mlsanityData to 7 Oct 2026

USER: Unsupervised Structural Entropy-based Robust Graph Neural Network

arXiv 2302.05889 ↗First posted 12 Feb 2023cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Unsupervised/self-supervised graph neural networks (GNN) are vulnerable to inherent randomness in the input graph data which greatly affects the performance of the model in downstream tasks. In this paper, we alleviate the interference of graph randomness and learn appropriate representations of nodes without label information. To this end, we propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy. We analyze the property of intrinsic connectivity and define intrinsic connectivity graph. We also identify the rank of the adjacency matrix as a crucial factor in revealing a graph that provides the same embeddings as the intrinsic connectivity graph. We then introduce structural entropy in the objective function to capture such a graph. Extensive experiments conducted on clustering and link prediction tasks under random-noises and meta-attack over three datasets show USER outperforms benchmarks and is robust to heavier randomness.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 20 of its 47 references that are in the map. First posted on arXiv 12 Feb 2023.

Builds on

20 of 47 references.

References · 20

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  8. 2018Deep Graph Infomaxcited by 1,101
  9. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  10. 2017Representation Learning on Graphs: Methods and Applicationscited by 456
  11. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  12. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
8 more
  1. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  2. 2019Attributed Graph Clustering: A Deep Attentional Embedding Approachcited by 149
  3. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  4. 2019Attributed Graph Clustering via Adaptive Graph Convolutioncited by 96
  5. 2020Adaptive Graph Encoder for Attributed Graph Embeddingcited by 88
  6. 2019Learning Graph Embedding with Adversarial Training Methodscited by 84
  7. 2020A Survey of Adversarial Learning on Graphscited by 42
  8. 2020Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learningcited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 2; 2026: 2.

5 papers.

  1. 2023Hierarchical State Abstraction Based on Structural Information Principlescited by 14
  2. 2025Unsupervised Graph Clustering with Deep Structural Entropycited by 4
  3. 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approachcited by 0
  4. 2026Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphscited by 0
  5. 2026Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspectivecited by 0