mlsanityData to 7 Oct 2026

Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily

arXiv 2203.10280 ↗First posted 19 Mar 2022cs.LG cs.SIcited by 14

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) show strong expressive power on graph data mining, by aggregating information from neighbors and using the integrated representation in the downstream tasks. The same aggregation methods and parameters for each node in a graph are used to enable the GNNs to utilize the homophily relational data. However, not all graphs are homophilic, even in the same graph, the distributions may vary significantly. Using the same convolution over all nodes may lead to the ignorance of various graph patterns. Furthermore, many existing GNNs integrate node features and structure identically, which ignores the distributions of nodes and further limits the expressive power of GNNs. To solve these problems, we propose Meta Weight Graph Neural Network (MWGNN) to adaptively construct graph convolution layers for different nodes. First, we model the Node Local Distribution (NLD) from node feature, topological structure and positional identity aspects with the Meta-Weight. Then, based on the Meta-Weight, we generate the adaptive graph convolutions to perform a node-specific weighted aggregation and boost the node representations. Finally, we design extensive experiments on real-world and synthetic benchmarks to evaluate the effectiveness of MWGNN. These experiments show the excellent expressive power of MWGNN in dealing with graph data with various distributions.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 19 Mar 2022.

Builds on

27 of 33 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2019Simplifying Graph Convolutional Networkscited by 1,470
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  12. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
15 more
  1. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  2. 2019Multi-scale Attributed Node Embeddingcited by 543
  3. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  4. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  5. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 363
  6. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 329
  7. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
  8. 2020Towards Deeper Graph Neural Networkscited by 296
  9. 2017struc2vec: Learning Node Representations from Structural Identitycited by 214
  10. 2019Position-aware Graph Neural Networkscited by 203
  11. 2020Graph Neural Networks with Heterophilycited by 202
  12. 2021Identity-aware Graph Neural Networkscited by 197
  13. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  14. 2018A simple yet effective baseline for non-attributed graph classificationcited by 16
  15. 2018Do Diffusion Protocols Govern Cascade Growth?cited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 7; 2024: 3; 2025: 2.

14 papers.

Sort:

  1. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 223
  2. 2023Continual Learning on Dynamic Graphs via Parameter Isolationcited by 35
  3. 2023Homophily-oriented Heterogeneous Graph Rewiringcited by 18
  4. 2024Understanding Heterophily for Graph Neural Networkscited by 15
  5. 2022ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splittingcited by 13
  6. 2022MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distributioncited by 11
  7. 2025DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approachcited by 11
  8. 2023Graph Neural Networks with Diverse Spectral Filteringcited by 9
  9. 2023GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropycited by 9
  10. 2023Heterophily-Aware Graph Attention Networkcited by 7
  11. 2025Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneitycited by 3
  12. 2024ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networkscited by 2
2 more
  1. 2023Centrality-Based Node Feature Augmentation for Robust Network Alignmentcited by 1
  2. 2024Graph as a feature: improving node classification with non-neural graph-aware logistic regressioncited by 0