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

arXiv: https://arxiv.org/abs/2212.12738 · HTML: https://mlsanity.com/paper/2212.12738/

## 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.

## Placed in

- Knowledge distillation / [Graph neural network distillation](https://mlsanity.com/distill/graph-neural-network-distillation/)

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings](https://mlsanity.com/paper/2006.13009/) (2020)
- [Position-aware Graph Neural Networks](https://mlsanity.com/paper/1906.04817/) (2019)
- [Scaling Graph Neural Networks with Approximate PageRank](https://mlsanity.com/paper/2007.01570/) (2020)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [AM-GCN: Adaptive Multi-channel Graph Convolutional Networks](https://mlsanity.com/paper/2007.02265/) (2020)
- [A Survey on Graph Structure Learning: Progress and Opportunities](https://mlsanity.com/paper/2103.03036/) (2021)
- [A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning](https://mlsanity.com/paper/2101.01669/) (2021)
- [Graph Convolutional Networks for Graphs Containing Missing Features](https://mlsanity.com/paper/2007.04583/) (2020)
- [Learning on Attribute-Missing Graphs](https://mlsanity.com/paper/2011.01623/) (2020)
- [Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction](https://mlsanity.com/paper/2006.01963/) (2020)
- [BasConv: Aggregating Heterogeneous Interactions for Basket Recommendation with Graph Convolutional Neural Network](https://mlsanity.com/paper/2001.09900/) (2020)

## Built on by (most cited first, 30 of 32)

- [A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges](https://mlsanity.com/paper/2403.04468/) (2024)
- [Knowledge Distillation on Graphs: A Survey](https://mlsanity.com/paper/2302.00219/) (2023)
- [Learning Strong Graph Neural Networks with Weak Information](https://mlsanity.com/paper/2305.18457/) (2023)
- [LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning](https://mlsanity.com/paper/2406.01032/) (2024)
- [Towards Data-centric Graph Machine Learning: Review and Outlook](https://mlsanity.com/paper/2309.10979/) (2023)
- [Accelerating Molecular Graph Neural Networks via Knowledge Distillation](https://mlsanity.com/paper/2306.14818/) (2023)
- [CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition](https://mlsanity.com/paper/2506.17709/) (2025)
- [Revisiting Initializing Then Refining: An Incomplete and Missing Graph Imputation Network](https://mlsanity.com/paper/2302.07524/) (2023)
- [EasyST: A Simple Framework for Spatio-Temporal Prediction](https://mlsanity.com/paper/2409.06748/) (2024)
- [EX-Graph: A Pioneering Dataset Bridging Ethereum and X](https://mlsanity.com/paper/2310.01015/) (2023)
- [SAGCNet: Spatial-Aware Graph Completion Network for Missing Slice Imputation in Population CMR Imaging](https://mlsanity.com/paper/2508.07041/) (2025)
- [Incomplete Graph Learning: A Comprehensive Survey](https://mlsanity.com/paper/2502.12412/) (2025)
- [Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation](https://mlsanity.com/paper/2507.13368/) (2025)
- [DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation](https://mlsanity.com/paper/2604.03154/) (2026)
- [Towards Unsupervised Graph Completion Learning on Graphs with Features and Structure Missing](https://mlsanity.com/paper/2309.02762/) (2023)
- [FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detection](https://mlsanity.com/paper/2407.00383/) (2024)
- [MDS-GNN: A Mutual Dual-Stream Graph Neural Network on Graphs with Incomplete Features and Structure](https://mlsanity.com/paper/2408.04845/) (2024)
- [Pruned Traffic Trees: Native Semantic Compression with a Protocol-Structured Model Family for Encrypted Traffic Classification](https://mlsanity.com/paper/2608.21874/) (2026)
- [Efficient Partitioning Method of Large-Scale Public Safety Spatio-Temporal Data based on Information Loss Constraints](https://mlsanity.com/paper/2306.12857/) (2023)
- [Reinforcement Federated Learning Method Based on Adaptive OPTICS Clustering](https://mlsanity.com/paper/2306.12859/) (2023)
- [Semantic Representation Learning of Scientific Literature based on Adaptive Feature and Graph Neural Network](https://mlsanity.com/paper/2311.00296/) (2023)
- [Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion](https://mlsanity.com/paper/2311.00300/) (2023)
- [Federated Topic Model and Model Pruning Based on Variational Autoencoder](https://mlsanity.com/paper/2311.00314/) (2023)
- [Relation Extraction Model Based on Semantic Enhancement Mechanism](https://mlsanity.com/paper/2311.02564/) (2023)
- [Topic model based on co-occurrence word networks for unbalanced short text datasets](https://mlsanity.com/paper/2311.02566/) (2023)
- [Topology-Driven Attribute Recovery for Attribute Missing Graph Learning in Social Internet of Things](https://mlsanity.com/paper/2501.10151/) (2025)
- [Knowledge-Driven Federated Graph Learning on Model Heterogeneity](https://mlsanity.com/paper/2501.12624/) (2025)
- [Divide-Then-Rule: A Cluster-Driven Hierarchical Interpolator for Attribute-Missing Graphs](https://mlsanity.com/paper/2507.10595/) (2025)
- [Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation](https://mlsanity.com/paper/2512.06356/) (2025)
- [FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputation](https://mlsanity.com/paper/2601.18938/) (2026)

## 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.