Enhancing Embedding Representations of Biomedical Data using Logic Knowledge

no code implementations • 23 Mar 2023 • Michelangelo Diligenti, Francesco Giannini, Stefano Fioravanti, Caterina Graziani, Moreno Falaschi, Giuseppe Marra

In this paper, we exploit logic rules to enhance the embedding representations of KGEs on the PharmKG dataset.

Knowledge Graph Embeddings Relational Reasoning

Weisfeiler--Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphs

no code implementations • 8 Oct 2022 • Silvia Beddar-Wiesing, Giuseppe Alessio D'Inverno, Caterina Graziani, Veronica Lachi, Alice Moallemy-Oureh, Franco Scarselli, Josephine Maria Thomas

Then, the results on the expressive power of GNNs are extended by proving that GNNs have the same capability as the 1-WL test in distinguishing dynamic and attributed graphs, the 1-WL equivalence equals unfolding equivalence and that GNNs are universal approximators modulo 1-WL/unfolding equivalence.