DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning

Aaditya Naik, Jason Liu, Claire Wang, Amish Sethi, Saikat Dutta, Mayur Naik, Eric Wong
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45461-45483, 2025.

Abstract

Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce DOLPHIN, a framework that tackles these challenges by supporting neurosymbolic programs in Python, executing complex symbolic reasoning on the CPU while vectorizing probabilistic computations and gradient propagation on the GPU. Across 13 benchmarks spanning tasks over text, image, and video data, with symbolic reasoning features like recursion and blackbox functions, DOLPHIN converges to state-of-the-art accuracies on the more complex benchmarks while existing frameworks such as Scallop, ISED, and IndeCateR+ fail to converge within the time limit. On simpler benchmarks, DOLPHIN matches their performance, while achieving these results 1.71x to 62x faster than the baselines. Overall, DOLPHIN advances the scalability of neurosymbolic frameworks, achieving state-of-the-art efficiency and convergence on difficult benchmarks where existing frameworks struggle. The code is published at https://github.com/Dolphin-NeSy/Dolphin.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-naik25a, title = {{DOLPHIN}: A Programmable Framework for Scalable Neurosymbolic Learning}, author = {Naik, Aaditya and Liu, Jason and Wang, Claire and Sethi, Amish and Dutta, Saikat and Naik, Mayur and Wong, Eric}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {45461--45483}, 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/naik25a/naik25a.pdf}, url = {https://proceedings.mlr.press/v267/naik25a.html}, abstract = {Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce DOLPHIN, a framework that tackles these challenges by supporting neurosymbolic programs in Python, executing complex symbolic reasoning on the CPU while vectorizing probabilistic computations and gradient propagation on the GPU. Across 13 benchmarks spanning tasks over text, image, and video data, with symbolic reasoning features like recursion and blackbox functions, DOLPHIN converges to state-of-the-art accuracies on the more complex benchmarks while existing frameworks such as Scallop, ISED, and IndeCateR+ fail to converge within the time limit. On simpler benchmarks, DOLPHIN matches their performance, while achieving these results 1.71x to 62x faster than the baselines. Overall, DOLPHIN advances the scalability of neurosymbolic frameworks, achieving state-of-the-art efficiency and convergence on difficult benchmarks where existing frameworks struggle. The code is published at https://github.com/Dolphin-NeSy/Dolphin.} }
Endnote
%0 Conference Paper %T DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning %A Aaditya Naik %A Jason Liu %A Claire Wang %A Amish Sethi %A Saikat Dutta %A Mayur Naik %A Eric Wong %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-naik25a %I PMLR %P 45461--45483 %U https://proceedings.mlr.press/v267/naik25a.html %V 267 %X Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce DOLPHIN, a framework that tackles these challenges by supporting neurosymbolic programs in Python, executing complex symbolic reasoning on the CPU while vectorizing probabilistic computations and gradient propagation on the GPU. Across 13 benchmarks spanning tasks over text, image, and video data, with symbolic reasoning features like recursion and blackbox functions, DOLPHIN converges to state-of-the-art accuracies on the more complex benchmarks while existing frameworks such as Scallop, ISED, and IndeCateR+ fail to converge within the time limit. On simpler benchmarks, DOLPHIN matches their performance, while achieving these results 1.71x to 62x faster than the baselines. Overall, DOLPHIN advances the scalability of neurosymbolic frameworks, achieving state-of-the-art efficiency and convergence on difficult benchmarks where existing frameworks struggle. The code is published at https://github.com/Dolphin-NeSy/Dolphin.
APA
Naik, A., Liu, J., Wang, C., Sethi, A., Dutta, S., Naik, M. & Wong, E.. (2025). DOLPHIN: A Programmable Framework for Scalable Neurosymbolic Learning. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:45461-45483 Available from https://proceedings.mlr.press/v267/naik25a.html.

Related Material