Search Results for author: Sebastijan Dumančić

Found 13 papers, 3 papers with code

Learning logic programs by discovering higher-order abstractions

no code implementations16 Aug 2023 Céline Hocquette, Sebastijan Dumančić, Andrew Cropper

We introduce the higher-order refactoring problem, where the goal is to compress a logic program by discovering higher-order abstractions, such as map, filter, and fold.

Inductive logic programming Program Synthesis +1

A Divide-Align-Conquer Strategy for Program Synthesis

no code implementations8 Jan 2023 Jonas Witt, Stef Rasing, Sebastijan Dumančić, Tias Guns, Claus-Christian Carbon

We show that compositional segmentation can be applied in the programming by examples setting to divide the search for large programs across multiple smaller program synthesis problems.

Inductive logic programming Program Synthesis +1

From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey

no code implementations25 Aug 2021 Giuseppe Marra, Sebastijan Dumančić, Robin Manhaeve, Luc De Raedt

This survey explores the integration of learning and reasoning in two different fields of artificial intelligence: neurosymbolic and statistical relational artificial intelligence.

Logical Reasoning

Learning large logic programs by going beyond entailment

no code implementations21 Apr 2020 Andrew Cropper, Sebastijan Dumančić

We argue that a key limitation of existing systems is that they use entailment to guide the hypothesis search.

Inductive logic programming Program Synthesis

From Statistical Relational to Neuro-Symbolic Artificial Intelligence

no code implementations18 Mar 2020 Luc De Raedt, Sebastijan Dumančić, Robin Manhaeve, Giuseppe Marra

Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning.

Logical Reasoning Position

Turning 30: New Ideas in Inductive Logic Programming

no code implementations25 Feb 2020 Andrew Cropper, Sebastijan Dumančić, Stephen H. Muggleton

Common criticisms of state-of-the-art machine learning include poor generalisation, a lack of interpretability, and a need for large amounts of training data.

BIG-bench Machine Learning Inductive logic programming

Neural Probabilistic Logic Programming in DeepProbLog

no code implementations NeurIPS 2018 Robin Manhaeve, Sebastijan Dumančić, Angelika Kimmig, Thomas Demeester, Luc De Raedt

We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates.

Program induction

Learning Sequence Encoders for Temporal Knowledge Graph Completion

3 code implementations EMNLP 2018 Alberto García-Durán, Sebastijan Dumančić, Mathias Niepert

In line with previous work on static knowledge graphs, we propose to address this problem by learning latent entity and relation type representations.

Link Prediction Relation +1

DeepProbLog: Neural Probabilistic Logic Programming

4 code implementations NeurIPS 2018 Robin Manhaeve, Sebastijan Dumančić, Angelika Kimmig, Thomas Demeester, Luc De Raedt

We introduce DeepProbLog, a probabilistic logic programming language that incorporates deep learning by means of neural predicates.

Program induction

COBRAS: Fast, Iterative, Active Clustering with Pairwise Constraints

no code implementations29 Mar 2018 Toon Van Craenendonck, Sebastijan Dumančić, Elia Van Wolputte, Hendrik Blockeel

This background knowledge is often obtained by allowing the clustering system to pose pairwise queries to the user: should these two elements be in the same cluster or not?

Clustering

Demystifying Relational Latent Representations

no code implementations16 May 2017 Sebastijan Dumančić, Hendrik Blockeel

This work addresses these issues and shows that (1) latent features created by clustering are interpretable and capture interesting properties of data; (2) they identify local regions of instances that match well with the label, which partially explains their benefit; and (3) although the number of latent features generated by this approach is large, often many of them are highly redundant and can be removed without hurting performance much.

Clustering Relational Reasoning

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