Graph machine learning has been intensively studied and widely applied into various applications recently, such as social network, knowledge graph, recommender system, etc. One underlying assumption commonly adopted by these methods is that all attributes of nodes are complete. However, in practice, this assumption may not hold due to 1) the absence of particular attributes; 2) the absence of all the attributes of specific nodes. Here we provide collections for partial graph machine learning literature.

1. [AAAI 2023] T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillation [paper]
2. [AAAI 2023] Data Imputation with Iterative Graph Reconstruction [paper]
3. [WWW 2023] SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking [paper]
4. [WWW 2023] GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner [paper]
5. [WWW 2023] Automated Spatio-Temporal graph contrastive learning [paper]
6. [ICLR 2023] Fair Attribute Completion on Graph with Missing Attributes [paper]
7. [ICLR 2023] Confidence-Based Feature Imputation for Graphs with Partially Known Features [paper]
8. [ICLR 2023] Learnable Topological Features for Phylogenetic Inference via Graph Neural Networks [paper]
9. [KBS 2023] Dynamic Graph Convolutional Recurrent Imputation Network for Spatiotemporal Traffic Missing Data [paper]
10. [KDD 2023] What’s Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders [paper]
11. [WSDM 2023] S2GAE: Self-Supervised Graph Autoencoders are Generalizable Learners with Graph Masking [paper]
12. [Information Sciences 2023] Ensembled Masked Graph Autoencoders for Link Anomaly Detection in A Road Network Considering Spatiotemporal Features [paper]
13. [Information Sciences 2023] HetReGAT-FC: Heterogeneous Residual Graph Attention Network via Feature Completion [paper]
14. [Methods 2023] Multi-sample dual-decoder graph autoencoder [paper]
15. [SIGIR 2023] Graph Masked Autoencoder for Sequential Recommendation [paper]
16. [Arxiv 2023.01] Generative Graph Neural Networks for Link Prediction [paper]
17. [Arxiv 2023.01] AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network [paper]
18. [Arxiv 2023.01] Who Should I Engage with At What Time? A Missing Event Aware Temporal Graph Neural Network [paper]
19. [Arxiv 2023.01] HAT-GAE: Self-Supervised Graph Auto-encoders with Hierarchical Adaptive Masking and Trainable Corruption [paper]
20. [Arxiv 2023.02] Revisiting Initializing Then Refining: An Incomplete and Missing Graph Imputation Network [paper]
21. [Arxiv 2023.02] Self-supervised Guided Hypergraph Feature Propagation for Semi-supervised Classification with Missing Node Features [paper]
22. [Arxiv 2023.03] Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction [paper]
23. [Arxiv 2023.04] RARE: Robust Masked Graph Autoencoder [paper]
24. [Arxiv 2023.05] AmGCL: Feature Imputation of Attribute Missing Graph via Self-supervised Contrastive Learning [paper]
25. [Arxiv 2023.06] Masked Contrastive Graph Representation Learning for Age Estimation [paper]

1. [IEEE TPAMI 2022] Learning on Attribute-Missing Graphs [paper|code]
2. [IEEE TKDE 2022] An Attribute-Aware Attentive GCN Model for Attribute Missing in Recommendation [paper]
3. [IEEE TMM 2022] Latent Heterogeneous Graph Network for Incomplete Multi-View Learning [paper]
4. [IEEE TCYB 2022] Amer: A New Attribute-Missing Network Embedding Approach [paper]
5. [IEEE TNNLS 2022] Analyzing Heterogeneous Networks with Missing Attributes by Unsupervised Contrastive Learning [paper]
6. [ACL 2022] SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models [paper]
7. [ACL 2022] CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion [paper]
8. [KDD 2022] GraphMAE: Self-Supervised Masked Graph Autoencoders [paper]
9. [KDD 2022] Knowledge Graph Completion with Pre-trained Multimodal Transformer and Twins Negative Sampling [paper]
10. [KDD 2022] Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries [paper]
11. [IJCAI 2022] Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion [paper]
12. [IJCAI 2022] Initializing Then Refining: A Simple Graph Attribute Imputation Network [paper]
13. [IJCAI 2022] Graph Masked Autoencoder Enhanced Predictor for Neural Architecture Search [paper]
14. [WWW 2022] Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data [paper|code]
15. [WWW 2022] From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer [paper]
16. [WWW Workshop 2022] Deep Partial Multiplex Network Embedding [paper]
17. [SIGIR 2022] Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective [paper]
18. [PR 2022] Incomplete Multiview Nonnegative Representation Learning with Multiple Graphs [paper]
19. [ICLR 2022] Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods [paper|code]
20. [ICLR 2022] Neural Methods for Logical Reasoning Over Knowledge Graphs [paper]
21. [ICML 2022] Self-Supervised Representation Learning via Latent Graph Prediction [paper]
22. [NeurIPS 2022] Neural-Symbolic Entangled Framework for Complex Query Answering [paper]
23. [NeurIPS 2022] Rethinking Knowledge Graph Evaluation Under the Open-World Assumption [paper]
24. [NeurIPS 2022] Deep Bidirectional Language-Knowledge Graph Pretraining [paper]
25. [NeurIPS Workshop 2022] Bi-channel Masked Graph Autoencoders for Spatially Resolved Single-cell Transcriptomics Data Imputation [paper]
26. [CIKM 2022] I Know What You Do Not Know: Knowledge Graph Embedding via Co-distillation Learning [paper]
27. [CIKM 2022] Models and Benchmarks for Representation Learning of Partially Observed Subgraphs [paper]
28. [CIKM 2022] MGMAE: Molecular Representation Learning by Reconstructing Heterogeneous Graphs with A High Mask Ratio [paper]
29. [CIKM 2022] MentorGNN: Deriving Curriculum for Pre-Training GNNs [paper]
30. [CIKM 2022] On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs [paper]
31. [EMNLP 2022] Self-supervised Graph Masking Pre-training for Graph-to-Text Generation [paper]
32. [COLING 2022] The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection [paper]
33. [ECML-PKDD 2022] Masked Graph Auto-Encoder Constrained Graph Pooling [paper]
34. [Arxiv 2022.01] MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs [paper]
35. [Arxiv 2022.02] Graph Masked Autoencoders with Transformers [paper]
36. [Arxiv 2022.03] Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment [paper]
37. [Arxiv 2022.03] ACTIVE: Augmentation-Free Graph Contrastive Learning for Partial Multi-View Clustering [paper]
38. [Arxiv 2022.03] Gransformer: Transformer-based Graph Generation [paper]
39. [Arxiv 2022.04] Graph Auto-Encoders for Network Completion [paper]
40. [Arxiv 2022.05] MaskGAE: Masked Graph Modeling Meets Graph Autoencoders [paper]
41. [Arxiv 2022.05] Robust Graph Representation Learning for Local Corruption Recovery [paper]
42. [Arxiv 2022.05] Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations [paper]
43. [Arxiv 2022.06] Accurate Node Feature Estimation with Structured Variational Graph Autoencoder [paper]
44. [Arxiv 2022.06] ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion [paper]
45. [Arxiv 2022.06] Schema-Guided Event Graph Completion [paper]
46. [Arxiv 2022.06] Attention-wise Masked Graph Contrastive Learning for Predicting Molecular Property [paper]
47. [Arxiv 2022.07] Unsupervised pre-training of graph transformers on patient population graphs [paper]
48. [Arxiv 2022.07] Masked Spatial-Spectral Autoencoders Are Excellent Hyperspectral Defenders [paper]
49. [Arxiv 2022.07] Cybersecurity Entity Alignment via Masked Graph Attention Networks [paper]
50. [Arxiv 2022.08] Heterogeneous Graph Masked Autoencoders [paper]
51. [Arxiv 2022.08] Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack Perspectiv [paper]
52. [Arxiv 2022.09] DiP-GNN: Discriminative Pre-Training of Graph Neural Networks [paper]
53. [Arxiv 2022.10] Federated Graph-based Networks with Shared Embedding [paper]
54. [Arxiv 2022.10] How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders [paper]
55. [Arxiv 2022.10] M3FGM: A Node Masking and Multi-granularity Message Passing-based Federated Graph Model for Spatial-temporal Data Prediction [paper]
56. [Arxiv 2022.11] BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation [paper]
57. [Arxiv 2022.11] Handling Missing Data via Max-Entropy Regularized Graph Autoencoder [paper]
58. [Arxiv 2022.12] Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation [paper]
59. [Arxiv 2022.12] Csat: Contrastive Sampling-Aggregating Transformer for Attribute-Missing Graph Learning [paper]

1. [WWW 2021] Heterogeneous Graph Neural Network via Attribute Completion [paper|code]
2. [WWW 2021] Mask-GVAE: Blind Denoising Graphs via Partition [paper]
3. [NeurIPS 2021] Subgraph Federated Learning with Missing Neighbor Generation [paper]
4. [NeurIPS 2021] Multi-view Contrastive Graph Clustering [paper|code]
5. [NeurIPS 2021] Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM) [paper]
6. [FGCS 2021] Graph Convolutional Networks for Graphs Containing Missing Features [paper|code]
7. [FGCS 2021] Efficient Search Over Incomplete Knowledge Graphs in Binarized Embedding Space [paper]
8. [AAAI Workshop 2021] Context-Enhanced Entity and Relation Embedding for Knowledge Graph Completion [paper]
9. [KDD Workshop 2021] On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs [paper|code]
10. [CIKM 2021] Inductive Matrix Completion Using Graph Autoencoder [paper|code]
11. [ICASSP 2021] Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation [paper]
12. [IEEE TSP 2021] Community Detection and Matrix Completion With Social and Item Similarity Graphs [paper|code]
13. [Nature Communications 2021] Masked Graph Modeling for Molecule Generation [paper]
14. [Arxiv 2021.02] Wasserstein Diffusion on Graphs with Missing Attributes [paper]
15. [Arxiv 2021.06] Incomplete Graph Representation and Learning via Partial Graph Neural Networks [paper]
16. [Arxiv 2021.06] Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining [paper]
17. [Arxiv 2021.10] VICAUSE: Simultaneous Missing Value Imputation and Causal Discovery with Groups [paper]
18. [Arxiv 2021.10] CORGI: Content-Rich Graph Neural Networks with Attention [paper|code]
19. [Arxiv 2021.10] SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs [paper|code]
20. [Arxiv 2021.11] On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features [paper]
21. [Arxiv 2021.12] Siamese Attribute-missing Graph Auto-encoder [paper]
22. [Arxiv 2021.12] Link-Intensive Alignment for Incomplete Knowledge Graphs [paper]
23. [Arxiv 2021.12] Incomplete Multi-view Clustering via Cross-view Relation Transfer [paper]
24. [Arxiv 2021.12] Two-view Graph Neural Networks for Knowledge Graph Completion [paper]
25. [Arxiv 2021.12] Incomplete Knowledge Graph Alignment [paper]

1. [NeurIPS 2020] Handling Missing Data with Graph Representation Learning [paper|code]
2. [NeurIPS 2020] Matrix Completion with Hierarchical Graph Side Information [paper]
3. [NN 2020] Missing Data Imputation with Adversarially-trained Graph Convolutional Networks [paper|code]
4. [ICLR 2020] Inductive Matrix Completion Based on Graph Neural Networks [paper|code]
5. [EMNLP 2020] TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion [paper|code]
6. [EMNLP 2020] Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer [paper|code]
7. [EMNLP 2020] MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning [paper]

1. [KBS 2019] Adversarial Learning for Multi-view Network Embedding on Incomplete Graphs [paper]
2. [ICDM 2019] Learning to Hash for Efficient Search over Incomplete Knowledge Graphs [paper|code]
3. [K-CAP 2019] Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs [paper|code]
4. [Arxiv 2019.07] Node Attribute Generation on Graphs [paper]

1. [ECCV Workshop 2018] Incomplete Multi-view Clustering via Graph Regularized Matrix Factorization [paper|code]
2. [RecSys 2018] Spectral Collaborative Filtering [paper|code]
3. [Arxiv 2018.11] Attributed Network Embedding for Incomplete Attributed Networks [paper]

1. [NeurIPS 2017] Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks [paper|code]
2. [CIKM 2017] From Properties to Links: Deep Network Embedding on Incomplete Graphs [paper]
3. [Arxiv 2017.06] Graph Convolutional Matrix Completion [paper|code]

• awesome-deep-graph-clustering
• awesome-graph-representation-learning
• awesome-graph-self-supervised-learning
• awesome-self-supervised-gnn
• awesome-self-supervised-learning-for-graphs
• awesome-masked-autoencoders

If interested, you are welcome to contribute this repo by contracting [email protected].