Georgia Tech researchers are heading to London this week to take part in the 24th Association for Computing Machinery SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).
KDD is the world’s premier forum for advancement, education, and adoption of the science of knowledge discovery and data mining and is being held August 19-23. The program includes keynotes, invited talks, workshops, hands-on tutorials, and conventional tutorials.
Faculty and students in the School of Computational Science and Engineering (CSE) and associated research units – Center for Machine Learning, School of Computer Science, and the Institute for Information Security and Privacy, are presenting at this year’s conference.
“It is incredibly exciting to be part of the Georgia Tech team of talented students and faculty, showcasing our diverse research achievements at KDD, ranging from scalable methods for health applications, novel approaches for searching for lead pipes in Flint, to practical defense for artificial intelligence,” said CSE Associate Professor Polo Chau.
Chau will be joined by more than 10 other faculty members and student researchers from Georgia Tech sharing 10 papers in oral, poster, and demo presentations during the five-day event.
In addition to these 10 papers – including one of Chau’s research team’s latest publications, which aims to protect artificial intelligence systems from malicious attacks – Georgia Tech researchers are presenting a conventional tutorial and an all-day workshop. The workshop, Interactive Data Exploration and Analytics, addresses the development of data mining techniques with 13 papers accepted for presentation from various research institutions and groups across the globe.
To help attendees and others interested in the conference, Georgia Tech has developed an interactive data visualization detailing of its research papers, as well as dates, times, and locations for the associated talks.
Below are the titles of Georgia Tech’s research being presented this week along with each paper’s respective authors. Each title is linked to the full paper.
- Decoupled Learning for Factorial Marked Temporal Point Processes (Weichang Wu, Junchi Yan, Xiaokang Yang, Hongyuan Zha)
- Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation (Lu Wang, Wei Zhang, Xiaofeng He, Hongyuan Zha)
- SUSTain: Scalable Unsupervised Scoring for Tensors and its Application to Phenotyping (Ioakeim Perros, Evangelos Papalexakis, Haesun Park, Richard Vuduc, Xiaowei Yan, Christopher Defilippi, Walter F. Stewart, Jimeng Sun)
- PCA by Determinant Optimization has no Spurious Local Optima (Raphael Hauser, Armin Eftekhari, Heinrich Matzinger)
- RAIM: Recurrent Attentive and Intensive Modeling of Multimodal Continuous Patient Monitoring Data (Yanbo Xu, Siddharth Biswal, Shriprasad Deshpande, Kevin Maher, Jimeng Sun)
- An Iterative Global Structure-Assisted Labeled Network Aligner Abdurrahman Yaşar (Georgia Institute of Technology)
- ActiveRemediation: The Search for Lead Pipes in Flint, Michigan (Jacob Abernethy, Alex Chojnacki, Arya Farahi, Eric Schwartz, Jared Webb)
- Detection of Paroxysmal Atrial Fibrillation using Attention based Bidirectional Recurrent Neural Net (Supreeth Prajwal Shashikumar, Amit Shah, Gari Clifford, Shamim Nemati)
- Compression to the Rescue: Defending from Adversarial Attacks Across Modalities (Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen, Fred Hohman, Siwei Li, Li Chen, Michael E. Kounavis, Duen Horng Chau)
- Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression (Nilaksh Das, Madhuri Shanbhogue, Shang-Tse Chen, Fred Hohman, Siwei Li, Li Chen, Michael E. Kounavis, Duen Horng Chau)
Workshops and Tutorials: