Taxonomic Networks: A Representation for Neuro-Symbolic Pairing

Zekun Wang, Ethan L. Haarer, Nicki Barari, Christopher J. MacLellan
Proceedings of the International Conference on Neuro-symbolic Systems, PMLR 288:459-471, 2025.

Abstract

We introduce the concept of a neuro-symbolic pair—neural and symbolic approaches that are linked through a common knowledge representation. Next, we present taxonomic networks, a type of discrimination network in which nodes represent hierarchically organized taxonomic concepts. Using this representation, we construct a novel neuro-symbolic pair and evaluate its performance. We show that our symbolic method learns taxonomic nets more efficiently with less data and compute, while the neural method finds higher-accuracy taxonomic nets when provided with greater resources. As a neuro-symbolic pair, these approaches can be used interchangeably based on situational needs, with seamless translation between them when necessary. This work lays the foundation for future systems that more fundamentally integrate neural and symbolic computation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v288-wang25b, title = {Taxonomic Networks: A Representation for Neuro-Symbolic Pairing}, author = {Wang, Zekun and Haarer, Ethan L. and Barari, Nicki and MacLellan, Christopher J.}, booktitle = {Proceedings of the International Conference on Neuro-symbolic Systems}, pages = {459--471}, year = {2025}, editor = {Pappas, George and Ravikumar, Pradeep and Seshia, Sanjit A.}, volume = {288}, series = {Proceedings of Machine Learning Research}, month = {28--30 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v288/main/assets/wang25b/wang25b.pdf}, url = {https://proceedings.mlr.press/v288/wang25b.html}, abstract = {We introduce the concept of a neuro-symbolic pair—neural and symbolic approaches that are linked through a common knowledge representation. Next, we present taxonomic networks, a type of discrimination network in which nodes represent hierarchically organized taxonomic concepts. Using this representation, we construct a novel neuro-symbolic pair and evaluate its performance. We show that our symbolic method learns taxonomic nets more efficiently with less data and compute, while the neural method finds higher-accuracy taxonomic nets when provided with greater resources. As a neuro-symbolic pair, these approaches can be used interchangeably based on situational needs, with seamless translation between them when necessary. This work lays the foundation for future systems that more fundamentally integrate neural and symbolic computation.} }
Endnote
%0 Conference Paper %T Taxonomic Networks: A Representation for Neuro-Symbolic Pairing %A Zekun Wang %A Ethan L. Haarer %A Nicki Barari %A Christopher J. MacLellan %B Proceedings of the International Conference on Neuro-symbolic Systems %C Proceedings of Machine Learning Research %D 2025 %E George Pappas %E Pradeep Ravikumar %E Sanjit A. Seshia %F pmlr-v288-wang25b %I PMLR %P 459--471 %U https://proceedings.mlr.press/v288/wang25b.html %V 288 %X We introduce the concept of a neuro-symbolic pair—neural and symbolic approaches that are linked through a common knowledge representation. Next, we present taxonomic networks, a type of discrimination network in which nodes represent hierarchically organized taxonomic concepts. Using this representation, we construct a novel neuro-symbolic pair and evaluate its performance. We show that our symbolic method learns taxonomic nets more efficiently with less data and compute, while the neural method finds higher-accuracy taxonomic nets when provided with greater resources. As a neuro-symbolic pair, these approaches can be used interchangeably based on situational needs, with seamless translation between them when necessary. This work lays the foundation for future systems that more fundamentally integrate neural and symbolic computation.
APA
Wang, Z., Haarer, E.L., Barari, N. & MacLellan, C.J.. (2025). Taxonomic Networks: A Representation for Neuro-Symbolic Pairing. Proceedings of the International Conference on Neuro-symbolic Systems, in Proceedings of Machine Learning Research 288:459-471 Available from https://proceedings.mlr.press/v288/wang25b.html.

Related Material