no code implementations • 8 Feb 2024 • Jeffrey Sardina, Luca Costabello, Christophe Guéret
Knowledge Graphs (KGs) have become increasingly common for representing large-scale linked data.
no code implementations • 2 Oct 2023 • Vasileios Baltatzis, Luca Costabello
To ensure faithfulness, each surrogate is trained by distilling knowledge from the original KGE model.
1 code implementation • 16 Dec 2022 • Matthew Wicker, Juyeon Heo, Luca Costabello, Adrian Weller
Post-hoc explanation methods are used with the intent of providing insights about neural networks and are sometimes said to help engender trust in their outputs.
no code implementations • 5 Dec 2022 • Adrianna Janik, Luca Costabello
We study the problem of explaining link predictions in the Knowledge Graph Embedding (KGE) models.
no code implementations • 17 Nov 2022 • Adrianna Janik, Maria Torrente, Luca Costabello, Virginia Calvo, Brian Walsh, Carlos Camps, Sameh K. Mohamed, Ana L. Ortega, Vít Nováček, Bartomeu Massutí, Pasquale Minervini, M. Rosario Garcia Campelo, Edel del Barco, Joaquim Bosch-Barrera, Ernestina Menasalvas, Mohan Timilsina, Mariano Provencio
Conclusions: Our results show that machine learning models trained on tabular and graph data can enable objective, personalised and reproducible prediction of relapse and therefore, disease outcome in patients with early-stage NSCLC.
1 code implementation • ACL 2021 • Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O'Sullivan
We study the problem of generating data poisoning attacks against Knowledge Graph Embedding (KGE) models for the task of link prediction in knowledge graphs.
1 code implementation • EMNLP 2021 • Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O'Sullivan
These attacks craft adversarial additions or deletions at training time to cause model failure at test time.
1 code implementation • 18 May 2021 • Sumit Pai, Luca Costabello
Numeric values associated to edges of a knowledge graph have been used to represent uncertainty, edge importance, and even out-of-band knowledge in a growing number of scenarios, ranging from genetic data to social networks.
1 code implementation • 16 Mar 2021 • Lisa Schut, Oscar Key, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal
Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions.
no code implementations • 25 Jun 2020 • Severin Gsponer, Luca Costabello, Chan Le Van, Sumit Pai, Christophe Gueret, Georgiana Ifrim, Freddy Lecue
Sequence classification is the supervised learning task of building models that predict class labels of unseen sequences of symbols.
no code implementations • 30 Apr 2020 • Federico Bianchi, Gaetano Rossiello, Luca Costabello, Matteo Palmonari, Pasquale Minervini
Knowledge graph embeddings are now a widely adopted approach to knowledge representation in which entities and relationships are embedded in vector spaces.
2 code implementations • ICLR 2020 • Pedro Tabacof, Luca Costabello
We show popular embedding models are indeed uncalibrated.
Calibration for Link Prediction Knowledge Graph Embedding +2
no code implementations • 13 Nov 2018 • Rory Mc Grath, Luca Costabello, Chan Le Van, Paul Sweeney, Farbod Kamiab, Zhao Shen, Freddy Lecue
Our contribution is two-fold: i) we propose positive counterfactuals, i. e. we adapt counterfactual explanations to also explain accepted loan applications, and ii) we propose two weighting strategies to generate more interpretable counterfactuals.