EVENT

Event News

AI Seminar by Emir Demirović & Meghyn Bienvenu

On October 22nd, we will hold the following open AI seminar.
The lecturers are Emir Demirović and Meghyn Bienvenu.
Anyone is welcome to attend.

Talk 1:

Optimal Decision Trees (with Constraints) via Dynamic Programming and Search

Abstract:

Decision trees are an effective and concise way of conveying information, easily understood by virtually everyone. Given the recent interest in explainable AI and related fields, decision trees stand out as a popular choice. From the algorithmic side, the unique structure of decision trees is interesting, since it may be exploited to obtain more efficient algorithms than structure-oblivious approaches.

In this talk, I will give an overview of the research we have been doing on constructing optimal regression/decision trees, i.e., trees that best represent tabular data whilst respecting different types of constraints such as fairness and size. We show that our techniques based on dynamic programming and search are able to obtain orders of magnitude improvements in runtime over state-of-the-art approaches. Our framework is also able to support a range of different objectives and constraints, e.g., fairness, survival analysis, nonlinear metrics such as F1-score. The success of our approach is attributed to a series of specialised techniques that exploit properties unique to decision/regression trees.

The talk summarises about half a dozen of our papers (AAAI'21/24, JMLR'22, NeurIPS'22, ICML'23/24) and is meant to be accessible to all backgrounds, with plenty of time for discussion.

Speaker Bio:

Emir Demirović, Delft University of Technology, The Netherlands

Emir Demirović is an assistant professor at TU Delft (Netherlands). He leads the Constraint Solving ("ConSol") research group, which advances combinatorial optimisation algorithms for a wide range of (real-world) problems, and co-directs the explainable AI in transportation lab ("XAIT") as part of the Delft AI Labs. Prior to his appointment at TU Delft, Emir worked at the University of Melbourne, Vienna University of Technology, National Institute of Informatics (internship), and at a production planning and scheduling company.

The focus point of Emir's current work is solving techniques based on constraint programming, optimising decision trees, and explainable methods for combinatorial optimisation. He is also interested in industrial applications, robust/resilient optimisation, and the integration of optimisation and machine learning.

Talk 2:

KR Meets Data Quality

Abstract:

Real-world data notoriously suffers from various forms of imperfections (missing facts, erroneous facts, duplicates, etc.), which can limit its utility and lead to flawed analyses and unreliable decision making. This makes data quality an issue of paramount importance across application domains, and one which I'll argue can both benefit from research on Knowledge Representation and Reasoning (KR) and serve as a testbed for KR techniques. Indeed, while recent years have seen increasing interest in machine learning-based approaches, declarative approaches to improving data quality remain highly relevant, due to their better interpretability. In this talk, I will illustrate the synergy between data quality and KR by giving an overview of some of my recent work on querying inconsistent data using repair-based semantics and on rule-based approaches to entity resolution, highlighting the insights gained and directions for future research.

Speaker Bio:

Meghyn Bienvenu, LaBRI - CNRS & University of Bordeaux, France

Meghyn Bienvenu is a senior researcher (directrice de recherche) at the CNRS (French National Center for Scientific Research), based at the LaBRI research lab in Bordeaux, France. Her research interests span a range of topics in knowledge representation and reasoning and database theory, but she is best known for her contributions to ontology-mediated query answering and to the study of logic-based methods for handling inconsistent data. Bienvenu's research has been recognized by an invited Early Career Spotlight talk at IJCAI'16, the 2016 CNRS Bronze Medal in computer science, and together with her coauthors, a 2023 ACM PODS Alberto Mendelzon Test-of-Time Award. She has taken on numerous responsibilities within the AI, KR, and database theory communities, notably serving as PC co-chair for KR 2021 and associate editor of Artificial Intelligence Journal.

Time/Date:

15:00 - 17:00 / Tuesday October 22, 2024

Programme:

15:00 Emir Demirović (TU Delft): Optimal Decision Trees (with Constraints) via Dynamic Programming and Search
16:00 Meghyn Bienvenu (LaBRI CNRS): KR Meets Data Quality