Gaussian Sheaf Neural Networks derive a sheaf Laplacian for Gaussian node features on graphs to preserve their geometric structure during message passing.
A Critical Look at the Evaluation of GNNs under Heterophily: Are We Really Making Progress?
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 9roles
background 1polarities
background 1representative citing papers
NeighborDiv detects graph anomalies via variance of inter-neighbor feature similarities under a new Neighbor-to-Neighbor Diversity Paradigm, achieving SOTA results with zero volatility in zero-shot cross-domain settings.
RS-GNNs predict random sets over classes using belief functions to jointly produce class probabilities and epistemic uncertainty estimates for graph nodes.
HMH builds soft hierarchies with orthonormal Haar bases and heterophily-aware encoders to apply learnable spectral filters while using skip unpooling to avoid oversmoothing and hub bias on heterophilous graphs.
SoftSignum replaces hard sign with soft-sign in optimizers via temperature control and quantile scheduling, extends to SoftMuon, provides a convergence proof for stochastic non-convex settings, and reports better performance than sign-based methods and AdamW on deep learning tasks.
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
HGUL jointly recovers reliable neighborhoods via kNN, adaptively filters noisy edges, and models class relationships with a polynomial kernel affinity matrix to handle heterophily and structural noise in heterogeneous graphs.
Three strategies for adding graph embeddings to event sequence SSL models improve AUC by up to 2.3% on four financial and e-commerce datasets, with graph density determining the best integration approach.
citing papers explorer
-
Gaussian Sheaf Neural Networks
Gaussian Sheaf Neural Networks derive a sheaf Laplacian for Gaussian node features on graphs to preserve their geometric structure during message passing.
-
NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity
NeighborDiv detects graph anomalies via variance of inter-neighbor feature similarities under a new Neighbor-to-Neighbor Diversity Paradigm, achieving SOTA results with zero volatility in zero-shot cross-domain settings.
-
Random-Set Graph Neural Networks
RS-GNNs predict random sets over classes using belief functions to jointly produce class probabilities and epistemic uncertainty estimates for graph nodes.
-
Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
HMH builds soft hierarchies with orthonormal Haar bases and heterophily-aware encoders to apply learnable spectral filters while using skip unpooling to avoid oversmoothing and hub bias on heterophilous graphs.
-
Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
SoftSignum replaces hard sign with soft-sign in optimizers via temperature control and quantile scheduling, extends to SoftMuon, provides a convergence proof for stochastic non-convex settings, and reports better performance than sign-based methods and AdamW on deep learning tasks.
-
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
-
Robust Learning on Heterogeneous Graphs with Heterophily: A Graph Structure Learning Approach
HGUL jointly recovers reliable neighborhoods via kNN, adaptively filters noisy edges, and models class relationships with a polynomial kernel affinity matrix to handle heterophily and structural noise in heterogeneous graphs.
-
Beyond Isolated Clients: Integrating Graph-Based Embeddings into Event Sequence Models
Three strategies for adding graph embeddings to event sequence SSL models improve AUC by up to 2.3% on four financial and e-commerce datasets, with graph density determining the best integration approach.
- GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?