Time series data are ubiquitous. In domains as diverse as finance, entertainment, transportation and
health care, we observe a fundamental shift away from parsimonious, infrequent measurement to nearly
continuous monitoring and recording. Rapid advances in diverse sensing technologies, ranging from
remote sensors to wearables and social sensing, are generating a rapid growth in the size and
complexity of time series archives. Thus, although time series analysis has been studied
extensively, its importance only continues to grow. What is more, modern time series data pose
significant challenges to existing techniques (e.g., irregular sampling in hospital records and
spatiotemporal structure in climate data). Finally, time series mining research is challenging and
rewarding because it bridges a variety of disciplines and demands interdisciplinary solutions. Now
is the time to discuss the next generation of temporal mining algorithms.
The focus of MiLeTS workshop is to synergize the research in this area and discuss both new and open
problems in time series analysis and mining. The solutions to these problems may be algorithmic,
theoretical, statistical, or systems-based in nature. Further, MiLeTS emphasizes applications to
high impact or relatively new domains, including but not limited to biology, health and medicine,
climate and weather, road traffic, astronomy, and energy.
The MiLeTS workshop will discuss a broad variety of topics related to time series, including:
08:00-08:10 Opening remarks
08:10-09:10 Keynote Talk
09:10-09:30 Contributed Talk
09:30-10:00 Coffee Break
10:00-11:00 Contributed Talks
11:00-12:00 Keynote Talk
12:00-13:00 Lunch Break
13:00-14:00 Keynote Talk
14:00-15:30 Poster Session & Coffee Break
15:30-16:50 Contributed Talks
16:50-17:00 Concluding Remarks
Today, we are collecting an immense amount of health data both inside and outside of the hospital.
While clinicians are studying ever more data about their patients, they are still ignoring the vast
majority of it. Transforming these observational data into actionable knowledge is challenging due
to a number of reasons including the presence of confounders, missing context, and complex
longitudinal relationships. At the same time, due to the high-stakes nature of healthcare, the field
requires tools that are not only accurate, but also interpretable and robust. In this talk, I will
present ongoing work focused on developing solutions to these challenges. In particular, I will show
how clinical domain expertise can be used to help guide model training and selection.
Bio
Jenna Wiens is a Morris Wellman Assistant Professor of Computer Science and Engineering (CSE) at the
University of Michigan in Ann Arbor. Her primary research interests lie at the intersection of
machine learning, data mining, and healthcare. She is particularly interested in time-series
analysis. The overarching goal of her research agenda is to develop the computational methods needed
to help organize, process, and transform patient data into actionable knowledge. Jenna received her
PhD from MIT in 2014. In 2015 she was named Forbes 30 under 30 in Science and Healthcare; she
received an NSF CAREER Award in 2016; and recently she was named to the MIT Tech Review's list of
Innovators Under 35.
Bio
Qiaozhu Mei is an associate professor at the University of Michigan School of Information. He
received his PhD degree from the Department of Computer Science at the University of Illinois at
Urbana-Champaign and Bachelor's degree from Peking University.
His interested in analyzing large scale text data, social and information networks, and user
behavior data. His research is broadly applied to Web search and mining, social computing,
scientific
literature mining, and health informatics. He also broadly interested in natural language
processing, machine learning, and social network analysis.
Bio
Kyunghyun Cho is an assistant professor of computer science and data science at New York University
and a research scientist at Facebook AI Research. He was a postdoctoral fellow at University of
Montreal until summer 2015 under the supervision of Prof. Yoshua Bengio, and received PhD and MSc
degrees from Aalto University early 2014 under the supervision of Prof. Juha Karhunen, Dr. Tapani
Raiko and Dr. Alexander Ilin. He tries his best to find a balance among machine learning, natural
language processing, and life, but almost always fails to do so.
Many applications, ranging from automobiles to financial markets and wearable sensors,
generate large amounts of time series data. In most cases, this data is multivariate and
heterogeneous, where the readings come from various types of entities, or sensors. These time series
datasets are often sparse, unlabeled, dynamic, and difficult to interpret. Therefore, there is a
need for methods that learn interpretable structure from such data, especially for methods that can
apply across many different domains. In this talk, I will discuss several approaches for analyzing
time series data, as well as future directions of research in this field, incorporating different
research areas ranging from distributed convex optimization to deep learning.
Bio
Jure Leskovec is Associate Professor of Computer Science at Stanford University, Chief Scientist at
Pinterest, and investigator at Chan Zuckerberg Biohub. His research focuses on machine learning and
data mining applied to social, information and biological networks, their evolution, and the
diffusion of information and influence over them. Computation over massive data is at the heart of
his research and has applications in computer science, social sciences, economics, marketing, and
healthcare. This research has won several awards including a Lagrange Prize, Microsoft Research
Faculty Fellowship, the Alfred P. Sloan Fellowship, and numerous best paper awards. Leskovec
received his bachelor's degree in computer science from University of Ljubljana, Slovenia, and his
PhD in in machine learning from the Carnegie Mellon University and postdoctoral training at Cornell
University.
Graph-Based Deep Modeling and Real Time Forecasting of Sparse Spatio-Temporal Data Bao Wang, Xiyang Luo, Fangbo Zhang, Baichuan Yuan, Andrea Bertozzi and Jeffrey Brantingham
Sample Path Generation for Probabilistic Demand Forecasting Dhruv Madeka, Lucas Swiniarski, Dean Foster, Leonid Razoumov, Ruofeng Wen and Kari Torkkola
Knowledge Discovery Approach from Blockchain, Crypto-currencies, and Financial Stock Exchanges Sofiane Lagraa, Jérémy Charlier and Radu State
Learning Latent Events from Network Message Logs Siddhartha Satpathi, Supratim Deb, R Srikant and He Yan
A Nonparametric Approach to Ensemble Forecasting Eugene Chen, Xiaojing Dong, Zhiyu Wang and Zhenyu Yan
MDL-based Development of Ensembles with Active Learning over Evolving Data Streams Samaneh Khoshrou and Mykola Pechenizky
Nested LSTM: Modeling Taxonomy and Temporal Dynamics in Location-Based Social Network Xuan-An Tseng, Da-Cheng Juan, Chun-Hao Liu, Wei Wei, Yu-Ting Chen, Shih-Chieh Chang and Jia-Yu Pan
Econometric Modeling of Systemic Risk: A Time Series Approach Jalal Etesami, Ali Habibnia and Negar Kiyavash
Hyper-network based Change Point Detection in Dynamic Networks Tingting Zhu, Ping Li, Kaiqi Chen, Yan Chen and Lanlan Yu
Comparing Prediction Methods in Anomaly Detection: An Industrial Evaluation Ralf Greis, Cu Duy Nguyen and Thorsten Ries
Detecting Granger-causal relationships in global spatio-temporal climate data via multi-task learning Christina Papagiannopoulou, Diego Miralles, Matthias Demuzere, Niko Verhoest and Willem Waegeman
Manifold Alignment and Wavelet Analysis For Fault Detection Across Machines Hala Mostafa, Soumalya Sarkar and George Ekladious
Reconstruction and Regression Loss for Time-Series Transfer Learning Nikolay Laptev, Jiafan Yu and Ram Rajagopal
Finding Multidimensional Patterns in Multidimensional Time Series Emil Laftchiev and Yuchao Liu
Submissions should follow the SIGKDD formatting requirements and will be evaluated using the SIGKDD Research Track evaluation criteria. Preference will be given to papers that are reproducible, and authors are encouraged to share their data and code publicly whenever possible. Submissions are limited to a total of 10 pages, including all content and references, and must be in PDF format and formatted according to the new Standard ACM Conference Proceedings Template. Submissions will be managed via the MiLeTS 2018 EasyChair website.
Note on open problem submissions: In order to promote new and innovative research on time series, we plan to accept a small number of high quality manuscripts describing open problems in time series analysis and mining. Such papers should provide a clear, detailed description and analysis of a new or open problem that poses a significant challenge to existing techniques, as well as a thorough empirical investigation demonstrating that current methods are insufficient.
Instructions for Oral/Poster presentation: Every accepted submission will have a poster presentation in the afternoon session. The size of the poster is recommendation to be A0 (33.1 x 46.8 in) or smaller. Besides, each accepted (oral) paper will have a 20 minutes presentation (including Q&A) at assigned time slot.
Any questions may be directed to the workshop e-mail address: kdd.milets18@gmail.com.
Paper Submission Deadline: May 8th, 2018, May 15th, 2018 11:59PM Alofi Time
Author Notification: June 8th, 2018 , June 11th, 2018
Camera Ready Version: June 29th, 2018
Workshop: August 20th, 2018
University of California Riverside
University of Southern California
University of New Mexico
University of Southern California