 am Session 2: Statistical/Bayesian Machine Learning
Chair: Hyunjung Helen Shin
  • #2.1: Probability Calibration Trees
    Tim Leathart, University of Waikato; Eibe Frank, University of Waikato; Geoffrey Holmes, University of Waikato; Bernhard Pfahringer, University of Auckland
  • #2.2: Data Sparse Nonparametric Regression with Epsilon-Insensitive Losses
    Maxime Sangnier, UPMC; Olivier Fercoq, Télécom ParisTech; Florence d'Alché-Buc, Télécom ParisTech
  • #2.3: Whitening-Free Least-Squares Non-Gaussian Component Analysis
    Hiroaki Shiino*, Yahoo Japan Corporation; Hiroaki Sasaki, Nara Institute of Science and Technology; Gang Niu, The University of Tokyo/ RIKEN; Masashi Sugiyama, RIKEN/ The University of Tokyo
  • #2.4: Magnitude-Preserving Ranking for Structured Outputs
    Céline Brouard, Aalto University; Eric Bach, Aalto University; Sebastian Böcker, Friedrich-Schiller University; Juho Rousu, Aalto University
  • #2.5: A Word Embeddings Informed Focused Topic Model
    He Zhao, Monash University; Lan Du, Monash University; Wray Buntine, "Monash University, Australia"
  • #2.6: A Mutually-Dependent Hadamard Kernel for Modelling Latent Variable Couplings
    Sami Remes, Aalto University; Markus Heinonen, Aalto University; Samuel Kaski, Aalto University
  • #2.7: Recovering Probability Distributions from Missing Data
    Jin Tian, Iowa State University
11:35 am - 1:00 pm Poster Session at Foyer/ Lunch Break at Cafeteria, Student Union
Poster Presentation: Session #1, #2, #3, #4
Paper# 1.1 - 1.7, 2.1 - 2.7, 3.1 - 3.7., 4.1 - 4.6
1:00 pm - 2:00 pm Keynote Talk: Causal Learning
by Bernhard Schölkopf, Max Planck Institute for Intelligent Systems, Germany
Chair: Masashi Sugiyama
2:00 pm - 4:00 pm Session 3: Machine Learning Applications
Chair: Masashi Sugiyama
  • #3.1: PHD: A Probabilistic Model of Hybrid Deep Collaborative Filtering for Recommender Systems
    Jie Liu, Shanghai Jiao Tong University; Dong Wang, Shanghai Jiao Tong University; Yue Ding, Shanghai Jiao Tong University
  • #3.2: Recognizing Art Style Automatically in Painting with Deep Learning
    Adrian Lecoutre, INSA Rouen; Benjamin Negrevergne, Université Paris-Dauphine; Florian Yger, Université Paris-Dauphine
  • #3.3: Computer Assisted Composition with Recurrent Neural Networks
    Christian Walder, DATA61; Dongwoo Kim, ANU
  • #3.4: Learning Deep Semantic Embeddings for Cross-Modal Retrieval
    Cuicui Kang, Institute of Information Engineering, CAS; Shengcai Liao, Institute of Automation, CAS; Zhen Li, Institute of Information Engineering, CAS; Zigang Cao, Institute of Information Engineering, CAS; Gang Xiong, Institute of Information Engineering, CAS
  • #3.5: Pyramid Person Matching Network for Person Re-identification
    Chaojie Mao, Zhejiang University; Yingming Li, Zhejiang University; Zhongfei Zhang, Zhejiang University; Yaqing Zhang, Zhejiang University; Xi Li, Zhejiang University
  • #3.6: Radical-level Ideograph Encoder for RNN-based Sentiment Analysis of Chinese and Japanese
    Yuanzhi Ke, Keio University; Masafumi Hagiwara, Keio University
  • #3.7: Attentive Path Combination for Knowledge Graph Completion
    Xiaotian Jiang, Institute of Information Engineering / School of Cyber Security, CAS; Quan Wang, Institute of Information Engineering / School of Cyber Security / State Key Laboratory of Information Security, CAS; Baoyuan Qi, Institute of Information Engineering / School of Cyber Security, CAS; Yongqin Qiu, Institute of Information Engineering / School of Cyber Security, CAS; Peng Li, Institute of Information Engineering / School of Cyber Security, CAS; Bin Wang, Institute of Information Engineering / School of Cyber Security, CAS
4:00 pm - 4:20 pm Afternoon Break
4:20 pm- 6:10 pm Session 4: Weakly-supervised/ Unsupervised Learning
Chair: Paul Weng
  • #4.1: ST-GAN: Unsupervised Facial Image Semantic Transformation Using Generative Adversarial Networks
    JiChao Zhang, Shandong University; Fan Zhong, Shandong University; Gongze Cao, Zhejiang University; Xueying Qin, Shandong University
  • #4.2: One Class Splitting Criteria for Random Forests
    Nicolas Goix, Télécom ParisTech; Nicolas Drougard, ISAE; Romain Brault*, Télécom ParisTech; Maël Chiapino, Télécom ParisTech
  • #4.3: Semi-supervised Convolutional Neural Networks for Identifying Wi-Fi Interference Sources
    Krista Longi, University of Helsinki; Teemu Pulkkinen, University of Helsinki; Arto Klami, University of Helsinki
  • #4.4: Learning RBM with a DC programming Approach
    Vidyadhar Upadhya, Indian Institute of Science, B; P S Sastry, Indian Institute of Science
  • #4.5: Learning Safe Multi-Label Prediction for Weakly Labeled Data
    Tong Wei, Nanjing University; Lan-Zhe Guo, Nanjing University; Yu-Feng Li*, Nanjing University; Wei Gao, Nanjing University
  • #4.6: Semi-Supervised AUC Optimization based on Positive-Unlabeled Learning
    Tomoya Sakai*, The University of Tokyo / RIKEN; Gang Niu, The University of Tokyo / RIKEN; Masashi Sugiyama, RIKEN / The University of Tokyo
6:30 pm - 9:00 pm Conference Banquet - Fradia, Han Riverside
Bus will leave for Fradia at 6:20pm

Friday, 17 November - Conference / Exhibition

Time Conference at Grand Ballroom / Exhibition at Foyer
8:30 am - 9:15 am Invited Talk: Beyond Deep Learning: Combining Neural Processing and Symbolic Processing
by Hang Li, Toutiao, China
Chair: Min-Ling Zhang
9:15 am - 9:35 am Morning Break
9:35 am - 11:35 am Session 5: Deep Learning
Chair: Alice Oh
  • #5.1: Learning Convolutional Neural Networks using Hybrid Orthogonal Projection and Estimation
    Hengyue Pan, York University; Hui Jiang, York University
  • #5.2: Limits of End-to-End Learning
    Tobias Glasmachers, Ruhr-University Bochum
  • #5.3: Locally Smoothed Neural Networks
    Liang Pang, Institute of Computing Technology, CAS / University of CAS; Yanyan Lan, Institute of Computing Technology, CAS; Jun Xu, Institute of Computing Technology, CAS; Jiafeng Guo, Institute of Computing Technology, CAS; Xueqi Cheng, Institute of Computing Technology, CAS
  • #5.4: Deep Competitive Pathway Networks
    Jia-Ren Chang, National Chiao Tung University; Yong-Sheng Chen*, National Chiao Tung University
  • #5.5: Scale-Invariant Recognition by Weight-Shared CNNs in Parallel
    Ryo Takahashi, Kobe University; Takashi Matsubara, Kobe University; Kuniaki Uehara, Kobe University
  • #5.6: Nested LSTMs
    Joel Ruben Antony Moniz, Carnegie Mellon University; David Krueger, Université de Montreal
  • #5.7: Neural-Power: Predict and Deploy Energy-Efficient Convolutional Neural Networks
    Ermao Cai, Carnegie Mellon University; Da-Cheng Juan, Google Research; Dimitrios Stamoulis, Carnegie Mellon University; Diana Marculescu, Carnegie Mellon University
11:35 am - 1:00 pm Poster Session at Foyer/ Lunch Break at Cafeteria, Student Union
Poster Presentation: Session #5, #6, #7
Paper# 5.1 - 5.7, 6.1 - 6.6, 7.1 - 7.7
1:00 pm - 2:00 pm Keynote Talk: Combining AI and Visualization to Manage Ecosystems
by Tom Dietterich, Oregon State University, USA
Chair: Kee-Eung Kim
2:00 pm - 3:50 pm Session 6: Learning Theory
Chair: Kee-Eung Kim
  • #6.1: Regret for Expected Improvement over the Best-Observed Value and Stopping Condition
    Vu Nguyen, Deakin University; Sunil Gupta, Deakin University; Santu Rana, Deakin University; Cheng Li, Deakin University; Svetha Venkatesh, Deakin University
  • #6.2: Distributionally Robust Groupwise Regularization Estimator
    Jose Blanchet, Columbia University; Yang Kang, Columbia University
  • #6.3: Rate Optimal Estimation for High Dimensional Spatial Covariance Matrices
    Aidong Adam Ding, Northeastern University; Yi Li, ; Jennifer Dy, Northeastern University
  • #6.4: A Quantum-Inspired Ensemble Method and Quantum-Inspired Forest Regressors
    Zeke Xie, The University of Tokyo; Issei Sato, The University of Tokyo
  • #6.5: On the Flatness of Loss Surface for Two-layered ReLU Networks
    Jiezhang Cao, South China University of Technology; Qingyao Wu, South China University of Technology; Yuguang Yan, South China University of Technology; Li Wang, University of Texas at Arlington; Mingkui Tan, South China University of Technology
  • #6.6: A Covariance Matrix Adaptation Evolution Strategy for Direct Policy Search in Reproducing Kernel Hilbert Space
    Ngo Anh Vien, Queen’s University of Belfast; Viet-Hung Dang, Duy Tan University; TaeChoong Chung, Kyung Hee University
3:50 pm - 4:10 pm Afternoon Break
4:10 pm - 6:10 pm Session 7: Multi-view, Multi-task, and Crowdsouced Learning
Chair: Yu-Feng Li
  • #7.1: Instance Specific Discriminative Modal Pursuit: A Serialized Approach
    Yang Yang, Nanjing University; De-Chuan Zhan, Nanjing University; Ying Fan, Nanjing University; Yuan Jiang, Nanjing University
  • #7.2: Multi-view Clustering with Adaptively Learned Graph
    Hong Tao, National University of Defense Technology; Chenping Hou, National University of Defense Technology; Jubo Zhu, National University of Defense Technology; Dongyun Yi, National University of Defense Technology
  • #7.3: Learning Predictive Leading Indicators for Forecasting Time Series Systems with Unknown Clusters of Forecast Tasks
    Magda Gregorová, University of Applied Sciences of Western Switzerland / University of Geneva; Alexandros Kalousis, University of Applied Sciences of Western Switzerland / University of Geneva; Stéphan Marchand-Maillet, University of Geneva
  • #7.4: Multi-Task Structured Prediction for Entity Analysis: Search-Based Learning Algorithms
    Chao Ma, Oregon State University; Janardhan Rao Doppa, Washington State University; Prasad Tadepalli, Oregon State University; Hamed Shahbazi, Oregon State University; Xiaoli Fern, Oregon State University
  • #7.5: Robust Plackett-Luce Model for k-ary Crowdsourced Preferences
    Bo Han, University of Technology Sydney; Yuangang Pan, University of Technology Sydney; Ivor W. Tsang, University of Technology Sydney
  • #7.6: Distributed Multi-task Classification: A Decentralized Online Learning Approach
    Chi Zhang, Nanyang Technological University; Peilin Zhao, Ant Financial; Shuji Hao, A*STAR; Yeng Chai Soh, Nanyang Technological University; Bu Sung Lee, Nanyang Technological University; Steven C.H. Hoi, Singapore Management University
  • #7.7: Crowdsourcing with Unsure Option
    Yao-Xiang Ding, Nanjing University; Zhi-Hua Zhou, Nanjing University
6:30 pm - 8:00 pm Closing Ceremony - Foyer