Search Results for author: İsmail İlkan Ceylan

Found 8 papers, 1 papers with code

Equivariant Quantum Graph Circuits

no code implementations10 Dec 2021 Péter Mernyei, Konstantinos Meichanetzidis, İsmail İlkan Ceylan

We investigate quantum circuits for graph representation learning, and propose equivariant quantum graph circuits (EQGCs), as a class of parameterized quantum circuits with strong relational inductive bias for learning over graph-structured data.

Graph Representation Learning

Temporal Knowledge Graph Completion using Box Embeddings

no code implementations18 Sep 2021 Johannes Messner, Ralph Abboud, İsmail İlkan Ceylan

Temporal knowledge graph completion (TKGC) is an extension of this task to temporal knowledge graphs, where each fact is additionally associated with a time stamp.

Knowledge Graph Completion Knowledge Graph Embedding +1

The Surprising Power of Graph Neural Networks with Random Node Initialization

no code implementations2 Oct 2020 Ralph Abboud, İsmail İlkan Ceylan, Martin Grohe, Thomas Lukasiewicz

In this work, we analyze the expressive power of GNNs with RNI, and prove that these models are universal, a first such result for GNNs not relying on computationally demanding higher-order properties.

Representation Learning

BoxE: A Box Embedding Model for Knowledge Base Completion

1 code implementation NeurIPS 2020 Ralph Abboud, İsmail İlkan Ceylan, Thomas Lukasiewicz, Tommaso Salvatori

Knowledge base completion (KBC) aims to automatically infer missing facts by exploiting information already present in a knowledge base (KB).

Knowledge Base Completion Knowledge Graphs +1

On the Approximability of Weighted Model Integration on DNF Structures

no code implementations17 Feb 2020 Ralph Abboud, İsmail İlkan Ceylan, Radoslav Dimitrov

Weighted model counting (WMC) consists of computing the weighted sum of all satisfying assignments of a propositional formula.

Dynamic Bayesian Ontology Languages

no code implementations26 Jun 2015 İsmail İlkan Ceylan, Rafael Peñaloza

Many formalisms combining ontology languages with uncertainty, usually in the form of probabilities, have been studied over the years.

Adding Context to Knowledge and Action Bases

no code implementations26 Dec 2014 Diego Calvanese, İsmail İlkan Ceylan, Marco Montali, Ario Santoso

Knowledge and Action Bases (KABs) have been recently proposed as a formal framework to capture the dynamics of systems which manipulate Description Logic (DL) Knowledge Bases (KBs) through action execution.

Cannot find the paper you are looking for? You can Submit a new open access paper.