mlsanityData to 14 Oct 2026

T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation

arXiv 2212.12738 ↗First posted 24 Dec 2022cs.LGcited by 32

On the map: Knowledge distillation → Graph neural network distillation

Abstract (arXiv)

Graph Neural Networks (GNNs) have been a prevailing technique for tackling various analysis tasks on graph data. A key premise for the remarkable performance of GNNs relies on complete and trustworthy initial graph descriptions (i.e., node features and graph structure), which is often not satisfied since real-world graphs are often incomplete due to various unavoidable factors. In particular, GNNs face greater challenges when both node features and graph structure are incomplete at the same time. The existing methods either focus on feature completion or structure completion. They usually rely on the matching relationship between features and structure, or employ joint learning of node representation and feature (or structure) completion in the hope of achieving mutual benefit. However, recent studies confirm that the mutual interference between features and structure leads to the degradation of GNN performance. When both features and structure are incomplete, the mismatch between features and structure caused by the missing randomness exacerbates the interference between the two, which may trigger incorrect completions that negatively affect node representation. To this end, in this paper we propose a general GNN framework based on teacher-student distillation to improve the performance of GNNs on incomplete graphs, namely T2-GNN. To avoid the interference between features and structure, we separately design feature-level and structure-level teacher models to provide targeted guidance for student model (base GNNs, such as GCN) through distillation. Then we design two personalized methods to obtain well-trained feature and structure teachers. To ensure that the knowledge of the teacher model is comprehensively and effectively distilled to the student model, we further propose a dual distillation mode to enable the student to acquire as much expert knowledge as possible.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation. Builds on 21 of its 32 references that are in the map. First posted on arXiv 24 Dec 2022.

Builds on

21 of 32 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2017Graph Attention Networkscited by 8,923
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  8. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,077
  9. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  10. 2019Multi-scale Attributed Node Embeddingcited by 548
  11. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
  12. 2019Position-aware Graph Neural Networkscited by 203
9 more
  1. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  2. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  3. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  4. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 71
  5. 2021A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learningcited by 55
  6. 2020Graph Convolutional Networks for Graphs Containing Missing Featurescited by 47
  7. 2020Learning on Attribute-Missing Graphscited by 42
  8. 2020Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Predictioncited by 30
  9. 2020BasConv: Aggregating Heterogeneous Interactions for Basket Recommendation with Graph Convolutional Neural Networkcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 14; 2024: 5; 2025: 8; 2026: 5.

32 papers.

Sort:

By area:

  1. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  2. 2023Knowledge Distillation on Graphs: A Surveycited by 38
  3. 2023Learning Strong Graph Neural Networks with Weak Informationcited by 25
  4. 2024LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learningcited by 17
  5. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  6. 2023Accelerating Molecular Graph Neural Networks via Knowledge Distillationcited by 11
  7. 2025CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisitioncited by 10
  8. 2023Revisiting Initializing Then Refining: An Incomplete and Missing Graph Imputation Networkcited by 6
  9. 2024EasyST: A Simple Framework for Spatio-Temporal Predictioncited by 6
  10. 2023EX-Graph: A Pioneering Dataset Bridging Ethereum and Xcited by 5
  11. 2025SAGCNet: Spatial-Aware Graph Completion Network for Missing Slice Imputation in Population CMR Imagingcited by 4
  12. 2025Incomplete Graph Learning: A Comprehensive Surveycited by 3
20 more
  1. 2025Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiationcited by 2
  2. 2026DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptationcited by 2
  3. 2023Towards Unsupervised Graph Completion Learning on Graphs with Features and Structure Missingcited by 1
  4. 2024FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detectioncited by 1
  5. 2024MDS-GNN: A Mutual Dual-Stream Graph Neural Network on Graphs with Incomplete Features and Structurecited by 1
  6. 2026Pruned Traffic Trees: Native Semantic Compression with a Protocol-Structured Model Family for Encrypted Traffic Classificationcited by 1
  7. 2023Efficient Partitioning Method of Large-Scale Public Safety Spatio-Temporal Data based on Information Loss Constraintscited by 0
  8. 2023Reinforcement Federated Learning Method Based on Adaptive OPTICS Clusteringcited by 0
  9. 2023Semantic Representation Learning of Scientific Literature based on Adaptive Feature and Graph Neural Networkcited by 0
  10. 2023Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusioncited by 0
  11. 2023Federated Topic Model and Model Pruning Based on Variational Autoencodercited by 0
  12. 2023Relation Extraction Model Based on Semantic Enhancement Mechanismcited by 0
  13. 2023Topic model based on co-occurrence word networks for unbalanced short text datasetscited by 0
  14. 2025Topology-Driven Attribute Recovery for Attribute Missing Graph Learning in Social Internet of Thingscited by 0
  15. 2025Knowledge-Driven Federated Graph Learning on Model Heterogeneitycited by 0
  16. 2025Divide-Then-Rule: A Cluster-Driven Hierarchical Interpolator for Attribute-Missing Graphscited by 0
  17. 2025Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputationcited by 0
  18. 2026FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputationcited by 0
  19. 2026Model-to-Data Distillation for Graph Neural Networkscited by 0
  20. 2026Beyond Metadata: CAPRA for Hidden Subgroup Analysis under Missing Metadata in Medical Imagingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs
  2. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
  3. 2021Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
  4. 2024GNNAnatomy: Rethinking Model-Level Explanations for Graph Neural Networks
  5. 2024Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
  6. 2025Enhancing Graph Neural Networks: A Mutual Learning Approach
  7. 2021Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
  8. 2024A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation