Learning Agent-Based Models from Data

Описание: Date Presented: 11/18/2025
Speaker: Gianmarco De Francisci Morales, CENTAI

Visit links below to subscribe and for details on upcoming seminars:
https://www.isi.edu/isi-seminar-series
https://www.isi.edu/events

Abstract:
Agent-Based Models (ABMs) are used in several fields to study the evolution of complex systems according to micro-level assumptions. These models encode the causal mechanisms that drive the dynamic processes and have the advantage of being easy to interpret. However, they do not take advantage of the widespread availability of data, so their predictive power is often limited. In addition, there is no principled way to do parameter calibration and model selection. Finally, ABMs typically can not estimate agent-specific (or “micro”) state variables. In this talk, I showcase a line of research aimed at learning the latent parameters and micro-level variables of an ABM from data. The key idea is to cast the ABM into a probabilistic generative model. This transformation follows two general design principles: balance of stochasticity and data availability, and replacement of unobservable discrete choices with differentiable approximations. Given this new form of the model, we can derive a proper likelihood function and proceed to maximize the likelihood of the latent variables thanks to auto-differentiation and gradient-based optimization. I will show:
(i) that a maximum likelihood approach for parameter estimation of opinion dynamics models outperforms the typical simulation-based approach,
(ii) a real application to social media data of an opinion dynamics ABM, and
(iii) a way to bypass the need to explicitly derive the likelihood, based on variational inference.
I will conclude by reflecting on the importance of scientific models in a world of black-box, deep-learning models.

Speaker's Bio:
Gianmarco De Francisci Morales is a Principal Researcher at CENTAI, a private research institute that focuses on Artificial Intelligence and Complex Systems, where he leads the Social Algorithmics Team (SALT). Previously, he worked as a Senior Researcher at ISI Foundation in Turin, Scientist at Qatar Computing Research Institute in Doha, Visiting Scientist at Aalto University in Helsinki, Research Scientist at Yahoo! Labs in Barcelona, and Research Associate at ISTI-CNR in Pisa. He received his Ph.D. in Computer Science and Engineering from the IMT Institute for Advanced Studies of Lucca in 2012. His research focuses on computational social science and data mining, with an emphasis on polarization and echo chambers on social media. He is a Senior Member of the Association for Computing Machinery (ACM), and a member of the European Laboratory for Learning and Intelligent Systems (ELLIS). He has been a member of the open source community of the Apache Software Foundation, where has worked on the Hadoop ecosystem, and has been a committer for the Apache Pig project. He was one of the lead developers of Apache SAMOA, an open-source platform for mining big data streams. He commonly serves on the PC of several major conferences in the area of data mining, including WSDM, WWW, KDD, and ICWSM. He co-organized the workshop series on Social News on the Web (SNOW), co-located with the WWW conference. He has published more than 100 scientific articles and won best paper awards at WSDM, CHI, WebSci, and SocInfo.