Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models

Harshit Varma, Abhijeet Awasthi, Sunita Sarawagi
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:34908-34923, 2023.

Abstract

We present CTreeOT, a convergent, differentiable algorithm for matching two trees when each tree is conditioned on some input. Such conditional tree matching is useful for light-weight, few-shot adaptation of tree prediction models without parameter fine-tuning. CTreeOT includes an alignment algorithm that extends the popular Sinkhorn algorithm for matching tree nodes while supporting constraints on tree edges. The algorithm involves alternating between matrix rescaling and message passing updates, and can be efficiently expressed as GPU tensor operations. The second part of CTreeOT is fine-grained relevance-based reweighting of nodes that makes the match scores useful for prediction tasks. We demonstrate the usefulness of CTreeOT for cross-schema adaptation of Text-to-SQL, a popular semantic parsing task. We show that compared to state-of-the-art methods, we achieve significant increase in adaptation accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-varma23a, title = {Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models}, author = {Varma, Harshit and Awasthi, Abhijeet and Sarawagi, Sunita}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {34908--34923}, 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/varma23a/varma23a.pdf}, url = {https://proceedings.mlr.press/v202/varma23a.html}, abstract = {We present CTreeOT, a convergent, differentiable algorithm for matching two trees when each tree is conditioned on some input. Such conditional tree matching is useful for light-weight, few-shot adaptation of tree prediction models without parameter fine-tuning. CTreeOT includes an alignment algorithm that extends the popular Sinkhorn algorithm for matching tree nodes while supporting constraints on tree edges. The algorithm involves alternating between matrix rescaling and message passing updates, and can be efficiently expressed as GPU tensor operations. The second part of CTreeOT is fine-grained relevance-based reweighting of nodes that makes the match scores useful for prediction tasks. We demonstrate the usefulness of CTreeOT for cross-schema adaptation of Text-to-SQL, a popular semantic parsing task. We show that compared to state-of-the-art methods, we achieve significant increase in adaptation accuracy.} }
Endnote
%0 Conference Paper %T Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models %A Harshit Varma %A Abhijeet Awasthi %A Sunita Sarawagi %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-varma23a %I PMLR %P 34908--34923 %U https://proceedings.mlr.press/v202/varma23a.html %V 202 %X We present CTreeOT, a convergent, differentiable algorithm for matching two trees when each tree is conditioned on some input. Such conditional tree matching is useful for light-weight, few-shot adaptation of tree prediction models without parameter fine-tuning. CTreeOT includes an alignment algorithm that extends the popular Sinkhorn algorithm for matching tree nodes while supporting constraints on tree edges. The algorithm involves alternating between matrix rescaling and message passing updates, and can be efficiently expressed as GPU tensor operations. The second part of CTreeOT is fine-grained relevance-based reweighting of nodes that makes the match scores useful for prediction tasks. We demonstrate the usefulness of CTreeOT for cross-schema adaptation of Text-to-SQL, a popular semantic parsing task. We show that compared to state-of-the-art methods, we achieve significant increase in adaptation accuracy.
APA
Varma, H., Awasthi, A. & Sarawagi, S.. (2023). Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:34908-34923 Available from https://proceedings.mlr.press/v202/varma23a.html.

Related Material