Kasim Candan
Arizona State University Campus Immersion, AZ·Computer Science
Most machine learning finds patterns that predict outcomes, but not the causes behind them. Causal learning aims to identify cause-and-effect relationships from data, which matters when decisions must hold up in new situations, such as responding to a disease outbreak.
- Fields
Computer Science
Public Health & Epidemiology
Mathematics & Statistics
- Topics
causal learning
causal discovery
causal inference
- Grants
- 2 known grants, through Jun 2027
What they work on
- Develop PanAX methods that separate setting-specific from transferable parts of epidemic data and models, so knowledge from data-rich outbreaks can be reused for new outbreaks with limited data.
- Use multi-layer causal relationships and causality-based de-biasing to make epidemic spread models built from observational data more robust, and support counterfactual what-if analyses of interventions.
- Deliver PanAX as open-source software for spatio-temporal epidemic prediction and intervention planning by researchers, public health officials and policymakers.
- Build CausalBench, a benchmarking platform with an evaluation ontology and standard mechanisms for contributing datasets, algorithms and models for causal learning.
- Establish integrated evaluation standards in CausalBench to assess causal learning algorithms on observational data, promoting reproducibility, fairness and bias awareness.
More about the research
The two projects here share that thread. One builds a shared platform for fairly testing causal learning methods. The other uses causal reasoning to reuse existing epidemic models and data so they work in new outbreaks where data are scarce.
Why it matters
Faster, reusable epidemic models could help public health officials and policymakers plan interventions and inform the public when a new outbreak hits and data are thin. A shared benchmarking platform could make causal machine learning methods more trustworthy and reproducible for uses such as public health and sustainability.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Elements: CausalBench: A Cyberinfrastructure for Causal-Learning Benchmarking for Efficacy, Reproducibility, and Scientific Collaboration
NSF · Jul 2023 – Jun 2027
Collaborative Research: ACED: Track 1: PanAX: Accelerating Epidemic Science through Causally-Informed Domain Generalization and Knowledge Transfer
NSF · Jun 2025 – Nov 2026
Closest labs
Faramarz Fekri
Georgia Institute of Technology, GA·Computer Science
Identify when cause-and-effect relationships can be calculated from observed data even when unmeasured confounders (hidden variables that affect both cause and outcome) are present, and develop robust ways to estimate those effects.
Elias Bareinboim
Columbia University, NY·Computer Science
Develop causality-integrated methods for online and offline policy learning, interventional planning, imitation learning and knowledge transfer so autonomous agents decide robustly with less data, building on structural causal models.
Jundong Li
University of Virginia, VA·Computer Science·Early-career
Design graph neural networks tailored to peptides, including amino acid-aware message passing and graph transformers, and combine them with pretrained protein language models to merge structural and evolutionary information.
The school
Arizona State University Campus Immersion: 36 labs on PI Pages, $1.0B a year on research, 625 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.