Keynote Talk

Disparate Graph Learning

Abstract: The emergence of deep learning models designed for graph and network data, often under an umbrella term named graph machine learning, has largely streamlined many graph learning problems in various science and engineering disciplines, ranging from biology, climate science, pharmaceutical science, to epidemiology. In many settings, graphs are often disparate, meaning that they are collected from different sources, they are in discrete spaces with varying sizes and different graphs are often not aligned. In this talk, I will introduce some of our recent works on learning from such disparate graphs, centered around the following four research questions, including (Q1. Alignment) how to align multi-sourced graphs? (Q2. Dictionary Learning) how to learn multi-level, interpretable embedding from disparate graphs? (Q3. Augmentation) how to augment weak supervision for disparate graph learning? and (Q4. Adaptation) How to adapt a graph learning model to a disparate graph?

Short Bio: Hanghang Tong is currently a professor at the Siebel School of Computing and Data Science at University of Illinois at Urbana-Champaign. Before that, he was an associate professor at School of Computing, Informatics, and Decision Systems Engineering (CIDSE), Arizona State University. He received his M.Sc. and Ph.D. degrees from Carnegie Mellon University in 2008 and 2009, both in Machine Learning. He has published 300+ papers and his research has received several awards, including SDM/IBM 2018 early career data mining research award, two ‘test of time’ awards (ICDM 2015 & 2022 10-Year Highest Impact Paper award), ICDM Tao Li award (2019), NSF CAREER award, and several best paper awards (e.g., ICDM’06 best paper, SDM’08 best paper, CIKM’12 best paper, etc.). He was Editor-in-Chief of ACM SIGKDD Explorations (2018–2022), and is Editor-in-Chief of ACM Computing Surveys (CSUR). He is a fellow of IEEE (2022), a university scholar (2024), a senior member of AAAI (2024), and a fellow of ACM (2025).

Workshop & Tutorial

Agentic AI as a System for Engineering Research

Overview: Large language models are most useful to researchers when they stop being a chat window and start being a system: a set of tools, a plan, and an agent that runs the plan. This 60-minute workshop opens with a 20-minute presentation on what an agentic AI system actually is — tools, memory, planning loops, and where these systems break — and then moves into 40 minutes of hands-on practice in which every attendee builds and runs a working research pipeline on their own machine.

The hands-on part follows a single three-stage pipeline that mirrors how engineering research is actually done:

Two Parallel Tracks — Same Concepts, Different Stack

Attendees choose the track that fits their setup. Both cover identical material, so nobody is left behind by a missing API key or an unsupported laptop.

Presenter: Harun Pirim is a faculty member at North Dakota State University and General Co-Chair of INTCEC 2026. His work spans network science, machine learning and data-driven decision systems for engineering problems. For questions about the workshop, contact harun.pirim@ndsu.edu.