GCN-MPPR: Enhancing the Propagation of Message Passing Neural Networks via Motif-Based Personalized PageRank
Not on the map. Why?
Abstract (arXiv)
The algorithms based on message passing neural networks (MPNNs) on graphs have recently achieved great success for various graph applications. However, studies find that these methods always propagate the information to very limited neighborhoods with shallow depth, particularly due to over-smoothing. That means most of the existing MPNNs fail to be so `deep'. Although some previous work tended to handle this challenge via optimization- or structure-level remedies, the overall performance of GCNs still suffers from limited accuracy, poor stability, and unaffordable computational cost. Moreover, neglect of higher-order relationships during the propagation of MPNNs has further limited the performance of them. To overcome these challenges, a novel variant of PageRank named motif-based personalized PageRank (MPPR) is proposed to measure the influence of one node to another on the basis of considering higher-order motif relationships. Secondly, the MPPR is utilized to the message passing process of GCNs, thereby guiding the message passing process at a relatively `high' level. The experimental results show that the proposed method outperforms almost all of the baselines on accuracy, stability, and time consumption. Additionally, the proposed method can be considered as a component that can underpin almost all GCN tasks, with DGCRL being demonstrated in the experiment. The anonymous code repository is available at: https://anonymous.4open.science/r/GCN-MPPR-AFD6/.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 58 references that are in the map. First posted on arXiv 8 Feb 2026.
Builds on
25 of 58 references.
References · 25
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2016Variational Graph Auto-Encoderscited by 1,373
- 2018Pitfalls of Graph Neural Network Evaluationcited by 994
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
- 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
- 2016Higher-order organization of complex networkscited by 109
- 2022RAW-GNN: RAndom Walk Aggregation based Graph Neural Networkcited by 25
- 2023Graph Neural Networks with Diverse Spectral Filteringcited by 9
- 2014Path Sampling: A Fast and Provable Method for Estimating 4-Vertex Subgraph Countscited by 8
- 2023Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomialscited by 8
- 2024Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theorycited by 8
13 more
- 2024Efficient Topology-aware Data Augmentation for High-Degree Graph Neural Networkscited by 6
- 2024Hyperdimensional Representation Learning for Node Classification and Link Predictioncited by 5
- 2024Hyperbolic Heterogeneous Graph Attention Networkscited by 5
- 2025Dual-level Mixup for Graph Few-shot Learning with Fewer Taskscited by 5
- 2024GraSP: Simple yet Effective Graph Similarity Predictionscited by 4
- 2019Ranking Users in Social Networks with Motif-based PageRankcited by 3
- 2025The Oversmoothing Fallacy: A Misguided Narrative in GNN Researchcited by 3
- 2022Graph Classification via Discriminative Edge Feature Learningcited by 2
- 2024Revisiting Neighborhood Aggregation in Graph Neural Networks for Node Classification using Statistical Signal Processingcited by 2
- 2025Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?cited by 2
- 2025Effective Clustering for Large Multi-Relational Graphscited by 2
- 2024Counting Cohesive Subgraphs with Hereditary Propertiescited by 1
- 2024Counting Small Induced Subgraphs: Hardness via Fourier Analysiscited by 1
Built on by
Not cited yet.