mlsanityData to 14 Oct 2026

Graph Classification via Deep Learning with Virtual Nodes

arXiv 1708.04357 ↗First posted 14 Aug 2017cs.LG cs.AI stat.MLcited by 30

Not on the map. Why?

Abstract (arXiv)

Learning representation for graph classification turns a variable-size graph into a fixed-size vector (or matrix). Such a representation works nicely with algebraic manipulations. Here we introduce a simple method to augment an attributed graph with a virtual node that is bidirectionally connected to all existing nodes. The virtual node represents the latent aspects of the graph, which are not immediately available from the attributes and local connectivity structures. The expanded graph is then put through any node representation method. The representation of the virtual node is then the representation of the entire graph. In this paper, we use the recently introduced Column Network for the expanded graph, resulting in a new end-to-end graph classification model dubbed Virtual Column Network (VCN). The model is validated on two tasks: (i) predicting bio-activity of chemical compounds, and (ii) finding software vulnerability from source code. Results demonstrate that VCN is competitive against well-established rivals.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 14; 2025: 4; 2026: 3.

30 papers.

Sort:

  1. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 133
  2. 2023KITS: Inductive Spatio-Temporal Kriging with Increment Training Strategycited by 19
  3. 2024VN-EGNN: E(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identificationcited by 15
  4. 2024Probabilistic Graph Rewiring via Virtual Nodescited by 15
  5. 2024Understanding Virtual Nodes: Oversquashing and Node Heterogeneitycited by 14
  6. 2022FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inferencecited by 11
  7. 2022GenGNN: A Generic FPGA Framework for Graph Neural Network Accelerationcited by 9
  8. 2023Learning Large Graph Property Prediction via Graph Segment Trainingcited by 9
  9. 2023Search to Capture Long-range Dependency with Stacking GNNs for Graph Classificationcited by 7
  10. 2025Fast and Distributed Equivariant Graph Neural Networks by Virtual Node Learningcited by 6
  11. 2024Next Level Message-Passing with Hierarchical Support Graphscited by 5
  12. 2024Vision HgNN: An Electron-Micrograph is Worth Hypergraph of Hypernodescited by 3
18 more
  1. 2025Short-Range Oversquashingcited by 3
  2. 2022DOTIN: Dropping Task-Irrelevant Nodes for GNNscited by 2
  3. 2023TacoGFN: Target-conditioned GFlowNet for Structure-based Drug Designcited by 2
  4. 2024Inference of Sequential Patterns for Neural Message Passing in Temporal Graphscited by 1
  5. 2024wav2graph: A Framework for Supervised Learning Knowledge Graph from Speechcited by 1
  6. 2024Whole-Graph Representation Learning For the Classification of Signed Networkscited by 1
  7. 2022Tired of Over-smoothing? Stress Graph Drawing Is All You Need!cited by 0
  8. 2024Sampling Foundational Transformer: A Theoretical Perspectivecited by 0
  9. 2024Multi-Source Knowledge-Based Hybrid Neural Framework for Time Series Representation Learningcited by 0
  10. 2024Multi-Knowledge Fusion Network for Time Series Representation Learningcited by 0
  11. 2024Kriformer: A Novel Spatiotemporal Kriging Approach Based on Graph Transformerscited by 0
  12. 2024Hypergraph-based multi-scale spatio-temporal graph convolution network for Time-Series anomaly detectioncited by 0
  13. 2024Introduction to Graph Neural Networks for Machine Learning Engineerscited by 0
  14. 2025BuildSTG: A Multi-building Energy Load Forecasting Method using Spatio-Temporal Graph Neural Networkcited by 0
  15. 2025Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregationcited by 0
  16. 2026NAG: A Unified Native Architecture for Encoder-free Text-Graph Modeling in Language Modelscited by 0
  17. 2026Pulmonary Embolism Risk Stratification from CTPA and Medical Records: Vascular Graphs Are Not All You Needcited by 0
  18. 2026Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphscited by 0