Amir H. Karimi

Assistant Professor

Electrical & Computer Engineering, University of Waterloo

Cheriton School of Computer Science (cross-appointment)

Faculty Affiliate, Vector Institute

amirh.karimi [at] uwaterloo.ca

Bio

Dr. Amir-Hossein Karimi is an Assistant Professor in the Department of Electrical and Computer Engineering with cross-appointment at the Cheriton School of Computer Science of the University of Waterloo at the University of Waterloo, and a Vector Institute Faculty Affiliate. He leads the Collaborative Human-AI Reasoning Machines (CHARM) Lab, dedicated to pioneering advances in AI to facilitate trustworthy human-AI collaborations.

Dr. Karimi's scholarly contributions have been showcased almost exclusively at top-tier AI and ML venues including NeurIPS, ICML, AAAI, AISTATS, ACM FAccT, and ACM AIES. He has authored influential publications such as a comprehensive survey paper in the prestigious ACM Computing Surveys, holds a patent, and is a contributing author of a book chapter. Dr. Karimi’s work on algorithmic recourse has notably elevated its prominence in responsible AI research, with its presence growing from almost none to hundreds on Google Scholar in just five years; algorithmic recourse is now a mandatory criterion in key sectors, including Canada’s Treasury Board Directive on Automated Decision-Making. Besides highlighted presentations at the aforementioned venues and serving on their respective conference program committees, numerous academic and industry research labs have invited Dr. Karimi to present talks, lectures, and tutorials. His invited talks span institutions like University College London, ETH Zurich, Cyber Valley Health, Harvard University, MIT, Montreal Institute for Learning Algorithms (MILA), Institute of Mathematical Statistics, NEC Europe Labs, DeepMind, and Google Brain. Notably, Dr. Karimi gave a tutorial on Causal Explainable AI at KDD 2023 and one on Algorithmic Recourse at the Toronto ML Summit 2024. Committed to knowledge mobilization and reproducibility, his open-source code has earned over 100 GitHub stars.

Dr. Karimi is a firm believer in the strength of diverse perspectives and is dedicated to building inclusive spaces in academia and beyond. As a professor, he strives to inspire the next generation of AI researchers and engineers, helping them understand and responsibly apply the power of AI. Further emphasizing his commitment to inclusive learning, he co-founded "Prince of AI," an initiative that provides free education on basic and advanced AI topics to a community of over 30,000 individuals. This initiative aims to reduce barriers to education and offer opportunities to those who traditionally lack access. With a wealth of content equivalent to an introductory ML course, their platform facilitates active learning through technical posts, engaging video reels, and interactive webinars.

Prior to joining UWaterloo, Dr. Karimi accumulated significant industry experience at leading tech companies such as BlackBerry, Meta (Facebook), Google Brain, and DeepMind, and provided consulting services for various startups and incubators including for NEXT AI. His contributions have earned him multiple accolades, such as the UofToronto Spirit of Engineering Science Award (2015), the UWaterloo Alumni Gold Medal Award (2018), the NSERC Canada Graduate Scholarship - Doctorate (2018), the Google PhD Fellowship (2021), the ETH Zurich Medal (2024), the NSERC Discovery Grants (2024), and the Igor Ivkovic Teaching Excellence Award (2024).

✨CHARM Lab✨

The mandate of the Collaborative Human-AI Reasoning Machines (CHARM) Lab is to enhance the integration of AI systems into human decision-making, ensuring they are not only powerful but also safe, reliable, and aligned with human values. As AI becomes more embedded in everyday life, e.g., 🏥 healthcare, 🎓 education, 💼 finance, and 🚗 transportation, our dependency on these systems grows, and so does the risk of potential consequential errors. Our mission is to develop AI systems that can detect 🕵️‍♂️ potential issues, correct 🛠️ mistakes, and ultimately perfect 🤝 human-AI partnership where humans and machines work together seamlessly to achieve better outcomes. 🌍✨

The CHARM Lab focuses on causal inference, explainable AI, and neuro-symbolic approaches in order to build systems that allow users to understand, challenge, and improve AI decisions. We occasionally also borrow insights from, and collaborate with leading experts in, such fields as social sciences, cognitive science, human-computer interaction, multi-agent reinforcement learning, game theory, and behavioral economics.

Prospective Students

The lab is always on the lookout for exceptional and highly motivated students/visitors across all levels (bachelor's, master's, doctoral, postdoctoral). If you are passionate about building the future of trustworthy human-AI symbiosis, and have a strong background in machine learning, computer science, or related fields please fill out this form.

Current Members
Amir-Hossein Karimi

Amir-Hossein Karimi

Principal Investigator (PI)

Mina Kebriaee

Mina Kebriaee

PhD Student
(w/ Prof. Tahvildari)

Zahra Khotanlou

Zahra Khotanlou

PhD Student

Maryam Ghorbansabagh

Maryam Ghorbansabagh

Master's Student
(w/ Prof. Grossmann)

Zachary Wu

Zachary Wu

Research Assistant
(w/ Prof. Tahvildari)

Lab Alumni
Abubakar Bello

Abubakar Bello

Research Assistant
(next: Microsoft Inc.)

Mohammadreza Alavi

Mohammadreza Alavi

Research Assistant

Past Mentees
Ahmad Ehyaei

Ahmad Ehyaei

Mentee (w/ Prof. Farnadi)
(next: Intl. Max Planck Research Schools)

Miriam Rateike

Miriam Rateike

Mentee (w/ Prof. Valera)
(next: Google PhD Fellow 2023)

Maryam Yalsavar

Maryam Yalsavar

Mentee (w/ Prof. Ghodsi)
(next: Huawei)

Ricardo Dominguez-Olmedo

Ricardo Dominguez-Olmedo

Mentee (w/ Prof. Schölkopf)
(next: Intl. Max Planck Research Schools)

Kiarash Mohammadi

Kiarash Mohammadi

Mentee (w/ Prof. Valera)
(next: MILA AI Institute)

Alexandra Walter

Alexandra Walter

Mentee (w/ Prof. Valera)
(next: Helmholtz Data Sci. Sch. of Health)

Publications

Most recent publications are available on Google Scholar.
indicates equal contribution.

On the Relationship Between Explanation and Prediction: A Causal View
Karimi, Muandet, Kornblith, Schölkopf, Kim
ICML 2023 (acceptance rate: 27.9%)
A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations
Karimi, Barthe, Schölkopf, Valera
ACM CSUR 2022 (impact factor: 23.8)
Algorithmic Recourse under Imperfect Causal Knowledge: a Probabilistic Approach
Karimi, von Kügelgen, Schölkopf, Valera
NeurIPS 2020 (acceptance rate: 20.1%)
Algorithmic Recourse: from Counterfactual Explanations to Interventions
Karimi, Schölkopf, Valera
ACM FAccT 2021 (acceptance rate: 25.0%)
Model-Agnostic Counterfactual Explanations for Consequential Decisions
Karimi, Barthe, Valera
AISTATS 2019 (acceptance rate: 32.4%)
Prospector Heads: Generalized Feature Attribution for Large Models & Data
Machiraju, Derry, Desai, Guha, Karimi, Zou, Altman, Ré, Mallick
ICML 2024 (acceptance rate: 27.5%)
On the Relationship Between Explanation and Prediction: A Causal View
Karimi, Muandet, Kornblith, Schölkopf, Kim
ICML 2023 (acceptance rate: 27.9%)
Scaling Guarantees for Nearest Counterfactual Explanations
Mohammadi, Karimi, Barthe, Valera
ACM AIES 2021 (acceptance rate: 38.0%)
Model-Agnostic Counterfactual Explanations for Consequential Decisions
Karimi, Barthe, Valera
AISTATS 2019 (acceptance rate: 32.4%)
Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces
Ehyaei, Mohammadi, Karimi, Samadi, Farnadi
AAAI 2023 (acceptance rate: 23.7%)
On the Relationship Between Explanation and Prediction: A Causal View
Karimi, Muandet, Kornblith, Schölkopf, Kim
ICML 2023 (acceptance rate: 27.9%)
On Data Manifolds Entailed by Structural Causal Models
Dominguez-Olmedo, Karimi, Arvanitidis, Schölkopf
ICML 2023 (acceptance rate: 27.9%)
A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations
Karimi, Barthe, Schölkopf, Valera
ACM CSUR 2022 (impact factor: 23.8)
Robustness Implies Fairness in Causal Algorithmic Recourse
Ehyaei, Karimi, Schölkopf, Maghsudi
ACM FAccT 2023 (acceptance rate: 24.6%)
On the Robustness of Causal Algorithmic Recourse
Dominguez-Olmedo, Karimi, Schölkopf
ICML 2022 (acceptance rate: 21.9%)
On the Fairness of Causal Algorithmic Recourse
von Kügelgen, Karimi, Bhatt, Valera, Weller, Schölkopf
AAAI 2022 (acceptance rate: 15.0%)
Algorithmic Recourse under Imperfect Causal Knowledge: a Probabilistic Approach
Karimi, von Kügelgen, Schölkopf, Valera
NeurIPS 2020 (acceptance rate: 20.1%)
Algorithmic Recourse: from Counterfactual Explanations to Interventions
Karimi, Schölkopf, Valera
ACM FAccT 2021 (acceptance rate: 25.0%)
A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations
Karimi, Barthe, Schölkopf, Valera
ACM CSUR 2022 (impact factor: 23.8)
Robustness Implies Fairness in Causal Algorithmic Recourse
Ehyaei, Karimi, Schölkopf, Maghsudi
ACM FAccT 2023 (acceptance rate: 24.6%)
On the Robustness of Causal Algorithmic Recourse
Dominguez-Olmedo, Karimi, Schölkopf
ICML 2022 (acceptance rate: 21.9%)
On the Fairness of Causal Algorithmic Recourse
von Kügelgen, Karimi, Bhatt, Valera, Weller, Schölkopf
AAAI 2022 (acceptance rate: 15.0%)
Algorithmic Recourse under Imperfect Causal Knowledge: a Probabilistic Approach
Karimi, von Kügelgen, Schölkopf, Valera
NeurIPS 2020 (acceptance rate: 20.1%)
Algorithmic Recourse: from Counterfactual Explanations to Interventions
Karimi, Schölkopf, Valera
ACM FAccT 2021 (acceptance rate: 25.0%)
SRP: Efficient class-aware embedding learning for large-scale data via supervised random projections
Karimi, Wong, Ghodsi
arxiv
Ensembles of Random Projections for Nonlinear Dimensionality Reduction
Karimi, Shafiee, Ghodsi, Wong
CVIS 2017 (acceptance rate: 40.0%)
Synthesizing Deep Neural Network Architectures using Biological Synaptic Strength Distributions
Karimi, Shafiee, Ghodsi, Wong
CCN 2017 (acceptance rate: 40.0%)
FEELS: a Full-Spectrum Enhanced Emotion Learning System for Assisting People with Autism Spectrum Disorder
Karimi, Boroomand, Pfisterer, Wong
CVIS 2018 (acceptance rate: 40.0%)
Discovery Radiomics via a Mixture Sequencers for Multi-Parameter MRI
Karimi, Chung, Shafiee, Khalvati, Haider, Ghodsi, Wong
ICIAR 2017 (acceptance rate: 40.0%)
Automated detection and cell density assessment of keratocytes in the human corneal stroma from ultrahigh resolution optical coherence tomograms
Karimi, Wong, Bizheva
Biomedical Optics Express (impact factor: 2.9)
Distance Correlation Autoencoder
Wang, Karimi, Ghodsi
IJCNN 2018 (acceptance rate: 22.7%)
Key-Value Memory Networks for Directly Reading Documents
Miller, Fisch, Dodge, Karimi, Bordes, Weston
EMNLP 2016 (acceptance rate: 24.3%)
Spatio-temporal Saliency Detection using Abstracted Fully-Connected Graphical Models
Karimi, Shafiee, Scharfenberger, BenDaya, Haider, Talukdar, Clausi, Wong
ICIP 2016 (acceptance rate: 40.0%)

Teaching

Dr. Karimi enjoys teaching diverse audiences, covering broad topics in AI for general audiences, courses on ML for undergrad/grad students, and specialized courses for practitioners. In his first teaching term at the University of Waterloo, he was honored with the 2024 Igor Ivkovic Teaching Excellence Award. Alongside the freely available content linked below, please reach out to book Dr. Karimi for teaching engagements at your organization or event.
General Content
Prince of AI
Prince of AI
Medium Blog
Success Studio
BBC Podcast
AI for Autism
University Courses
Intro to Machine Learning
Intro to Machine Learning
CausEthical ML
CausEthical Machine Learning
Dimension Reduction & PCA
Dimension Reduction & PCA
Specialized Tutorials
Toronto ML Summit Tutorial
Algorithmic Recourse
KDD Tutorial
Causal Explainable AI

Vitæ

Having immigrated five times across three continents for studies and work, from Iran to Canada, and then onward to the USA, Germany, Switzerland, and the UK, Dr. Amir-Hossein Karimi has accumulated over 15 years of technical experience in both research and industry roles. Now an Assistant Professor at the University of Waterloo and a Vector Institute Faculty Affiliate, he has held prominent research positions at Google DeepMind, Google Brain, alongside software engineering roles at BlackBerry and Meta (Facebook). His academic journey includes a Ph.D. at the Max Planck Institute & ETH Zürich, with a focus on causal inference and explainable AI. Full CV in PDF.

Press, Funding, & Consultations

Dr. Karimi is grateful for the generous funding support from the University of Waterloo, NSERC, Google, and Waterloo.AI, enabling his team to push the boundaries of human-AI research.

In addition to his academic contributions, Dr. Karimi has consulted internationally for several startups, leveraging his expertise for discovery, product-market fit, and scaling of operations, in addition to fundraising and grant writing . He is available to discuss how his research and experience can deliver value to your organization and stakeholders.

For press inquiries, feel free to reach out.