Saved in:
Bibliographic Details
Main Authors: Braithwaite, Luke, Borgi, Alessio, Onorato, Gabriele, Tarantelli, Kristjan, Restuccia, Francesco, Silvestri, Fabrizio, Liò, Pietro
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.08036
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911705634701312
author Braithwaite, Luke
Borgi, Alessio
Onorato, Gabriele
Tarantelli, Kristjan
Restuccia, Francesco
Silvestri, Fabrizio
Liò, Pietro
author_facet Braithwaite, Luke
Borgi, Alessio
Onorato, Gabriele
Tarantelli, Kristjan
Restuccia, Francesco
Silvestri, Fabrizio
Liò, Pietro
contents 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 94.97% Macro F1 Score on node classification and up to 99.62% on link prediction) on the Heterogeneous Graph Benchmark (HGB) framework against homogeneous (GCN, GAT, GIN, GraphSAGE), heterogeneous (R-GCN, HAT, HGT) and type-agnostic sheaf baselines, while reducing the number of parameters by up to 10$\times$.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08036
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Heterogeneous Sheaf Neural Networks
Braithwaite, Luke
Borgi, Alessio
Onorato, Gabriele
Tarantelli, Kristjan
Restuccia, Francesco
Silvestri, Fabrizio
Liò, Pietro
Machine Learning
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 94.97% Macro F1 Score on node classification and up to 99.62% on link prediction) on the Heterogeneous Graph Benchmark (HGB) framework against homogeneous (GCN, GAT, GIN, GraphSAGE), heterogeneous (R-GCN, HAT, HGT) and type-agnostic sheaf baselines, while reducing the number of parameters by up to 10$\times$.
title Heterogeneous Sheaf Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2409.08036