mlsanityData to 7 Oct 2026

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

arXiv 2204.00323 ↗First posted 1 Apr 2022cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Two prominent examples are molecule property prediction and brain connectome analysis. Importantly, recent works have shown that considering relationships between input data samples have a positive regularizing effect for the downstream task in healthcare applications. These relationships are naturally modeled by a (possibly unknown) graph structure between input samples. In this work, we propose Graph-in-Graph (GiG), a neural network architecture for protein classification and brain imaging applications that exploits the graph representation of the input data samples and their latent relation. We assume an initially unknown latent-graph structure between graph-valued input data and propose to learn end-to-end a parametric model for message passing within and across input graph samples, along with the latent structure connecting the input graphs. Further, we introduce a degree distribution loss that helps regularize the predicted latent relationships structure. This regularization can significantly improve the downstream task. Moreover, the obtained latent graph can represent patient population models or networks of molecule clusters, providing a level of interpretability and knowledge discovery in the input domain of particular value in healthcare.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 53 of its 113 references that are in the map. First posted on arXiv 1 Apr 2022.

Builds on

53 of 113 references.

References · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  7. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  8. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  9. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  10. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
38 more
  1. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  2. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  3. 2018Link Prediction Based on Graph Neural Networkscited by 829
  4. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  5. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  6. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  7. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  8. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  9. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  10. 2018Learning Human-Object Interactions by Graph Parsing Neural Networkscited by 176
  11. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  12. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  13. 2018Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Diseasecited by 98
  14. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  15. 2020Differentiable Graph Module (DGM) for Graph Convolutional Networkscited by 86
  16. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  17. 2019Hierarchical Graph Pooling with Structure Learningcited by 81
  18. 2021Few-Shot Graph Learning for Molecular Property Predictioncited by 81
  19. 2019Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspectivecited by 73
  20. 2019k-hop Graph Neural Networkscited by 57
  21. 2020Spatio-Temporal Graph Convolution for Resting-State fMRI Analysiscited by 57
  22. 2017Learning Graph-Level Representation for Drug Discoverycited by 43
  23. 2018Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunitiescited by 43
  24. 2017Spectral Graph Convolutions for Population-based Disease Predictioncited by 42
  25. 2020Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysiscited by 41
  26. 2019InceptionGCN: Receptive Field Aware Graph Convolutional Network for Disease Predictioncited by 39
  27. 2020Latent-Graph Learning for Disease Predictioncited by 39
  28. 2018Graph Neural Networks for IceCube Signal Classificationcited by 24
  29. 2020Deep Graph Normalizer: A Geometric Deep Learning Approach for Estimating Connectional Brain Templatescited by 16
  30. 2021Graph Kernel Neural Networkscited by 13
  31. 2020Deep Representation Learning For Multimodal Brain Networkscited by 12
  32. 2018Self-Attention Equipped Graph Convolutions for Disease Predictioncited by 11
  33. 2021Partition and Code: learning how to compress graphscited by 10
  34. 2021MGN-Net: a multi-view graph normalizer for integrating heterogeneous biological network populationscited by 8
  35. 2021Non-isomorphic Inter-modality Graph Alignment and Synthesis for Holistic Brain Mappingcited by 8
  36. 2019DS-GCNs: Connectome Classification Using Dynamic Spectral Graph Convolution Networks with Assistant Task Trainingcited by 6
  37. 2020Simultaneous imputation and disease classification in incomplete medical datasets using Multigraph Geometric Matrix Completion (MGMC)cited by 6
  38. 2018Multi-modal Disease Classification in Incomplete Datasets Using Geometric Matrix Completioncited by 5

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2024MM-GTUNets: Unified Multi-Modal Graph Deep Learning for Brain Disorders Predictioncited by 9
  2. 2025Heterogeneous Graph Structure Learning through the Lens of Data-generating Processescited by 2
  3. 2025Rethinking Graph Super-resolution: Dual Frameworks for Topological Fidelitycited by 0
  4. 2026Incremental Graph Construction Enables Robust Spectral Clustering of Textscited by 0