FilterMoE uses joint node-channel routing of Chebyshev filter experts through a 3D gating tensor in pre-propagation GNNs and outperforms baselines on nine of eleven benchmarks while ranking first on all three large-scale ones with a 1.53-point average gain.
hub
A Critical Look at the Evaluation of GNNs under Heterophily: Are We Really Making Progress?
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
years
2026 14roles
background 1polarities
background 1representative citing papers
Gaussian Sheaf Neural Networks derive a sheaf Laplacian for Gaussian node features on graphs to preserve their geometric structure during message passing.
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.
GraphIP-Bench is a new unified benchmark showing GNN model extraction succeeds at moderate query budgets while most defenses fail to prevent it or retain verification signals on surrogates.
SIES learns generalizable local coupling operators via signed source-target attention for controllable synchronization in graph dynamical systems and applies the principle to heterophilous graph representation learning.
ProMoS introduces the first unsupervised generalist graph anomaly detection method via prototype-based distillation from a self-supervised GNN teacher to a mixture-of-students model for zero-shot cross-graph transfer.
ReFi-GAD uses a semantics-aware relational fingerprint and transformer-based model with SNR refinement to align heterogeneous features for generalist graph anomaly detection across unseen graphs.
GNSN adds convection governed by a dynamic velocity field to graph message passing, adaptively balancing it with diffusion to handle varying homophily levels and reduce oversmoothing while outperforming baselines on 12 datasets.
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
-
Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs
FilterMoE uses joint node-channel routing of Chebyshev filter experts through a 3D gating tensor in pre-propagation GNNs and outperforms baselines on nine of eleven benchmarks while ranking first on all three large-scale ones with a 1.53-point average gain.
-
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.
-
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
GraphIP-Bench is a new unified benchmark showing GNN model extraction succeeds at moderate query budgets while most defenses fail to prevent it or retain verification signals on surrogates.
-
Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems
SIES learns generalizable local coupling operators via signed source-target attention for controllable synchronization in graph dynamical systems and applies the principle to heterophilous graph representation learning.
-
Generalist Graph Anomaly Detection via Prototype-Based Distillation
ProMoS introduces the first unsupervised generalist graph anomaly detection method via prototype-based distillation from a self-supervised GNN teacher to a mixture-of-students model for zero-shot cross-graph transfer.
-
Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
ReFi-GAD uses a semantics-aware relational fingerprint and transformer-based model with SNR refinement to align heterogeneous features for generalist graph anomaly detection across unseen graphs.
-
Graph Navier Stokes Networks
GNSN adds convection governed by a dynamic velocity field to graph message passing, adaptively balancing it with diffusion to handle varying homophily levels and reduce oversmoothing while outperforming baselines on 12 datasets.
-
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.