• Classified by Research Topic • Sorted by Date • Classified by Publication Type •
Embedding Symbolic Knowledge into Deep Networks.
Yaqi Xie, Ziwei Xu, Kankanhalli,Mohan S., Meel,Kuldeep S. and Harold Soh.
In Proceedings of Advances in Neural Information Processing Systems(NeurIPS), December 2019.
In this work, we aim to leverage prior symbolic knowledge to improve the performance of deep models. We propose a graph embedding network that projects propositional formulae (and assignments) onto a manifold via an augmented Graph Convolutional Network (GCN). To generate semantically-faithful embeddings, we develop techniques to recognize node heterogeneity, and semantic regularization that incorporate structural constraints into the embedding. Experiments show that our approach improves the performance of models trained to perform entailment checking and visual relation prediction. Interestingly, we observe a connection between the tractability of the propositional theory representation and the ease of embedding. Future exploration of this connection may elucidate the relationship between knowledge compilation and vector representation learning.
@inproceedings{XXKMS19,
title={Embedding Symbolic Knowledge into Deep Networks},
author={Xie, Yaqi and Xu, Ziwei and Kankanhalli,Mohan S. and Meel,Kuldeep S. and Soh, Harold},
booktitle=NIPS,
year={2019},
month=dec,
bib2html_dl_pdf={https://arxiv.org/abs/1909.01161},
code={https://github.com/ZiweiXU/LENSR},
bib2html_pubtype={Refereed Conference},
bib2html_rescat={Formal Methods 4 ML},
abstract={ In this work, we aim to leverage prior symbolic knowledge to improve the performance of deep models.
We propose a graph embedding network that projects propositional formulae (and assignments) onto a manifold via
an augmented Graph Convolutional Network (GCN). To generate semantically-faithful embeddings, we develop techniques
to recognize node heterogeneity, and semantic regularization that incorporate structural constraints into the
embedding. Experiments show that our approach improves the performance of models trained to perform entailment
checking and visual relation prediction. Interestingly, we observe a connection between the tractability of the propositional theory representation and the ease of embedding. Future exploration of this connection may elucidate the relationship between knowledge compilation and vector representation learning. },
}
Generated by bib2html.pl (written by Patrick Riley with layout from Sanjit A. Seshia ) on Sun Apr 14, 2024 11:15:51