Relational Learning with Polynomials

Kuelka, Ondrej; Szabóová, Andrea; #x, Filip elezn

doi:10.1109/ictai.2012.163

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The test errors of the LRNNs based purely on the partial charges are higher than the test errors of LRNNs based purely on soft clustering, which was to be expected. Indeed, similar results for relational features based on atom types or partial charges have been previously reported (Kuželka, Szabóová, &Železný, 2012). However, the fact that the combined LRNNs did not outperform the soft clustering LRNNs is more surprising.…”

Section: Learnable Numerical Transformationssupporting

confidence: 81%

Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures

Šourek¹,

Aschenbrenner²,

Železný³

et al. 2018

jair

Self Cite

View full text Add to dashboard Cite

We propose a method to combine the interpretability and expressive power of firstorder logic with the effectiveness of neural network learning. In particular, we introduce a lifted framework in which first-order rules are used to describe the structure of a given problem setting. These rules are then used as a template for constructing a number of neural networks, one for each training and testing example. As the different networks corresponding to different examples share their weights, these weights can be efficiently learned using stochastic gradient descent. Our framework provides a flexible way for implementing and combining a wide variety of modelling constructs. In particular, the use of first-order logic allows for a declarative specification of latent relational structures, which can then be efficiently discovered in a given data set using neural network learning. Experiments on 78 relational learning benchmarks clearly demonstrate the effectiveness of the framework.

show abstract

Section: Learnable Numerical Transformationssupporting

confidence: 81%

Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures

Šourek¹,

Aschenbrenner²,

Železný³

et al. 2018

jair

Self Cite

View full text Add to dashboard Cite

show abstract

“…In terms of Statistical Relational Learning (SRL) tools, we considered RapidMiner 34 and Tree-Liker 35 [12]. Unfortunately we were not able to integrate RapidMiner since its server component imposed requirements that were not fulfilled in our overall workflow 36 .…”

Section: Sml-bench Frameworkmentioning

confidence: 99%

SML-Bench – A benchmarking framework for structured machine learning

Westphal¹,

Bühmann²,

Bin³

et al. 2019

View full text Add to dashboard Cite

The availability of structured data has increased significantly over the past decade and several approaches to learn from structured data have been proposed. These logic-based, inductive learning methods are often conceptually similar, which would allow a comparison among them even if they stem from different research communities. However, so far no efforts were made to define an environment for running learning tasks on a variety of tools, covering multiple knowledge representation languages. With SML-Bench, we propose a benchmarking framework to run inductive learning tools from the ILP and semantic web communities on a selection of learning problems. In this paper, we present the foundations of SML-Bench, discuss the systematic selection of benchmarking datasets and learning problems, and showcase an actual benchmark run on the currently supported tools.

show abstract

Relational Learning with Polynomials

Cited by 2 publications

References 9 publications

Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures

Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures

SML-Bench – A benchmarking framework for structured machine learning

Contact Info

Product

Resources

About