[Lunch Lecture Series] Talk by Claudia d’Amato on March 27, 2026 at 13:00 (Paris Time)

Dear all,

It's time to announce our next talk in the Lunch Lecture Series [1]. It will be given by Claudia d’Amato (Associate Professor @ University of Bari, Italy) on March 27, 2026 at 13:00. 

If you are interested in attending please register on [2]. Visit [1] for staying updated with the upcoming talks. 

NOTE: "This will be our last email announcement to avoid spamming the mailing lists. If you want to subscribe to the whole series please register on [3]."

Title: Explanations and Semantics-Aware Machine Learning for Knowledge Graph Refinement

Abstract: Knowledge Graphs (KGs) are receiving increasing attention both from academia and industry and are exploited in a multitude of application domains and research fields. Despite their large usage, it is well known that KGs suffer from incompleteness and noise, being the result of a complex building process, hence significant research efforts are currently devoted to improve the coverage and quality of existing KGs, particularly focussing on the link prediction task. For this purpose, mostly numeric based Machine Learning (ML) solutions, that proved to scale on very large KGs, are adopted. They are usually grounded on the graph structure and they generally consist of a series of numbers without any obvious human interpretation, thus possibly affecting the interpretability, the explainability and sometimes the trustworthiness of the results. Nevertheless, KGs may rely on expressive representation languages, e.g., RDFS and OWL (ultimately grounded on Description Logics), that are also endowed with deductive reasoning capabilities, but both expressiveness and reasoning are most of the time disregarded by the majority of the numeric methods that have been developed so far. A similar issue applies when trying to explain link predictions on KGs. In this talk, the role and the value added that the semantics may have for link prediction solutions will be argued. Additionally, the importance of tacking into account semantics when computing explanations for link prediction solutions will be addressed. Hence, research directions on empowering link prediction and explanation solutions by injecting background knowledge will be presented. Afterwards, the urgent problem of evaluating explanations for link prediction results will be analyzed and a unified protocol for evaluating link prediction explanations will be presented.

[1] https://sites.google.com/view/mehwish-alam/lecture-series-goblin , https://goblin-cost.eu/announcements/lunch-lecture-series/ 
[2] https://forms.gle/TKUmUP7neCzSfQzx7 
[3] https://forms.gle/FsSGCH6RmGS1zp64A 


— 
Best Regards
Mehwish Alam

Associate Professor
Telecom Paris, Institut Polytechnique de Paris
Department of Informatics and Networks (INFRES)
19 Pl. Marguerite Perey, 91120 Palaiseau, France

Web: https://sites.google.com/view/mehwish-alam/home