Banyan: Improved Representation Learning with Explicit Structure

Mattia Opper, Siddharth N
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:47287-47301, 2025.

Abstract

We present Banyan, a model that efficiently learns semantic representations by leveraging explicit hierarchical structure. While transformers excel at scale, they struggle in low-resource settings. Conversely recent structured models have shown promise as efficient learners, but lack performance. Banyan bridges this gap with two key innovations: an entangled hierarchical tree structure and diagonalized message passing, enabling it to outperform larger transformer models with just 14 non-embedding parameters. It excels in low-resource settings, offering a viable alternative for under-represented languages and highlighting its potential for efficient, interpretable NLP in resource-constrained environments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-opper25a, title = {Banyan: Improved Representation Learning with Explicit Structure}, author = {Opper, Mattia and N, Siddharth}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {47287--47301}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/opper25a/opper25a.pdf}, url = {https://proceedings.mlr.press/v267/opper25a.html}, abstract = {We present Banyan, a model that efficiently learns semantic representations by leveraging explicit hierarchical structure. While transformers excel at scale, they struggle in low-resource settings. Conversely recent structured models have shown promise as efficient learners, but lack performance. Banyan bridges this gap with two key innovations: an entangled hierarchical tree structure and diagonalized message passing, enabling it to outperform larger transformer models with just 14 non-embedding parameters. It excels in low-resource settings, offering a viable alternative for under-represented languages and highlighting its potential for efficient, interpretable NLP in resource-constrained environments.} }
Endnote
%0 Conference Paper %T Banyan: Improved Representation Learning with Explicit Structure %A Mattia Opper %A Siddharth N %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-opper25a %I PMLR %P 47287--47301 %U https://proceedings.mlr.press/v267/opper25a.html %V 267 %X We present Banyan, a model that efficiently learns semantic representations by leveraging explicit hierarchical structure. While transformers excel at scale, they struggle in low-resource settings. Conversely recent structured models have shown promise as efficient learners, but lack performance. Banyan bridges this gap with two key innovations: an entangled hierarchical tree structure and diagonalized message passing, enabling it to outperform larger transformer models with just 14 non-embedding parameters. It excels in low-resource settings, offering a viable alternative for under-represented languages and highlighting its potential for efficient, interpretable NLP in resource-constrained environments.
APA
Opper, M. & N, S.. (2025). Banyan: Improved Representation Learning with Explicit Structure. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:47287-47301 Available from https://proceedings.mlr.press/v267/opper25a.html.

Related Material