Have Graph — Will Lift? The Case for Higher-Order Benchmarks

Bastian Rieck
Proceedings of the Geometry, Topology, and Machine Learning Workshop, PMLR 325:109-119, 2026.

Abstract

After a somewhat rocky start, geometry and topology have established a foothold in machine learning. Message passing, either on graphs or higher-order complexes, is one of the main drivers of \emph{geometric deep learning}, and paradigms that were once considered to be firmly in the realm of the abstract—like sheaves—have been “tamed” to serve as novel inductive biases for model architectures in \emph{topological deep learning}. The veritable diversity of models, however, is in stark contrast to the scarcity of suitable benchmark datasets. As a result, researchers often resort to \emph{lifting} existing graph datasets to include higher-order information. In this opinion paper, I want to encourage the community to also source new datasets, which may be used to prop up the foundations of our research field.

Cite this Paper

BibTeX
@InProceedings{pmlr-v325-rieck26a, title = {Have Graph — Will Lift? The Case for Higher-Order Benchmarks}, author = {Rieck, Bastian}, booktitle = {Proceedings of the Geometry, Topology, and Machine Learning Workshop}, pages = {109--119}, year = {2026}, editor = {Bleher, Michael and Jensen, Freya and Maier, Levin and Taha, Diaaeldin and Wienhard, Anna}, volume = {325}, series = {Proceedings of Machine Learning Research}, month = {10--14 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v325/main/assets/rieck26a/rieck26a.pdf}, url = {https://proceedings.mlr.press/v325/rieck26a.html}, abstract = {After a somewhat rocky start, geometry and topology have established a foothold in machine learning. Message passing, either on graphs or higher-order complexes, is one of the main drivers of \emph{geometric deep learning}, and paradigms that were once considered to be firmly in the realm of the abstract—like sheaves—have been “tamed” to serve as novel inductive biases for model architectures in \emph{topological deep learning}. The veritable diversity of models, however, is in stark contrast to the scarcity of suitable benchmark datasets. As a result, researchers often resort to \emph{lifting} existing graph datasets to include higher-order information. In this opinion paper, I want to encourage the community to also source new datasets, which may be used to prop up the foundations of our research field.} }
Endnote
%0 Conference Paper %T Have Graph — Will Lift? The Case for Higher-Order Benchmarks %A Bastian Rieck %B Proceedings of the Geometry, Topology, and Machine Learning Workshop %C Proceedings of Machine Learning Research %D 2026 %E Michael Bleher %E Freya Jensen %E Levin Maier %E Diaaeldin Taha %E Anna Wienhard %F pmlr-v325-rieck26a %I PMLR %P 109--119 %U https://proceedings.mlr.press/v325/rieck26a.html %V 325 %X After a somewhat rocky start, geometry and topology have established a foothold in machine learning. Message passing, either on graphs or higher-order complexes, is one of the main drivers of \emph{geometric deep learning}, and paradigms that were once considered to be firmly in the realm of the abstract—like sheaves—have been “tamed” to serve as novel inductive biases for model architectures in \emph{topological deep learning}. The veritable diversity of models, however, is in stark contrast to the scarcity of suitable benchmark datasets. As a result, researchers often resort to \emph{lifting} existing graph datasets to include higher-order information. In this opinion paper, I want to encourage the community to also source new datasets, which may be used to prop up the foundations of our research field.
APA
Rieck, B.. (2026). Have Graph — Will Lift? The Case for Higher-Order Benchmarks. Proceedings of the Geometry, Topology, and Machine Learning Workshop, in Proceedings of Machine Learning Research 325:109-119 Available from https://proceedings.mlr.press/v325/rieck26a.html.

Related Material