A Formula-Structure-Embedding-Based GNN for Formula Equivalence Determination
Source abstract
Abstract
The complexity of mathematical formulas in scientific documents makes efficient formula similarity computation a critical task in information retrieval. Approaches based on text or structure matching cannot fully capture the inherent semantic and hierarchical properties of formulas. Although large language models (LLM) made significant progress in formula similarity comparison, the linear processing may ignore the structure information of formulas. In contrast, GNN excel at modeling the structure relationships of formulas, but still face challenges in accurately defining nodes and edges in a formula tree, especially in distinguishing between nodes at different levels and modeling edge relationships. In this paper, we propose a formula-structure-embedding based GNN (FSCMGNN), and it is integrated with formula structure embedding, structure standardization and attention mechanism. The model is designed for semantic equivalence comparison. Experimental results show that the model outperforms existing models in formula equivalence determination in calculus.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Mathematics, Computing, and Information Processing · Algorithms and Data Compression · Natural Language Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information Science and Technology, Beijing Forestry University, Beijing 100083, China
Funding
Beijing Advanced Innovation Center
References (24)
Show source-provided references
1. Garcez, A.d., Gori, M., Lamb, L.C., Serafini, L., Spranger, M., and Tran, S.N. (2019). Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning. arXiv.
2. Besold, T.R., Bader, S., Bowman, H., Domingos, P., Hitzler, P., Kühnberger, K.U., Lamb, L.C., Lima, P.M.V., de Penning, L., and Pinkas, G. (2021). Neural-symbolic learning and reasoning: A survey and interpretation 1. Neuro-Symbolic Artificial Intelligence: The State of the Art, IOS Press.10.3233/FAIA210348 ↗
3. Yokoi, K., and Aizawa, A. (2009). An approach to similarity search for mathematical expressions using MathML. Towards a Digital Mathematics Library. Grand Bend, Ontario, Canada, July 8–9th, 2009, Masaryk University Press.
4. Kamali, S., and Tompa, F.W. (2013, January 8–12). Structural similarity search for mathematics retrieval. Proceedings of the International Conference on Intelligent Computer Mathematics, Bath, UK.10.1007/978-3-642-39320-4_16 ↗
5. Zanibbi, R., and Yuan, B. (2011, January 23–27). Keyword and image-based retrieval of mathematical expressions. Proceedings of the Document Recognition and Retrieval XVIII, San Francisco, CA, USA.10.1117/12.873312 ↗
6. Miner, R., and Munavalli, R. (2007, January 27–30). An approach to mathematical search through query formulation and data normalization. Proceedings of the International Conference on Mathematical Knowledge Management, Hagenberg, Austria.
7. Recognition and retrieval of mathematical expressions10.1007/s10032-011-0174-4 ↗
8. Zaremba, W., Kurach, K., and Fergus, R. (2014, January 8–13). Learning to discover efficient mathematical identities. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
9. Irving, G., Szegedy, C., Alemi, A.A., Eén, N., Chollet, F., and Urban, J. (2016, January 5–10). Deepmath-deep sequence models for premise selection. Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain.
10. Allamanis, M., Chanthirasegaran, P., Kohli, P., and Sutton, C. (2017, January 6–11). Learning continuous semantic representations of symbolic expressions. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, Australia.
11. Davila, K., and Zanibbi, R. (2017, January 7–11). Layout and semantics: Combining representations for mathematical formula search. Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Tokyo, Japan.10.1145/3077136.3080748 ↗
12. Gao, L., Jiang, Z., Yin, Y., Yuan, K., Yan, Z., and Tang, Z. (2017). Preliminary Exploration of Formula Embedding for Mathematical Information Retrieval: Can mathematical formulae be embedded like a natural language?. arXiv.
13. Arabshahi, F., Singh, S., and Anandkumar, A. (2018, January 14). Towards solving differential equations through neural programming. Proceedings of the ICML Workshop on Neural Abstract Machines and Program Induction (NAMPI), Stockholm, Sweden.
14. Lample, G., and Charton, F. (2019). Deep learning for symbolic mathematics. arXiv.
15. Zhong, W., Rohatgi, S., Wu, J., Giles, C.L., and Zanibbi, R. (2020, January 14–17). Accelerating substructure similarity search for formula retrieval. Proceedings of the Advances in Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal. Proceedings, Part I 42.10.1007/978-3-030-45439-5_47 ↗
16. Peng, S., Yuan, K., Gao, L., and Tang, Z. (2021). Mathbert: A pre-trained model for mathematical formula understanding. arXiv.
17. Autoformalize mathematical statements by symbolic equivalence and semantic consistency
18. Raz, T., Shalyt, M., Leibtag, E., Kalisch, R., Hadad, Y., and Kaminer, I. (2025). From Euler to AI: Unifying Formulas for Mathematical Constants. arXiv.
19. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
20. Bai, Y., Ding, H., Bian, S., Chen, T., Sun, Y., and Wang, W. (2019, January 11–15). Simgnn: A neural network approach to fast graph similarity computation. Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, Melbourne, Australia.10.1145/3289600.3290967 ↗
21. Bittinger, M.L., Ellenbogen, D., and Surgent, S.A. (2016). Calculus and Its Applications, Pearson.
22. Stewart, J., Clegg, D., and Watson, S. (2012). Single Variable Calculus: Early Transcendentals, Brooks/Cole Cengage Learning. [2nd ed.].
23. Zill, D.G., and Wright, W.S. (2009). Calculus: Early Transcendentals, Jones & Bartlett Publishers.
24. Jimidovich, B.P. (2002). Mathematical Analysis Exercise Set, MIR Publishers.