2024-04-18-anh-trang24a.md

title	software	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
E(3)-Equivariant Mesh Neural Networks	https://github.com/HySonLab/EquiMesh	Triangular meshes are widely used to represent three-dimensional objects. As a result, many recent works have addressed the need for geometric deep learning on 3D meshes. However, we observe that the complexities in many of these architectures do not translate to practical performance, and simple deep models for geometric graphs are competitive in practice. Motivated by this observation, we minimally extend the update equations of E(n)-Equivariant Graph Neural Networks (EGNNs) (Satorras et al., 2021) to incorporate mesh face information and further improve it to account for long-range interactions through a hierarchy. The resulting architecture, Equivariant Mesh Neural Network (EMNN), outperforms other, more complicated equivariant methods on mesh tasks, with a fast run-time and no expensive preprocessing. Our implementation is available at \url{https://github.com/HySonLab/EquiMesh}.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	anh-trang24a	0	E(3)-Equivariant Mesh Neural Networks	748	756	748-756	748	false	Anh Trang, Thuan and Ngo, Nhat Khang and Levy, Daniel T. and Ngoc Vo, Thieu and Ravanbakhsh, Siamak and Son Hy, Truong	given family Thuan Anh Trang given family Nhat Khang Ngo given family Daniel T. Levy given family Thieu Ngoc Vo given family Siamak Ravanbakhsh given family Truong Son Hy	2024-04-18		Proceedings of The 27th International Conference on Artificial Intelligence and Statistics	238	inproceedings	date-parts 2024 4 18	https://proceedings.mlr.press/v238/anh-trang24a/anh-trang24a.pdf