Introduces Hypergraph U-Nets with PHPool and PHUnpool operators derived from hierarchical clustering dendrograms for hypergraph reconstruction, classification, and anomaly detection.
hub
Adaptive universal generalized pagerank graph neural network
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
representative citing papers
MbaGCN combines message aggregation, selective state space transitions, and node state prediction to create a more scalable deep graph convolutional network.
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.
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.
LIP decomposes GNN message passing to quantify label influences, builds a label influence graph, and propagates high-order effects to outperform prior methods on multi-label node classification benchmarks.
ADC-GNN improves few-shot graph fraud detection by combining diffusion-guided feature augmentation, contrastive learning, and multi-hop spectral attention, showing gains on public benchmarks under 1% labeled data.
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
InGSL reduces edge redundancy in existing graph structure learning methods by adding a mutual-information-guided diversity term, delivering better results with fewer edges across six tested frameworks.
Inductive subgraphs serve as shortcuts in heterophilic graphs, and CD-GNN disentangles spurious from causal subgraphs by blocking non-causal paths to improve robustness and accuracy.
QUIET is a hierarchical RVQ-based graph tokenizer with a learned level-weighting gate; it improves several benchmarks but not consistently against the strongest baselines.
citing papers explorer
-
Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets
Introduces Hypergraph U-Nets with PHPool and PHUnpool operators derived from hierarchical clustering dendrograms for hypergraph reconstruction, classification, and anomaly detection.
-
Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
MbaGCN combines message aggregation, selective state space transitions, and node state prediction to create a more scalable deep graph convolutional network.
-
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.
-
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.
-
Multi-Label Node Classification with Label Influence Propagation
LIP decomposes GNN message passing to quantify label influences, builds a label influence graph, and propagates high-order effects to outperform prior methods on multi-label node classification benchmarks.
-
Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection
ADC-GNN improves few-shot graph fraud detection by combining diffusion-guided feature augmentation, contrastive learning, and multi-hop spectral attention, showing gains on public benchmarks under 1% labeled data.
-
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.
-
Informative Graph Structure Learning
InGSL reduces edge redundancy in existing graph structure learning methods by adding a mutual-information-guided diversity term, delivering better results with fewer edges across six tested frameworks.
-
Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
Inductive subgraphs serve as shortcuts in heterophilic graphs, and CD-GNN disentangles spurious from causal subgraphs by blocking non-causal paths to improve robustness and accuracy.
-
A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
QUIET is a hierarchical RVQ-based graph tokenizer with a learned level-weighting gate; it improves several benchmarks but not consistently against the strongest baselines.