@article{Paliwal_Loos_Rabe_Bansal_Szegedy_2020, title={Graph Representations for Higher-Order Logic and Theorem Proving}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/5689}, DOI={10.1609/aaai.v34i03.5689}, abstractNote={<p>This paper presents the first use of graph neural networks (GNNs) for higher-order proof search and demonstrates that GNNs can improve upon state-of-the-art results in this domain. Interactive, higher-order theorem provers allow for the formalization of most mathematical theories and have been shown to pose a significant challenge for deep learning. Higher-order logic is highly expressive and, even though it is well-structured with a clearly defined grammar and semantics, there still remains no well-established method to convert formulas into graph-based representations. In this paper, we consider several graphical representations of higher-order logic and evaluate them against the HOList benchmark for higher-order theorem proving.</p>}, number={03}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Paliwal, Aditya and Loos, Sarah and Rabe, Markus and Bansal, Kshitij and Szegedy, Christian}, year={2020}, month={Apr.}, pages={2967-2974} }