About
PhD (2012), MSc (2008), Laurea Specialistica (2008)
Reader, Chancellor’s Fellow, Royal Society University Research Fellow, and Alan Turing Faculty Fellow at the University of Edinburgh.
Very brief bio: Dr Vaishak Belle (he/him) is Reader at the University of Edinburgh, an Alan Turing Fellow, and a Royal Society University Research Fellow. He has made a career out of doing research on the science and technology of AI. He has published close to 100 peer-reviewed articles, won best paper awards, and consulted with banks on explainability. As PI and CoI, he has secured a grant income of close to 8 million pounds.
Brief bio: Dr Vaishak Belle (he/him) is a Chancellor’s Fellow and Reader at the School of Informatics, University of Edinburgh. He is an Alan Turing Institute Faculty Fellow, a Royal Society University Research Fellow, and a member of the RSE (Royal Society of Edinburgh) Young Academy of Scotland. He was previously at KU Leuven (Belgium), University of Toronto (Canada), Aachen University of Technology (Germany) and University of Trento (Italy).
At the University of Edinburgh, he directs a research lab on artificial intelligence, specialising in the unification of logic and machine learning, with a recent emphasis on explainability and ethics. He has given research seminars at academic institutions such as MIT and Oxford, tutorials at AI conferences, and talks at venues such as Ars Electronica and the Samsung AI Forum.
He has co-authored close to 100 peer-reviewed articles on AI, at venues such as IJCAI, UAI, AAAI, MLJ, AIJ, JAIR, AAMAS, and along with his co-authors, he has won the Microsoft best paper award at UAI, the Machine learning journal best student paper award at ECML-PKDD, and the Machine learning journal best student paper award at ILP. In 2014, he received a silver medal by the Kurt Goedel Society.
He has served on the senior program committee/area chair of major AI conferences, co-chaired the ML track at KR, among others, and as PI and CoI secured a grant income of close to 8 million pounds. Recently, he has consulted with major banks on explainable AI and its impact in financial institutions.
A few representative publications are below, organized thematically.
Robust Machine Learning
One Down, 699 to go: or, synthesizing compositional desugarings.
OOPSLA, 2021.
S. Bartha, J. Cheney, and V Belle.
Learning Implicitly with Noisy Data in Linear Arithmetic.
IJCAI, 2021.
A. Rader, I. Mocanu, V. Belle, and B. Juba.
Implicitly Learning to Reason in First-Order Logic.
NeurIPS, 2019.
V. Belle and B. Juba.
Automated Planning
Analyzing Generalized Planning Under Nondeterminism.
Artificial Intelligence, 2022.
V. Belle.
Efficient Multi-agent Epistemic Planning: Teaching Planners About Nested Belief.
Artificial Intelligence, 2021.
C. Muise, V. Belle, P. Felli, S. McIlraith, T. Miller, A. Pearce, A and L. Sonenberg.
A Correctness Result for Synthesizing Plans With Loops in Stochastic Domains.
International Journal of Approximate Reasoning, 2020.
L. Treszkai and V. Belle.
Statistical relational AI
Planning in hybrid relational MDPs.
Machine Learning:1-28, 2017.
D. Nitti, V. Belle, T. De Laet and L. De Raedt.
Weighted Model Counting with Conditional Weights for Bayesian Networks.
UAI, 2021.
P. Dilkas and V. Belle.
Probabilistic Inference in Hybrid Domains by Weighted Model Integration.
IJCAI, 2015.
V. Belle, A. Passerini and G. Van den Broeck.
First-Order Logic and Probability
Regression and Progression in Stochastic Domains.
Artificial Intelligence, 2020.
V. Belle and H. Levesque.
Reasoning about discrete and continuous noisy sensors and effectors in dynamical systems.
Artificial Intelligence, 262:189 - 221, 2018.
V. Belle and H. Levesque.
Reasoning about Probabilities in Unbounded First-Order Dynamical Domains.
IJCAI, 2017.
V. Belle and G. Lakemeyer.
Multi-agent Modal Logics
Only Knowing Meets Common Knowledge.
IJCAI, 2015.
V. Belle and G. Lakemeyer.
Semantical Considerations on Multiagent Only Knowing.
Artificial Intelligence, 223:1-26, 2015.
V. Belle and G. Lakemeyer.
Multiagent Only Knowing in Dynamic Systems.
Journal of Artificial Intelligence Research, 49:363-402, 2014.
V. Belle and G. Lakemeyer.
Neuro-Symbolic AI
MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks.
AAAI, 2022.
N. Hoernle, R. Karampatsis, V. Belle and K. Gal.
Logic meets Learning: From Aristotle to Neural Networks.
Neuro-Symbolic Artificial Intelligence: The State of the Art, 2021.
V. Belle.
Breaking CAPTCHA with Capsule Networks.
Neural Networks, 2022.
I. Mocanu, Z. Yang, and V. Belle.
Explainability
Principles and Practice of Explainable Machine Learning.
Frontiers in Big Data, 2021.
I. Papantonis and V. Belle.
Logic meets Probability: Towards Explainable AI Systems for Uncertain Worlds.
IJCAI, 2017.
V. Belle.
Semiring Programming: A Semantic Framework for Generalized Sum Product Problems.
International Journal of Approximate Reasoning, 2020.
V. Belle and L. De Raedt.
Ethical AI
Tractable Probabilistic Models for Ethical AI.
ICCS, 2022.
V. Belle.
Fairness in Machine Learning with Tractable Models.
Knowledge-Based Systems, 2021.
M. Varley and V. Belle.
Tractable Probabilistic Models for Moral Responsibility and Blame.
Data Mining and Knowledge Discovery, 2021.
L. Hammond and V. Belle.