Heterogeneous Sheaf Neural Networks
This addresses the challenge of oversmoothing in GNNs for heterogeneous graphs, offering a more efficient solution for applications like social networks or knowledge graphs, though it appears incremental by building on existing sheaf-based methods.
The authors tackled the problem of processing heterogeneous graphs with Graph Neural Networks (GNNs) by proposing HetSheaf, a framework that uses cellular sheaves to encode data heterogeneity directly into the data structure, achieving competitive results on standard benchmarks while being more parameter-efficient.
Heterogeneous graphs, with nodes and edges of different types, are commonly used to model relational structures in many real-world applications. Standard Graph Neural Networks (GNNs) struggle to process heterogeneous data due to oversmoothing. Instead, current approaches have focused on accounting for the heterogeneity in the model architecture, leading to increasingly complex models. Inspired by recent work, we propose using cellular sheaves to model the heterogeneity in the graph's underlying topology. Instead of modelling the data as a graph, we represent it as cellular sheaves, which allows us to encode the different data types directly in the data structure, eliminating the need to inject them into the architecture. We introduce HetSheaf, a general framework for heterogeneous sheaf neural networks, and a series of heterogeneous sheaf predictors to better encode the data's heterogeneity into the sheaf structure. Finally, we empirically evaluate HetSheaf on several standard heterogeneous graph benchmarks, achieving competitive results whilst being more parameter-efficient.