Publications 2026
Heterogeneous Sheaf Neural Networks
NeurIPS 2026 Workshop on Symmetry and Geometry in Neural Representations (NeurReps, PMLR)
Cellular sheaves for heterogeneous graphs: type-aware restriction maps replace relation-specific modules, with up to 10× fewer parameters.
Abstract
Heterogeneous graphs, whose nodes and edges can belong to different types and feature spaces, arise in many real-world domains, including biology, recommendation, social networks, and computer systems. Existing heterogeneous graph neural networks typically handle this heterogeneity at the architectural level through relation-specific modules, meta-path machinery or type-aware attention, which often leads to increasingly specialised, parameter-heavy designs. In this work, we propose HetSheaf, a framework for learning heterogeneous graphs through cellular sheaves. Instead of encoding heterogeneity solely in the architecture, HetSheaf represents it directly in the underlying data structure by assigning type-aware local feature spaces and learning restriction maps conditioned on node features, node types, and edge types. To support graph-level prediction, we further introduce SheafPool, a universal stalk-space readout that aggregates node representations while being invariant to local changes of basis, thereby making graph classification with sheaf networks well-defined and achieving an F1 Score up to 42 percentage points higher than mean pooling. Across a diverse suite of benchmarks (node classification, link prediction and graph classification), HetSheaf consistently achieves up to 2 percentage points higher performance (up to 94.93% Macro F1 Score on node classification and up to 99.64% on link prediction) on the Heterogeneous Graph Benchmark (HGB) framework against homogeneous (GCN, GAT, GIN, GraphSAGE), heterogeneous (R-GCN, HAN, HGT) and type-agnostic sheaf baselines, while reducing the number of parameters by up to 10×.
Cite
@inproceedings{braithwaite2026hetero,
title = {Heterogeneous Sheaf Neural Networks},
author = {Braithwaite, Luke and Borgi, Alessio and Onorato, Gabriele and Tarantelli, Kristjan and Restuccia, Francesco and Silvestri, Fabrizio and Li{\`o}, Pietro},
booktitle = {NeurIPS 2026 Workshop on Symmetry and Geometry in Neural Representations (Proceedings Track)},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
year = {2026},
eprint = {2409.08036},
archivePrefix = {arXiv}
}