Feature-Aware (Hyper)graph Generation via Next-Scale Prediction

Dorian Gailhard, Enzo Tartaglione, Lirida Naviner, Jhony H. Giraldo
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:32640-32674, 2026.

Abstract

Graph generative models perform well on small structured data but struggle to scale to large, complex structures. Hierarchical approaches improve scalability but often ignore node and edge features, which are critical in real-world applications, particularly for hypergraphs that model higher-order relationships. In this paper, we propose FAHNES (feature-aware (hyper)graph generation via next-scale prediction), a hierarchical framework that jointly generates topology and features for graphs and hypergraphs. FAHNES builds multi-scale representations through node coarsening and localized expansion, guided by a novel hierarchical scale encoding that controls granularity and ensures cross-scale consistency. Experiments on synthetic, 3D mesh, and graph point cloud datasets demonstrate competitive or state-of-the-art performance while uniquely scaling to featured large-scale graphs and hypergraphs. Our code is open source.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-gailhard26a, title = {Feature-Aware ({H}yper)graph Generation via Next-Scale Prediction}, author = {Gailhard, Dorian and Tartaglione, Enzo and Naviner, Lirida and Giraldo, Jhony H.}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {32640--32674}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/gailhard26a/gailhard26a.pdf}, url = {https://proceedings.mlr.press/v306/gailhard26a.html}, abstract = {Graph generative models perform well on small structured data but struggle to scale to large, complex structures. Hierarchical approaches improve scalability but often ignore node and edge features, which are critical in real-world applications, particularly for hypergraphs that model higher-order relationships. In this paper, we propose FAHNES (feature-aware (hyper)graph generation via next-scale prediction), a hierarchical framework that jointly generates topology and features for graphs and hypergraphs. FAHNES builds multi-scale representations through node coarsening and localized expansion, guided by a novel hierarchical scale encoding that controls granularity and ensures cross-scale consistency. Experiments on synthetic, 3D mesh, and graph point cloud datasets demonstrate competitive or state-of-the-art performance while uniquely scaling to featured large-scale graphs and hypergraphs. Our code is open source.} }
Endnote
%0 Conference Paper %T Feature-Aware (Hyper)graph Generation via Next-Scale Prediction %A Dorian Gailhard %A Enzo Tartaglione %A Lirida Naviner %A Jhony H. Giraldo %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-gailhard26a %I PMLR %P 32640--32674 %U https://proceedings.mlr.press/v306/gailhard26a.html %V 306 %X Graph generative models perform well on small structured data but struggle to scale to large, complex structures. Hierarchical approaches improve scalability but often ignore node and edge features, which are critical in real-world applications, particularly for hypergraphs that model higher-order relationships. In this paper, we propose FAHNES (feature-aware (hyper)graph generation via next-scale prediction), a hierarchical framework that jointly generates topology and features for graphs and hypergraphs. FAHNES builds multi-scale representations through node coarsening and localized expansion, guided by a novel hierarchical scale encoding that controls granularity and ensures cross-scale consistency. Experiments on synthetic, 3D mesh, and graph point cloud datasets demonstrate competitive or state-of-the-art performance while uniquely scaling to featured large-scale graphs and hypergraphs. Our code is open source.
APA
Gailhard, D., Tartaglione, E., Naviner, L. & Giraldo, J.H.. (2026). Feature-Aware (Hyper)graph Generation via Next-Scale Prediction. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:32640-32674 Available from https://proceedings.mlr.press/v306/gailhard26a.html.

Related Material