SFU Theory Seminar: Vaishak Belle

We consider the problem of answering queries about formulas of first-order logic based on background knowledge partially represented explicitly as other formulas, and partially represented as examples independently drawn from a fixed probability distribution. PAC semantics, introduced by Valiant, is one rigorous, general proposal for learning to reason in formal languages: although weaker than classical entailment, it allows for a powerful model theoretic framework for answering queries while requiring minimal assumptions about the form of the distribution in question. To date, however, the most significant limitation of that approach, and more generally most machine learning approaches with robustness guarantees, is that the logical language is ultimately essentially propositional, with finitely many atoms. Indeed, the theoretical findings on the learning of relational theories in such generality have been resoundingly negative. This is despite the fact that first-order logic is widely argued to be most appropriate for representing human knowledge. In this work, we present a new theoretical approach to robustly learning to reason in first-order logic, and consider universally quantified clauses over a countably infinite domain. Our results exploit symmetries exhibited by constants in the language, and generalize the notion of implicit learnability to show how queries can be computed against (implicitly) learned first-order background knowledge.

This paper was accepted at NeurIPS-2019, and was selected as a best paper at The Fourth International Workshop on Declarative Learning Based Programming (IJCAI-2019).

Bio:

Dr Vaishak Belle is a Chancellor's Fellow and Faculty at the University of Edinburgh, 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. At the University of Edinburgh, he directs a lab that specializes in the unification of symbolic systems and machine learning.

Vaishak's research is in artificial intelligence, and is motivated by the need to augment learning and perception with high-level structured, commonsensical knowledge, to enable AI systems to learn faster and more accurate models of the world. In particular, he has worked on areas such as knowledge representation, probabilistic inference, statistical relational learning, probabilistic programming, cognitive robotics, and his recent research has touched upon explainability and ethics in AI.

He has co-authored over 50 scientific 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, and the Machine learning journal award at ECML-PKDD. In 2014, he received a silver medal by the Kurt Goedel Society.

More information can be found at: https://vaishakbelle.com/lab