Ralph Abboud
University of Oxford
13 Papers
22 Citations
Ralph Abboud is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 6, co-authored 13 publications. Previous affiliations of Ralph Abboud include Lebanese American University.
Chat about Author
Papers
•Posted Content
The Surprising Power of Graph Neural Networks with Random Node Initialization
TL;DR: This paper proves that GNNs with RNI are universal, a first such result for GNN's not relying on computationally demanding higher-order properties, and empirically analyzes the effect of RNI on GNN’s, finding that the empirical findings support the superior performance of GNNS with R NI over standard Gnns.
168
•Posted Content
BoxE: A Box Embedding Model for Knowledge Base Completion
TL;DR: BoxE is a spatio-translational embedding model that achieves state-of-the-art performance, both on benchmark knowledge graphs and on more general KBs, and empirically shows the power of integrating logical rules.
120
The Surprising Power of Graph Neural Networks with Random Node Initialization
Ralph Abboud,Ismail Ilkan Ceylan,Martin Grohe,Thomas Lukasiewicz +3 more
- 04 May 2021
TL;DR: In this article, the expressive power of GNNs with RNI was analyzed, and it was shown that GNN with random node initialization (RNI) is more expressive than GNN without RNI.
•Posted Content
Temporal Knowledge Graph Completion using Box Embeddings.
TL;DR: In this article, the authors propose a box embedding model for temporal knowledge graph completion (TKGC), where each fact is additionally associated with a time stamp and the idea is to learn latent representations for entities, relations, and timestamps and then use the learned representations to predict missing facts at various time steps.
57
Integration of nonparametric fuzzy classification with an evolutionary-developmental framework to perform music sentiment-based analysis and composition
Ralph Abboud,Joe Tekli +1 more
- 01 Jul 2020
TL;DR: A new algorithmic framework for autonomous music sentiment-based expression and composition, titled MUSEC, that perceives an extensible set of six primary human emotions expressed by a MIDI musical file and then composes new polyphonic, thematic, and diversified musical pieces that express these emotions.
49