AI

IBM Research AI at KDD 2019

Share this post:

The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2019) is August 4 – 8, 2019 in Anchorage, Alaska. IBM Research has been at the forefront of knowledge discovery and data mining research for more than a quarter century and is a proud Platinum level sponsor of the conference.

With the explosive growth of structured and unstructured data in enterprise domains, new technologies are needed to effectively manage, extract insights and exploit this data. IBM Research AI is committed to developing new technologies for advancing, trusting, and scaling AI that address the increasing reliance of enterprises on growing volumes and variety of data.  We are excited to participate in the annual KDD conference, which is a hotbed of innovation in these areas, and provides a fantastic opportunity to interact with top students and researchers in the field.

At KDD 2019, IBM Research AI will present technical papers describing the latest results in deep learning for graphs, adversarial learning, text understanding, and data science for healthcare, financial crimes, and scientific discovery.

Charu Aggarwal received the SIGKDD innovation award for his reseaarch contributions in high-dimensional data, privacy, data streams, uncertain data, graphs, text mining, and social networks

Charu Aggarwal received the SIGKDD innovation award for his research contributions in high-dimensional data, privacy, data streams, uncertain data, graphs, text mining, and social networks

At KDD’s opening ceremony, IBM Research Staff Member Charu Aggarwal received the SIGKDD innovation award for lifetime achievements in data mining. Congratulations to Charu! He is also presenting three of his papers at the conference (see below).

At our booth (#3), we will showcase tech demos of our latest AI technologies, including collaboration with AI to create your own work of art, automatically creating customized neural network models using IBM’s NeuNetS, building trust in AI using our open source AI Fairness 360 Toolkit, one-of-a-kind analog AI chip, Adversarial Robustness 360 toolbox, and more.

Please stop by the and attend our presentations and workshops listed below. Hope to see you in Anchorage!

Accepted papers – research track

Coupled Variational Recurrent Collaborative Filtering
Qingquan Song, Shiyu Chang, Xia Hu
Tuesday, August 6, 7:00 – 9:30am, Idlughet Hall 3, Street Level, Dena’ina

Efficient Global String Kernel with Random Features: Beyond Counting Substructures
Lingfei Wu, Ian En-Hsu Yen, Siyu Huo, Liang Zhao, Kun Xu, Liang Ma, Shouling Ji, Charu Aggarwal
Wednesday, August 7, 10:00am – 12:00pm, Summit 2, Ground Level, Egan Center

Graph Convolutional Networks with EigenPooling
Yao Ma, Suhang Wang, Charu Aggarwal, Jiliang Tang
Tuesday, August 6, 7:00 – 9:30am, Idlughet Hall 3, Street Level, Dena’ina

PerDREP: Personalized Drug Effectiveness Prediction from Longitudinal Observational Data
Sanjoy Dey, Ping Zhang, Daby Sow, Kenney Ng
Tuesday, August 6, 4:00 – 6:00pm, Summit 4, Ground Level, Egan Center

Revisiting kd-tree for Nearest Neighbor Search
Parikshit Ram, Kaushik Sinha
Tuesday, August 6, 10:00am – 12:00pm, Summit 4, Ground Level, Egan Center

Scalable Global Graph Kernel Using Random Features:  From Node Embedding to Graph Embedding
Lingfei Wu, Ian En-Hsu Yen, Zhen Zhang, Kun Xu, Liang Zhao, Xi Peng, Yinglong Xia, Charu Aggarwal
Tuesday, August 6, 1:30 – 3:30pm, Summit 2, Ground Level, Egan Center

Scalable Hierarchical Clustering via Tree Grafting
Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, Michael Glass, Andrew Mccallum
Wednesday, August 7, 10:00am – 12:00pm, Summit 3, Ground Level, Egan Center

Accepted papers – applied data science track

A Robust Framework for Accelerated Outcome-driven Risk Factor Identification from EHR
Prithwish Chakraborty, Faisal Farooq
Poster blitz session: Tuesday, August 6, 1:00 – 6:00pm, Tikahtnu Ballroom, Level 3, Dena’ina
Poster reception: Tuesday, August 6, 7:00 – 9:30am, Idlughet Hall 3, Street Level, Dena’ina

Workshop papers

Workshop: KDD Cup
Paper:  Policy Learning for Malaria Elimination
Authors: Oliver Bent, Sekou Remy, Charles Wachira, Nelson Bore
Tuesday, August 6, 10:00 am – 5:00 pm, Arteaga Room, Street Level, Egan Center

Workshop: Fragile Earth
Paper:  Accelerating Physics-Based Simulations Using Neural Network Proxies: An Application in Oil Reservoir Modeling
Authors: Jiri Navratil, Alan King, Jesus Rios Aliaga, Georgios Kollias, Ruben Torrado, Andres Codas Duarte
Monday, August 5, 8:00am – 12:00pm, Summit 3, Ground Level, Egan

Workshop: Applied Data Science for Healthcare
Paper:  An Information Extraction and Knowledge Graph Platform for Accelerating Biochemical Discoveries
Authors: Matteo Manica, Christoph Auer, Valery Weber, Federico Zipoli, Michele Dolfi, Peter Staar, Teodoro Laino, Costas Bekas, Akihiro Fujita, Hiroki Toda, Shuichi Hirose, Yasumitsu Orii
Monday, August 5, 1:00 – 5:00 pm, Summit 3, Ground Level, Egan

Workshop: Applied Data Science for Healthcare
Paper: Understanding Behavior of Clinical Models under Domain Shifts
Jayaraman J. Thiagarajan, Deepta Rajan and Prasanna Sattigeri
Monday, August 5, 1:00 – 5:00 pm, Summit 3, Ground Level, Egan

Workshop: Anomaly Detection in Finance
Paper:  Experiments in Graph Deep Learning for Cryptocurrency Forensics
Authors: Mark Weber, Jie Chen, Giacomo Domeniconi, Charles Leiserson, Claudio Bellei, Moreno Bonaventura
Monday, August 5, 8:00 – 12:00, Summit 8, Ground Level, Egan

Workshop:  Explainable AI (XAI)
Paper:  On Fairness in Budget-Constrained Decision Making
Authors: Michiel A. Bakker, Alejandro Noriega-campero, Duy Patrick Tu, Prasanna Sattigeri, Kush Varshney, Alex ‘Sandy’ Pentland
Monday, August 5, 8:00 – 12:00, Summit 7, Ground Level, Egan

Workshop:  The Third International Workshop on Automation in Machine Learning
Paper:  Learning the Exploration for the Contextual Bandit
Authors: Djallel Bouneffouf, Emmanuel Claeys
Monday, August 5, 1:00 – 5:00, Summit 11, Ground Level, Egan

Workshop:  Adversarial Learning Methods for Machine Learning and Data Mining
Paper:  Corrupted Contextual Bandit
Author: Djallel Bouneffouf
Monday, August 5, 8:00 – 12:00, Tubughnenq 5, Level 2, Dena’ina

Workshop:  Adversarial Learning Methods for Machine Learning and Data Mining
Paper:  Generation of Low Distortion Adversarial Attacks via Convex Programming
Authors: Tianyun Zhang, Sijia Liu, Yanzhi Wang, Makan Fardad
Monday, August 5, 8:00 – 12:00, Tubughnenq 5, Level 2, Dena’ina

Workshop:  Adversarial Learning Methods for Machine Learning and Data Mining
Paper:  Defending against Backdoor Attack on Deep Neural Networks
Authors: Hao Cheng, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Pu Zhao, Xue Lin
Monday, August 5, 8:00 – 12:00, Tubughnenq 5, Level 2, Dena’ina

Workshop:  Adversarial Learning Methods for Machine Learning and Data Mining
Paper:  Block Switching: A Stochastic Approach for Deep Learning Security
Authors: Xiao Wang, Siyue Wang, Pin-Yu Chen, Xue Lin, Peter Chin
Monday, August 5, 8:00 – 12:00, Tubughnenq 5, Level 2, Dena’ina

Workshop:  Deep Learning on Graphs: Methods and Applications
Paper:  Deep Graph Translation
Authors: Xiaojie Guo, Lingfei Wu, Liang Zhao
Monday, August 5, 1:00 – 5:00, Summit 10, Ground Level, Egan

Workshop:  Deep Learning on Graphs: Methods and Applications
Paper:  An Empirical Study of Graph Neural Networks Based Semantic Parsing
Authors: Shucheng Li, Lingfei Wu, Shiwei Feng, Fangli Xu, Fengyuan Xu and Sheng Zhong
Monday, August 5, 1:00 – 5:00, Summit 10, Ground Level, Egan

Workshop:  Deep Learning on Graphs: Methods and Applications
Paper:  Exploiting Graph Neural Netwrks with Context Information for RDF-to-Text Generation
Authors: Hanning Gao, Lingfei Wu, Po Hu and Fangli Xu
Monday, August 5, 1:00 – 5:00, Summit 10, Ground Level, Egan

Tutorials

Recent Progress in Zeroth Order Optimization and Its Applications to Adversarial Robustness in Data Mining and Machine Learning
Pin-Yu Chen, Sijia Liu
Sunday, August 4, 1:00-5:00 pm, Summit 4, Ground Level, Egan

Declarative Text Understanding with SystemT
Yunyao Li, Laura Chiticariu, Marina Hailpern, Sanjana Sahayaraj,  Teruki Tauchi
Sunday, August 4, 1:30-4:30pm, Tubughnenq 5, Level 2, Dena’ina

Workshops co-organized by IBM

Parallel and Distributed Computing for Large-Scale Machine Learning and Big Data Analytics
Arindam Pal, Henri Bal, Azalia Mirhoseini, Thomas Parnell, Anand Panangadan, Sutanay Choudhury, Yinglong Xia
Monday, August 5, 8:00am – 12pm

Fragile Earth: Theory Guided Data Science to Enhance Scientific Discovery
Naoki Abe, Kathleen Buckingham, Emre Eftelioglu, James Hodson, Auroop R. Ganguly, Ramakrishnan Kannan
Monday, August 5, 8:00am – 12pm

Adversarial Learning Methods for Machine Learning and Data Mining
Pin-Yu Chen, Cho-Jui Hsieh, Bo Li, Sijia Liu
Monday, August 5, 8:00am – 12pm

Deep Learning on Graphs: Methods and Applications
Jian Pei, Lingfei Wu, Yinglong Xia, Hongxia Yang
Monday, August 5, 1:00-5:00 pm

Applied Data Science for Healthcare
Fei Wang, Pei-Yun Sabrina Hsueh, Prithwish Chakraborty, Carly Eckert, Mansoor Saqi, Lixia Yao, Fred Rahmanian, Muhammad Aurangzeb Ahmad, Ankur Teredesai
Monday, August 5, 1:00-5:00 pm

Research Staff Member, IBM Research

More AI stories

MIT-IBM Watson AI Lab Welcomes Inaugural Members

Two years in, and the MIT-IBM Watson AI Lab is now engaging with leading companies to advance AI research. Today, the Lab announced its new Membership Program with Boston Scientific, Nexplore, Refinitiv and Samsung as the first companies to join.

Continue reading

Adversarial Robustness 360 Toolbox v1.0: A Milestone in AI Security

IBM researchers published the first major release of the Adversarial Robustness 360 Toolbox (ART). Initially released in April 2018, ART is an open-source library for adversarial machine learning that provides researchers and developers with state-of-the-art tools to defend and verify AI models against adversarial attacks. ART addresses growing concerns about people’s trust in AI, specifically the security of AI in mission-critical applications.

Continue reading

Making Sense of Neural Architecture Search

It is no surprise that following the massive success of deep learning technology in solving complicated tasks, there is a growing demand for automated deep learning. Even though deep learning is a highly effective technology, there is a tremendous amount of human effort that goes into designing a deep learning algorithm.

Continue reading