NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
hub
A Note on Over-Smoothing for Graph Neural Networks, June 2020
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
Looped LLMs converge to distinct cyclic fixed points per layer, repeating feedforward-style inference stages across recurrences.
Relaxed unitary convolutions for GNNs on meshes balance smoothness preservation with natural smoothing in dynamics, outperforming unitary convolutions and other models on PDEs and weather tasks.
HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduced parameter counts.
Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data.
SACHI enriches agent representations via graph transformer convolutions over inter-agent graphs to enable holistic information integration, outperforming baselines across five cooperative tasks with statistical significance.
The authors introduce aspect-aware datasets GoldRiM and SilverRiM for math papers and AchGNN, a heterogeneous GNN that outperforms prior methods by jointly modeling textual semantics, citations, and author lineage across aspects.
HISTOGRAPH applies unified layer-wise attention followed by node-wise attention over historical GNN activations to improve graph classification, especially in deep models.
C3E estimates hidden dimensions and depths for GNNs by treating them as communication channels to reduce over-squashing and improve representation learning.
GHR uses hierarchical recurrence on pooled graph abstractions to improve long-range dependency capture and out-of-range generalization while using far fewer parameters than existing models.
Introduces Hodge Spectral Duality, a hybrid neural architecture that applies Hodge orthogonality and operator splitting to isolate unlearnable topological degrees of freedom from learnable geometric dynamics in solution operators on geometric meshes.
LEDF-GNN fuses multi-layer embeddings nonlinearly and runs parallel processing on original and reconstructed topologies to capture long-range dependencies and mitigate heterophily-induced misaggregation in deep GNNs.
citing papers explorer
-
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.
-
A Mechanistic Analysis of Looped Reasoning Language Models
Looped LLMs converge to distinct cyclic fixed points per layer, repeating feedforward-style inference stages across recurrences.
-
Smoothness Errors in Dynamics Models and How to Avoid Them
Relaxed unitary convolutions for GNNs on meshes balance smoothness preservation with natural smoothing in dynamics, outperforming unitary convolutions and other models on PDEs and weather tasks.
-
Heterogeneous Sheaf Neural Networks
HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduced parameter counts.
-
Neural Point-Forms
Neural point-forms are introduced as permutation-invariant neural layers that output learned form-comparison matrices for point clouds, with a claimed consistency proof under sampling and manifold assumptions and competitive results on synthetic and biological data.
-
SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
SACHI enriches agent representations via graph transformer convolutions over inter-agent graphs to enable holistic information integration, outperforming baselines across five cooperative tasks with statistical significance.
-
Aspect-Aware Content-Based Recommendations for Mathematical Research Papers
The authors introduce aspect-aware datasets GoldRiM and SilverRiM for math papers and AchGNN, a heterogeneous GNN that outperforms prior methods by jointly modeling textual semantics, citations, and author lineage across aspects.
-
Learning from Historical Activations in Graph Neural Networks
HISTOGRAPH applies unified layer-wise attention followed by node-wise attention over historical GNN activations to improve graph classification, especially in deep models.
-
How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation
C3E estimates hidden dimensions and depths for GNNs by treating them as communication channels to reduce over-squashing and improve representation learning.
-
Graph Hierarchical Recurrence for Long-Range Generalization
GHR uses hierarchical recurrence on pooled graph abstractions to improve long-range dependency capture and out-of-range generalization while using far fewer parameters than existing models.
-
Topology-Preserving Neural Operator Learning via Hodge Decomposition
Introduces Hodge Spectral Duality, a hybrid neural architecture that applies Hodge orthogonality and operator splitting to isolate unlearnable topological degrees of freedom from learnable geometric dynamics in solution operators on geometric meshes.
-
Layer Embedding Deep Fusion Graph Neural Network
LEDF-GNN fuses multi-layer embeddings nonlinearly and runs parallel processing on original and reconstructed topologies to capture long-range dependencies and mitigate heterophily-induced misaggregation in deep GNNs.