A Soft Version of Predicate Invention Based on Structured Sparsity
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Special Track on Machine Learning. Pages 3918-3923.
Abstract
In predicate invention (PI), new predicates are introduced into a logical theory, usually by rewriting a group of closely-related rules to use a common invented predicate as a subroutine. PI is difficult, since a poorly-chosen invented predicate may lead to error cascades. Here we suggest a soft version of predicate invention: instead of explicitly creating new predicates, we implicitly group closely-related rules by using structured sparsity to regularize their parameters together. We show that soft PI, unlike hard PI, consistently improves over previous strong baselines for structure-learning on two large-scale tasks.
@inproceedings{ijcai2015p550,
title = {A Soft Version of Predicate Invention Based on Structured Sparsity},
author = {Wang, William Yang and Mazaitis, Kathryn and Cohen, William W.},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {3918--3923},
year = {2015},
month = {7},
note = {Special Track on Machine Learning},
url = {https://ijcai.org/proceedings/2015/550},
}
TY - CPAPER TI - A Soft Version of Predicate Invention Based on Structured Sparsity AU - Wang, William Yang AU - Mazaitis, Kathryn AU - Cohen, William W. T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 3918 EP - 3923 UR - https://ijcai.org/proceedings/2015/550 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
