mlsanityData to 14 Oct 2026

Recovering Missing Node Features with Local Structure-based Embeddings

arXiv 2309.09068 ↗First posted 16 Sep 2023cs.LG eess.SPcited by 5

Not on the map. Why?

Abstract (arXiv)

Node features bolster graph-based learning when exploited jointly with network structure. However, a lack of nodal attributes is prevalent in graph data. We present a framework to recover completely missing node features for a set of graphs, where we only know the signals of a subset of graphs. Our approach incorporates prior information from both graph topology and existing nodal values. We demonstrate an example implementation of our framework where we assume that node features depend on local graph structure. Missing nodal values are estimated by aggregating known features from the most similar nodes. Similarity is measured through a node embedding space that preserves local topological features, which we train using a Graph AutoEncoder. We empirically show not only the accuracy of our feature estimation approach but also its value for downstream graph classification. Our success embarks on and implies the need to emphasize the relationship between node features and graph structure in graph-based learning.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 16 Sep 2023.

Builds on

27 of 33 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  5. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  6. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  7. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  8. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
  9. 2019Position-aware Graph Neural Networkscited by 203
  10. 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 198
  11. 2021Identity-aware Graph Neural Networkscited by 198
  12. 2017Graph Embedding Techniques, Applications, and Performance: A Surveycited by 188
15 more
  1. 2020Random Features Strengthen Graph Neural Networkscited by 186
  2. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 146
  3. 2020Handling Missing Data with Graph Representation Learningcited by 133
  4. 2021On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Featurescited by 63
  5. 2019Missing Data Imputation with Adversarially-trained Graph Convolutional Networkscited by 54
  6. 2022Graph Filters for Signal Processing and Machine Learning on Graphscited by 53
  7. 2021On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphscited by 49
  8. 2020Learning on Attribute-Missing Graphscited by 42
  9. 2017Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networkscited by 40
  10. 2015Discrete Signal Processing on Graphs: Sampling Theorycited by 34
  11. 2016Kernel-based Reconstruction of Graph Signalscited by 20
  12. 2022GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clusteringcited by 13
  13. 2022Joint Network Topology Inference via a Shared Graphon Modelcited by 11
  14. 2021Graph-signal Reconstruction and Blind Deconvolution for Structured Inputscited by 5
  15. 2023Blind Graph Matching Using Graph Signalscited by 3

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 3.

5 papers.

  1. 2024Redesigning graph filter-based GNNs to relax the homophily assumptioncited by 8
  2. 2025Adapting to Heterophilic Graph Data with Structure-Guided Neighbor Discoverycited by 2
  3. 2024Structure-Guided Input Graph for GNNs facing Heterophilycited by 1
  4. 2025Topology-Driven Attribute Recovery for Attribute Missing Graph Learning in Social Internet of Thingscited by 0
  5. 2025How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?cited by 0