Predict then Propagate: Graph Neural Networks meet Personalized PageRank
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:IFHGNZKWrecord.jsonopen to challenge →
read the original abstract
Neural message passing algorithms for semi-supervised classification on graphs have recently achieved great success. However, for classifying a node these methods only consider nodes that are a few propagation steps away and the size of this utilized neighborhood is hard to extend. In this paper, we use the relationship between graph convolutional networks (GCN) and PageRank to derive an improved propagation scheme based on personalized PageRank. We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP. Our model's training time is on par or faster and its number of parameters on par or lower than previous models. It leverages a large, adjustable neighborhood for classification and can be easily combined with any neural network. We show that this model outperforms several recently proposed methods for semi-supervised classification in the most thorough study done so far for GCN-like models. Our implementation is available online.
This paper has not been read by Pith yet.
Forward citations
Cited by 14 Pith papers
-
AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network
AGDN is a new GNN framework using a MixScore matrix and anisotropic graph diffusion to outperform prior methods on TSP instances across sizes and distributions.
-
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.
-
Graph Navier Stokes Networks
GNSN defines a dynamic velocity field on graphs to enable convection alongside diffusion, mitigating oversmoothing and outperforming baselines on twelve datasets with varying homophily.
-
A Benchmark Dataset for Graph Regression with Homogeneous and Multi-Relational Variants
RelSC is a new graph regression benchmark from program graphs with execution time labels, released in homogeneous (RelSC-H) and multi-relational (RelSC-M) variants to study representation effects.
-
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.
-
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
Bidirectional LLM-GNN co-teaching with round-based pseudo-label preference optimization outperforms golden-teacher baselines on few-shot TAG benchmarks by 3-8% absolute gains.
-
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 1...
-
Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents
A bidirectional semantic complementary tool retrieval method using planning-based query enhancement and dynamic tool dependency graphs with neighborhood aggregation improves retrieval accuracy on remote sensing and ge...
-
UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains
UniDetect is an LLM-based system that generates universal transaction summary texts and uses two-stage multimodal training on text plus graphs to detect fraudulent accounts across heterogeneous blockchains, outperform...
-
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.
-
A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
A hierarchical quantized tokenization framework with task-adaptive routing and dual-view streams for improved graph representation learning on node classification and link prediction.
-
An Efficient and Scalable Graph Condensation with Structure-Preserving
SP-ESGC decouples graph condensation into heat-kernel node condensation and pre-trained edge prediction for structure, claiming high efficiency and cross-GNN generalization on real-world datasets.
-
Attention-based graph neural networks: a survey
The survey groups attention-based GNNs into three stages—graph recurrent attention networks, graph attention networks, and graph transformers—while reviewing architectures and future directions.
-
Multi-Perspective Evidence Synthesis and Reasoning for Unsupervised Multimodal Entity Linking
MSR-MEL synthesizes instance-centric, group-level, lexical, and statistical evidence with LLMs and asymmetric teacher-student GNNs to outperform prior unsupervised methods on multimodal entity linking benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.