mlsanityData to 7 Oct 2026

HyperAggregation: Aggregating over Graph Edges with Hypernetworks

arXiv 2407.11596 ↗First posted 16 Jul 2024cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

HyperAggregation is a hypernetwork-based aggregation function for Graph Neural Networks. It uses a hypernetwork to dynamically generate weights in the size of the current neighborhood, which are then used to aggregate this neighborhood. This aggregation with the generated weights is done like an MLP-Mixer channel mixing over variable-sized vertex neighborhoods. We demonstrate HyperAggregation in two models, GraphHyperMixer is a model based on MLP-Mixer while GraphHyperConv is derived from a GCN but with a hypernetwork-based aggregation function. We perform experiments on diverse benchmark datasets for the vertex classification, graph classification, and graph regression tasks. The results show that HyperAggregation can be effectively used for homophilic and heterophilic datasets in both inductive and transductive settings. GraphHyperConv performs better than GraphHyperMixer and is especially strong in the transductive setting. On the heterophilic dataset Roman-Empire it reaches a new state of the art. On the graph-level tasks our models perform in line with similarly sized models. Ablation studies investigate the robustness against various hyperparameter choices. The implementation of HyperAggregation as well code to reproduce all experiments is available under https://github.com/Foisunt/HyperAggregation .

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

38 of 48 references.

References · 38

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  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. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  6. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  7. 2019Simplifying Graph Convolutional Networkscited by 1,470
  8. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  9. 2016HyperNetworkscited by 1,003
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  11. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  12. 2020Simple and Deep Graph Convolutional Networkscited by 857
26 more
  1. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  2. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  3. 2020Benchmarking Graph Neural Networkscited by 672
  4. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  5. 2019Multi-scale Attributed Node Embeddingcited by 543
  6. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  7. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  8. 2022Structure-Aware Transformer for Graph Representation Learningcited by 191
  9. 2020Graph-Bert: Only Attention is Needed for Learning Graph Representationscited by 176
  10. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 154
  11. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 151
  12. 2021Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Predictioncited by 137
  13. 2018Graph HyperNetworks for Neural Architecture Searchcited by 131
  14. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  15. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  16. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 88
  17. 2021Graph-MLP: Node Classification without Message Passing in Graphcited by 73
  18. 2019Hyper-SAGNN: a self-attention based graph neural network for hypergraphscited by 69
  19. 2021Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoodscited by 57
  20. 2021Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced trainingcited by 54
  21. 2023Cooperative Graph Neural Networkscited by 35
  22. 2023Graph Neural Convection-Diffusion with Heterophilycited by 26
  23. 2022NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphscited by 14
  24. 2022HyperMixer: An MLP-based Low Cost Alternative to Transformerscited by 13
  25. 2022ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splittingcited by 13
  26. 2023Open-World Lifelong Graph Learningcited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025iN2V: Bringing Transductive Node Embeddings to Inductive Graphscited by 0