mlsanityData to 13 Oct 2026

Representation Learning on Graphs with Jumping Knowledge Networks

arXiv 1806.03536 ↗First posted 9 Jun 2018cs.LG cs.AI cs.CVcited by 877

Not on the map. Why?

Abstract (arXiv)

Recent deep learning approaches for representation learning on graphs follow a neighborhood aggregation procedure. We analyze some important properties of these models, and propose a strategy to overcome those. In particular, the range of "neighboring" nodes that a node's representation draws from strongly depends on the graph structure, analogous to the spread of a random walk. To adapt to local neighborhood properties and tasks, we explore an architecture -- jumping knowledge (JK) networks -- that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation. In a number of experiments on social, bioinformatics and citation networks, we demonstrate that our model achieves state-of-the-art performance. Furthermore, combining the JK framework with models like Graph Convolutional Networks, GraphSAGE and Graph Attention Networks consistently improves those models' performance.

Key facts. Cited by 877 papers in the map (data through 13 Oct 2026). First posted on arXiv 9 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2020: 1; 2021: 184; 2022: 182; 2023: 170; 2024: 158; 2025: 112; 2026: 70.

877 papers.

Sort:

By area:

  1. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 473
  2. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
  3. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 266
  4. 2021A Survey on Deep Semi-supervised Learningcited by 250
  5. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 247
  6. 2021Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networkscited by 220
  7. 2023Language is All a Graph Needscited by 219
  8. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  9. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 209
  10. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  11. 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 193
  12. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
38 more
  1. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  2. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  3. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  4. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  5. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  6. 2023On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topologycited by 165
  7. 2021Equivariant Subgraph Aggregation Networkscited by 154
  8. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  9. 2023SGFormer: Simplifying and Empowering Transformers for Large-Graph Representationscited by 132
  10. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  11. 2021UniGNN: a Unified Framework for Graph and Hypergraph Neural Networkscited by 129
  12. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  13. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 126
  14. 2022Graph-Coupled Oscillator Networkscited by 124
  15. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  16. 2021DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networkscited by 117
  17. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  18. 2023GraphText: Graph Reasoning in Text Spacecited by 110
  19. 2021Combinatorial Optimization with Physics-Inspired Graph Neural Networkscited by 108
  20. 2022Transformer for Graphs: An Overview from Architecture Perspectivecited by 107
  21. 2022Not too little, not too much: a theoretical analysis of graph (over)smoothingcited by 106
  22. 2022FoSR: First-order spectral rewiring for addressing oversquashing in GNNscited by 105
  23. 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
  24. 2022Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvaturecited by 97
  25. 2023Understanding Oversquashing in GNNs through the Lens of Effective Resistancecited by 96
  26. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  27. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  28. 2021GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddingscited by 90
  29. 2022How Powerful are K-hop Message Passing Graph Neural Networkscited by 90
  30. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 89
  31. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  32. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 87
  33. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  34. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 85
  35. 2022Graph Attention Multi-Layer Perceptroncited by 83
  36. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  37. 2023DRew: Dynamically Rewired Message Passing with Delaycited by 82
  38. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81

50 most cited of 877 All 877 (JSON)