Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion
Neural Sheaf Diffusion (NSD) generalizes diffusion-based Graph Neural Networks by replacing scalar graph Laplacians with sheaf Laplacians whose learned restriction maps define a task-adapted geometry. While the diffusion limit of NSD is known to be the space of global sections, the representation-theoretic structure of this harmonic space remains largely implicit. We develop a quiver-theoretic interpretation of NSD by identifying cellular sheaves on graphs with representations of the associated incidence quiver. Under this correspondence, learned sheaf geometries become points in a finite-dimensional representation space. We show that direct-sum decompositions of the underlying incidence-quiver representation induce decompositions of the harmonic space reached in the diffusion limit. This gives an algebraic interpretation of oversmoothing as representation degeneration: learned sheaves may collapse toward low-complexity summands whose global sections fail to preserve discriminative information. Building on this viewpoint, we connect sheaf diffusion to stability and moment-map principles from Geometric Invariant Theory. We introduce moment-map-inspired regularizers that bias restriction maps toward balanced representation geometries, and identify a structural obstruction in equal-stalk architectures: when $d_v = d_e$, admissibility for learnable stability parameters forces the trivial all-object summand onto a stability wall. Non-uniform stalk dimensions remove this obstruction, making adaptive stability meaningful. Experiments on heterophilic benchmarks are consistent with this mechanism: breaking stalk symmetry can reduce variance or improve validation behavior, and adaptive stability becomes more effective in selected rectangular settings. Overall, our framework reframes oversmoothing as a degeneration phenomenon in the representation geometry underlying learned sheaf diffusion.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
On the Necessity of Learnable Sheaf Laplacians
Sheaf Neural Networks (SNNs) were introduced as an extension of Graph Convolutional Networks to address oversmoothing on heterophilous graphs by attaching a sheaf to the input graph and replacing the adjacency-based oper…
Demystifying Oversmoothing in Sheaf Neural Networks: An Index-Theoretic Criterion
To combat oversmoothing in Graph Convolutional Networks, Sheaf Neural Networks (SNNs) were proposed as a generalization by equipping the graph with a sheaf structure and replacing the graph Laplacian with a sheaf Laplaci…
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Cellular sheaves equip graphs with a "geometrical" structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph with a trivial underlying sheaf. This cho…
Node ClassificationNode Classification on Non-Homophilic (Heterophilic) GraphsCooperative Sheaf Neural Networks
Sheaf diffusion has recently emerged as a promising design pattern for graph representation learning due to its inherent ability to handle heterophilic data and avoid oversmoothing. Meanwhile, cooperative message passing…
Graph Representation LearningDynamic Sheaf Diffusion Networks with Adaptive Local Structure for Heterogeneous Spatio-Temporal Graph Learning
Spatio-temporal processes often exhibit highly heterogeneous and non-intuitive responses to localized disruptions, limiting the effectiveness of conventional message passing approaches in modeling local heterogeneity. We…
Graph Neural NetworkGraph Learning