Abstract

The goal of this tutorial is to bring together data scientists, AI researchers, and social scientists to discuss research problems and challenges in computational event modeling. Traditional machine learning models for societal event forecasting focus on predictive performance using structured data. We present new directions of interpretable AI/ML models for predictive analysis in dynamic, heterogeneous, and multi-source event data. The tutorial will cover technical material related to event detection, forecasting, and precursor identification with assumed preliminary knowledge in supervised learning, deep learning, and temporal event modeling. First, we will introduce formal definitions of event prediction and event precursors, along with a brief discussion on the methods applied in this field. Next, we will present recently developed deep learning methods including dynamic graph convolutional networks in event forecasting and actor (participant) inference. Last, we will discuss real-world applications based on temporal event modeling.

Slides

Outline

• Introduction
• Societal Event Prediction
• Main Challenges in Explainable Event Prediction
• Temporal Event Forecasting
• Part 1: Precursor Identification in Spatio-Temporal Event Forecasting
• Nested Multi-instance learning
• Multi-task learning
• Part 2: Event Graphs for Interpretable Event Forecasting
• Dynamic Graph Convolutional Networks
• Dynamic Knowledge Graph based Multi-Event Forecasting
• Cross-location Attention Mechanisms
• Summary and Future Work

Presenters

• Songgaojun Deng is a PhD candidate in the Department of Computer Science at Stevens Institute of Technology. Her research interests are machine learning and deep learning in social informatics and health informatics. Her current research focuses on developing graph neural networks to capture dynamic and interpretable graph-based patterns.

• Yue Ning is an Assistant Professor in the department of Computer Science at Stevens Institute of Technology. Dr. Ning received her Ph.D. in Computer Science at Virginia Tech. Her research focuses on applied machine learning, data analytics, and social media analysis motivated by real-world problems in social informatics, health informatics, and personalization.

• Huzefa Rangwala is the Lawrence Cranberg Faculty Fellow and Professor in the Department of Computer Science at George Mason University. His research interests are data mining and machine learning applications in the areas of biological sciences, learning sciences and cyber-physical sciences involving fundamental contributions of multitask learning, hierarchical classification, and recommender systems.

References