Block-Wise Construction of Acyclic Relational Features with Monotone Irreducibility and Relevancy Properties

Abstract

We describe an algorithm for constructing a set of acyclic conjunctive relational features by combining smaller conjunctive blocks. Unlike traditional level-wise approaches which preserve the monotonicity of frequency, our block-wise approach preserves a form of monotonicity of the irreducibility and relevancy feature properties, which are important in propositionalization employed in the context of classification learning. With pruning based on these properties, our block-wise approach efficiently scales to features including tens of first-order literals, far beyond the reach of state-of-the art propositionalization or inductive logic programming systems.

Cite

Text

Kuzelka and Zelezný. "Block-Wise Construction of Acyclic Relational Features with Monotone Irreducibility and Relevancy Properties." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553448

Markdown

[Kuzelka and Zelezný. "Block-Wise Construction of Acyclic Relational Features with Monotone Irreducibility and Relevancy Properties." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/kuzelka2009icml-block/) doi:10.1145/1553374.1553448

BibTeX

@inproceedings{kuzelka2009icml-block,
  title     = {{Block-Wise Construction of Acyclic Relational Features with Monotone Irreducibility and Relevancy Properties}},
  author    = {Kuzelka, Ondrej and Zelezný, Filip},
  booktitle = {International Conference on Machine Learning},
  year      = {2009},
  pages     = {569-576},
  doi       = {10.1145/1553374.1553448},
  url       = {https://mlanthology.org/icml/2009/kuzelka2009icml-block/}
}