IEEE ICDM 2013 Conference in Dallas, TX – Day 3

On Tuesday, Dec. 10, Prof. Dr. JC. Mao (Microsoft, see picture below) presented his keynote talk titled “Large-Scale Learning in Computational Advertising”. The openness and detail of discussion is really appreciated! He discussed response prediction systems, multi-label random forests. In sum, great content!

After the coffee break, yours truly (@dirkvandenpoel) attended the “Social Media Mining: Fundamental Issues and Challenges” tutorial by Mohammad Ali Abbasi, Prof. Dr. Huan Liu, and Reza Zafarani (see pictures below).

During lunch, the ICDM community meeting was held.

Next, Prof. Dr. Shusaku Tsumoto (see picture below) took the stage to talk about the review process, which topics were accepted, … .

Finally, I attended that ICDM Panel on Data Mining with Big Data. From left to right: Professors Geoff Webb (Monash University, Australia), Zhi-Hua Zhou (Nanjing University, China), Xindong Wu (University of Vermont), Chris Clifton (Purdue University assigned to the NSF), Bhavani Thuraisingham (University of Texas at Dallas), Vipin Kumar (University of Minnesota), and Jian Pei (Simon Fraser University, Canada).

IEEE ICDM 2013 Conference in Dallas, TX – Day 2

 

On Monday, Dec. 9, the conference started with a keynote by Prof. Dr. Joydeep Ghosh (see picture below) titled “Predictive Healthcare Analytics under Privacy Constraints”. He covered several topics: availability of “Big” Data in healthcare, how to analyze such data, privacy-preserving measures.

 

 

Next, I joined the tutorial titled “Applied Matrix Analytics: Recent Advance and Case Studies” by H. Tong, F. Wang, Ch. Ding. They covered both theory (NMF: non-negative matrix factorization, CUR/CX decomposition, which features better interpretability than SVD, and the even better Colibri-S method) and applications.

 

 

Next, the focus shifted to the application of matrix math in health informatics. Dr. Fei Wang gave a very detailed talk on how to analyze Electronic Health Record data.

 

 

 

After lunch, all ICDM attendees boarded busses to either the Perot Museum of Nature and Science or the JFK tour to the Sixth Floor Museum (corner of Elm Str. and Houston). I chose the latter, so below you see some pictures of our tour.

 

That evening, the banquet was held at the Sheraton hotel. This also included an award ceremony, of course. Prof. Dr. Hans-Peter Kriegel (LMU Munich, Germany, see picture below) received the IEEE ICDM Research Contribution Award for outstanding research contributions, and Prof. Dr. Geoff Webb received the IEEE ICDM Outstanding Service Award. Congratulations!

IEEE ICDM 2013 Conference in Dallas, TX – Day 1

 

The IEEE International Conference on Data Mining (ICDM) started on Sunday, Dec. 8 with a welcome by the conference co-chair: Prof. Dr. Bhavani Thuraisingham (see picture below). Even tough the conference had 500+ registrations, the number of attendees was much lower due to the winter weather with freezing temperatures. 

Following the welcome, the first keynote talk titled “Opportunities and Challenges facing Recommender Systems: Where can we go from here?” was held by Prof. Dr. Alexander Tuzhilin (NYU, see picture below).

He discussed the state-of-the-art in recommender systems. He grouped them into first generation (1G), 2G, and context-award 3G recommender systems (CARS).

 

Next, I attended the Classification I session. The first paper was by A. Dukkipati, G. Pandey, D. Ghoshdastidar, P. Koley, and D.M.V.S. Sriram titled “Generative Maximum Entropy Learning for Multiclass Classification” (see pictures below).

Meng Fang, Yin Jie, and Xingquan Zhu presented their talk “Transfer Learning across Networks for Collective Classification” (see pictures below).

Next, Xu-Ying Liu, Qian-Qian Li & Zhi-Hua Zhou (see pictures below) presented their paper “Learning Imbalanced Multi-Class Data with Optimal Dichotomy Weights”.

 

Finally, F. Giannotti, L. Milli, A. Monreale, D. Pedreschi, G. Rossetti & F. Sebastiani presented their talk “Quantification Trees”.

 

After lunch, I attended the Graph and Network Mining session. The first talk I saw was titled “Blocking Simple and Complex Contagion By Edge Removal” (Ch. Kuhlman, G. Tuli, S. Swarup, M. Marathe, and S.S. Ravi).

 

 

Next, Danai Koutra (co-authors: H. Tong, D. Lubensky) presented their paper titled “BIG-ALIGN: Fast Bipartite Graph Alignment”.

Finally, Petko Bogdanov (see picture below) presented their talk (co-authors: M. Monglovi & A. Singh) titled “Mining Evolving Network Processes”.

During the breaks we had plenty of opportunity for networking.

Next, I attended the talk about “Statistical Selection of Congruent Subspaces for Outlier Detection on Attributed Graphs” (authors: P.I. Sanchez, E. Mueller, F. Laforet, F. Keller, K. Boehm).

 

That evening, the welcome reception was held (see pictures below). This also included a poster session.

 

Data Mining for Service (DMS 2013) Workshop at IEEE ICDM in Dallas, TX

 

On Saturday, Dec. 7, 2013, Prof. Dr. Shusaku Tsumoto (Shimane University, see picture above) and Prof. Dr. Katsutoshi Yada (Kansai University, see picture above) organized another edition of the Data Mining for Service Workshop (DMS 2013), just prior to the IEEE ICDM conference. Even though the ice storm the day before the workshop tried to throw off many travel plans many attendees still made it to the DMS event. After an introduction by the workshop organizers, Prof. Dr. Sano (see picture below) gave his talk titled “Evaluation of Discount Effect Using Poisson Regression Based on Interaction Effect Between Bargain Scale and Product Category” (co-author: Tomomichi Suzuki).

Next, it was my turn to present our paper “Using Eye-Tracking Data of Advertisement Viewing Behavior to Predict Customer Churn” (co-author: Michel Ballings).

 

After the break, Dr. Yi Zuo (co-author: Prof. Dr. Katsutoshi Yada) took the stage with his talk “Application of Bayesian Network Sheds Light on Purchase Decision Process basing on RFID Technology”.

Next, Maitreya Natu, Vaishali Sadaphal, Anuja Kelkar, Utkarsh Naiknaware, Sachin Sukhlecha and Ashish Sanadhya presented her talk “Analytics-Based Solutions for Improving Alert Management Service for Enterprise Systems”.

After lunch, Dr. Edward M.L. Peters (co-authors: Guido Dedene and Jonas Poelmans) presented a talk “Understanding Service Quality and Customer Churn by Process Discovery for a Multi-National Banking Contact Center”.

 

 

Next, the paper by Ban Kawas, Mark Squillante, Dharmashankar Subramanian and Kush Varshney was presented titled “Prescriptive Analytics for Allocating Sales Teams to Opportunities”.

Next, Dr. Shoji Hirano (Shimane University, Japan, see picture below) presented his work titled “Clustering of order sequences based on the typicalness index for finding clinical pathway candidate” (co-author: Prof. Dr. Shusaku Tsumoto).

Finally, the two organizers of the DMS 2013 workshop Prof. Dr. Shusaku Tsumoto and Prof. Dr. Katsutoshi Yada wrapped up the session. Even though the keynote speaker was stuck at some airport in the US (due to the severe winter weather) it was a very nice event. Congratulations to the organizers!

SC13 Supercomputing Conference in Denver, CO – Conference Day 1

 

Tuesday, Nov. 19 started off with a keynote presentation titled “The Secret Life of Data” by Dr. Genevieve Bell (@feraldata, Intel Fellow). She gave many examples about the value of data: The first example is the Domesday book. Next, she discussed the value of visualizations.

Next, Prof. Dr. Klaus Schulten (University of Illinois Urbana-Champaign, see picture below) took the stage for the first invited talk on “The State of Extreme-Scale Molecular Dynamics (in Computational Biology)”. He explained how they use computational models to explain how drugs attack viruses (e.g. interfere in the communication, acting as a con-artist).

 

Next, Prof. Dr. Takashi Furumura (Earthquake Research Institute, University of Tokyo, see picture below) presented a great keynote speech on the topic of “Visualization of Strong Ground Motion and Tsunami for the Great Earthquake of 2011 Off Tohoku, Japan”. 

Several years ago, the Kobe earthquake was analyzed in great detail. This led to the installation of many more sensors across the entire country. The outcome was a prediction of a M7.5 earthquake in the area off Tohoku. It happened, but was much stronger: In 2011 a magnitude 9.0 earthquake off Tohoku took place. Thanks to the many sensors, very detailed measurements were available. As a result of having better data, Japanese researchers were able to create a compound ground motion and tsunami simulation (instead of separate ones)! After building the prediction models, they then applied it to the likely new earthquakes…

 

 

Next, I walked the show floor again. Japanese universities and research institutes had a strong presence in Denver.

The NAIST (Nara Institute of Science and Technology, see picture below) showed a video documenting the interesting concept of placing HPC equipment in containers. They have two such HPC installations in production.

After lunch, I attended the Awards ceremony. Prof. Dr. Jack Dongarra (University of Tennessee) received the Ken Kennedy Award. He gave an acceptance speech sharing many interesting ideas and anecdotes in his career.

 

Next, Prof. Dr. Marc Snir (University of Illinois, Urbana-Champaign) gave his acceptance speech for the IEEE Computer Society Seymour Cray Computer Engineering Award (@ComputerSociety).

 

 

 

Finally, Prof. Dr. Chris Johnson (University of Utah) accepted the IEEE CS Fernbach Award for his visualization institute. 

Next, I attended the European Cray meeting. Cray CEO (@Cray_Inc), Peter Ungaro (see picture below), discussed the highlights of their strategy: The fusion of Supercomputing and Big Data.