mlsanityData to 14 Oct 2026

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

arXiv 1704.02901 ↗First posted 10 Apr 2017cs.CV cs.LG cs.NEcited by 310

Not on the map. Why?

Abstract (arXiv)

A number of problems can be formulated as prediction on graph-structured data. In this work, we generalize the convolution operator from regular grids to arbitrary graphs while avoiding the spectral domain, which allows us to handle graphs of varying size and connectivity. To move beyond a simple diffusion, filter weights are conditioned on the specific edge labels in the neighborhood of a vertex. Together with the proper choice of graph coarsening, we explore constructing deep neural networks for graph classification. In particular, we demonstrate the generality of our formulation in point cloud classification, where we set the new state of the art, and on a graph classification dataset, where we outperform other deep learning approaches. The source code is available at https://github.com/mys007/ecc

Key facts. Cited by 310 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 105; 2022: 68; 2023: 54; 2024: 44; 2025: 22; 2026: 17.

310 papers.

Sort:

By area:

  1. 2021Dynamic Neural Networks: A Surveycited by 408
  2. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  3. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
  4. 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 197
  5. 2021Spherical Message Passing for 3D Graph Networkscited by 168
  6. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  7. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  8. 2021Weisfeiler and Leman go Machine Learning: The Story so farcited by 122
  9. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 120
  10. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  11. 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
  12. 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
38 more
  1. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  2. 2021PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equationscited by 106
  3. 2021BRepNet: A topological message passing system for solid modelscited by 95
  4. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 93
  5. 2021Graph Neural Networks in Network Neurosciencecited by 92
  6. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  7. 2023Attending to Graph Transformerscited by 83
  8. 2021SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanismcited by 75
  9. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  10. 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
  11. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  12. 2021Understanding Pooling in Graph Neural Networkscited by 69
  13. 2021FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizescited by 66
  14. 2021Reconstruction for Powerful Graph Representationscited by 65
  15. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  16. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  17. 2022Ordered Subgraph Aggregation Networkscited by 57
  18. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 57
  19. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  20. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  21. 2021A Hyperbolic-to-Hyperbolic Graph Convolutional Networkcited by 53
  22. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  23. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  24. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  25. 2022MIP-GNN: A Data-Driven Framework for Guiding Combinatorial Solverscited by 49
  26. 2021Dynamic Attentive Graph Learning for Image Restorationcited by 48
  27. 2022Shortest Path Networks for Graph Property Predictioncited by 46
  28. 2021From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformerscited by 38
  29. 2021Edge Representation Learning with Hypergraphscited by 37
  30. 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networkscited by 37
  31. 2023Attention-based Point Cloud Edge Samplingcited by 37
  32. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
  33. 2023Cooperative Graph Neural Networkscited by 36
  34. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloudcited by 35
  35. 2021Learning Graph Cellular Automatacited by 33
  36. 2022GNN-Surrogate: A Hierarchical and Adaptive Graph Neural Network for Parameter Space Exploration of Unstructured-Mesh Ocean Simulationscited by 32
  37. 2022A Unified Query-based Paradigm for Point Cloud Understandingcited by 32
  38. 2023Path Neural Networks: Expressive and Accurate Graph Neural Networkscited by 32

50 most cited of 310 All 310 (JSON)