Beam Tree Recursive Cells

Jishnu Ray Chowdhury, Cornelia Caragea
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28768-28791, 2023.

Abstract

We propose Beam Tree Recursive Cell (BT-Cell) - a backpropagation-friendly framework to extend Recursive Neural Networks (RvNNs) with beam search for latent structure induction. We further extend this framework by proposing a relaxation of the hard top-$k$ operators in beam search for better propagation of gradient signals. We evaluate our proposed models in different out-of-distribution splits in both synthetic and realistic data. Our experiments show that BT-Cell achieves near-perfect performance on several challenging structure-sensitive synthetic tasks like ListOps and logical inference while maintaining comparable performance in realistic data against other RvNN-based models. Additionally, we identify a previously unknown failure case for neural models in generalization to unseen number of arguments in ListOps. The code is available at: https://github.com/JRC1995/BeamTreeRecursiveCells.

Cite this Paper


BibTeX
@InProceedings{pmlr-v202-ray-chowdhury23a, title = {Beam Tree Recursive Cells}, author = {Ray Chowdhury, Jishnu and Caragea, Cornelia}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {28768--28791}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/ray-chowdhury23a/ray-chowdhury23a.pdf}, url = {https://proceedings.mlr.press/v202/ray-chowdhury23a.html}, abstract = {We propose Beam Tree Recursive Cell (BT-Cell) - a backpropagation-friendly framework to extend Recursive Neural Networks (RvNNs) with beam search for latent structure induction. We further extend this framework by proposing a relaxation of the hard top-$k$ operators in beam search for better propagation of gradient signals. We evaluate our proposed models in different out-of-distribution splits in both synthetic and realistic data. Our experiments show that BT-Cell achieves near-perfect performance on several challenging structure-sensitive synthetic tasks like ListOps and logical inference while maintaining comparable performance in realistic data against other RvNN-based models. Additionally, we identify a previously unknown failure case for neural models in generalization to unseen number of arguments in ListOps. The code is available at: https://github.com/JRC1995/BeamTreeRecursiveCells.} }
Endnote
%0 Conference Paper %T Beam Tree Recursive Cells %A Jishnu Ray Chowdhury %A Cornelia Caragea %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-ray-chowdhury23a %I PMLR %P 28768--28791 %U https://proceedings.mlr.press/v202/ray-chowdhury23a.html %V 202 %X We propose Beam Tree Recursive Cell (BT-Cell) - a backpropagation-friendly framework to extend Recursive Neural Networks (RvNNs) with beam search for latent structure induction. We further extend this framework by proposing a relaxation of the hard top-$k$ operators in beam search for better propagation of gradient signals. We evaluate our proposed models in different out-of-distribution splits in both synthetic and realistic data. Our experiments show that BT-Cell achieves near-perfect performance on several challenging structure-sensitive synthetic tasks like ListOps and logical inference while maintaining comparable performance in realistic data against other RvNN-based models. Additionally, we identify a previously unknown failure case for neural models in generalization to unseen number of arguments in ListOps. The code is available at: https://github.com/JRC1995/BeamTreeRecursiveCells.
APA
Ray Chowdhury, J. & Caragea, C.. (2023). Beam Tree Recursive Cells. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:28768-28791 Available from https://proceedings.mlr.press/v202/ray-chowdhury23a.html.

Related Material