mlsanityData to 14 Oct 2026

Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddings

arXiv 2309.16564 ↗First posted 28 Sep 2023cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Unsupervised learning allows us to leverage unlabelled data, which has become abundantly available, and to create embeddings that are usable on a variety of downstream tasks. However, the typical lack of interpretability of unsupervised representation learning has become a limiting factor with regard to recent transparent-AI regulations. In this paper, we study graph representation learning and we show that data augmentation that preserves semantics can be learned and used to produce interpretations. Our framework, which we named INGENIOUS, creates inherently interpretable embeddings and eliminates the need for costly additional post-hoc analysis. We also introduce additional metrics addressing the lack of formalism and metrics in the understudied area of unsupervised-representation learning interpretability. Our results are supported by an experimental study applied to both graph-level and node-level tasks and show that interpretable embeddings provide state-of-the-art performance on subsequent downstream tasks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 35 references that are in the map. First posted on arXiv 28 Sep 2023.

Builds on

27 of 35 references.

References · 27

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  4. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  5. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  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. 2019Graph Neural Networks for Social Recommendationcited by 714
  9. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
  10. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  11. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  12. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
15 more
  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  2. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  3. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  4. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  5. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  6. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  7. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 133
  8. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  9. 2022Rethinking Minimal Sufficient Representation in Contrastive Learningcited by 69
  10. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  11. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  12. 2021RELAX: Representation Learning Explainabilitycited by 12
  13. 2022Bootstrapping Informative Graph Augmentation via A Meta Learning Approachcited by 6
  14. 2020netrd: A library for network reconstruction and graph distancescited by 5
  15. 2022Towards Explanation for Unsupervised Graph-Level Representation Learningcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025i-WiViG: Interpretable Window Vision GNNcited by 0