mlsanityData to 7 Oct 2026

Learning Hierarchical Graph Neural Networks for Image Clustering

arXiv 2107.01319 ↗First posted 3 Jul 2021cs.CV cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities using a training set of images annotated with labels belonging to a disjoint set of identities. Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level. Unlike fully unsupervised hierarchical clustering, the choice of grouping and complexity criteria stems naturally from supervision in the training set. The resulting method, Hi-LANDER, achieves an average of 54% improvement in F-score and 8% increase in Normalized Mutual Information (NMI) relative to current GNN-based clustering algorithms. Additionally, state-of-the-art GNN-based methods rely on separate models to predict linkage probabilities and node densities as intermediate steps of the clustering process. In contrast, our unified framework achieves a seven-fold decrease in computational cost. We release our training and inference code at https://github.com/dmlc/dgl/tree/master/examples/pytorch/hilander.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 34 of its 64 references that are in the map. First posted on arXiv 3 Jul 2021.

Builds on

34 of 64 references.

References · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2017Billion-scale similarity search with GPUscited by 2,477
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  10. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  11. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  12. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
22 more
  1. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  2. 2018Additive Margin Softmax for Face Verificationcited by 275
  3. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 241
  4. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  5. 2018Graph-Based Global Reasoning Networkscited by 120
  6. 2020GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learningcited by 113
  7. 2020Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrievalcited by 98
  8. 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 96
  9. 2018The Devil of Face Recognition is in the Noisecited by 65
  10. 2017HARP: Hierarchical Representation Learning for Networkscited by 58
  11. 2019Linkage Based Face Clustering via Graph Convolution Networkcited by 55
  12. 2019Learning to Cluster Faces on an Affinity Graphcited by 50
  13. 2020Learning to Cluster Faces via Confidence and Connectivity Estimationcited by 42
  14. 2019Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Poolingcited by 30
  15. 2016Clustering Millions of Faces by Identitycited by 26
  16. 2018Multi-task Learning of Hierarchical Vision-Language Representationcited by 26
  17. 2018Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognitioncited by 20
  18. 2017A Proximity-Aware Hierarchical Clustering of Facescited by 12
  19. 2018Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondencescited by 11
  20. 2018Hierarchical Graph Clustering using Node Pair Samplingcited by 11
  21. 2020Improving Face Recognition by Clustering Unlabeled Faces in the Wildcited by 5
  22. 2020A Multiscale Graph Convolutional Network Using Hierarchical Clusteringcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 7; 2025: 5.

18 papers.

Sort:

  1. 2022Equivariant Graph Hierarchy-Based Neural Networkscited by 24
  2. 2024Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detectioncited by 8
  3. 2023Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarizationcited by 6
  4. 2023VertexSerum: Poisoning Graph Neural Networks for Link Inferencecited by 5
  5. 2022FaceMap: Towards Unsupervised Face Clustering via Map Equationcited by 3
  6. 2025Hierarchical Material Recognition from Local Appearancecited by 3
  7. 2023Hierarchical Graph Pattern Understanding for Zero-Shot VOScited by 2
  8. 2023Learning for Transductive Threshold Calibration in Open-World Recognitioncited by 1
  9. 2024End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarizationcited by 1
  10. 2025Generalized Category Discovery under the Long-Tailed Distributioncited by 1
  11. 2024Holistically-Nested Structure-Aware Graph Neural Network for Road Extractioncited by 0
  12. 2024Spectral Graph Reasoning Network for Hyperspectral Image Classificationcited by 0
6 more
  1. 2024Graph-Boosted Attentive Network for Semantic Body Parsingcited by 0
  2. 2024Graph Clustering with Cross-View Feature Propagationcited by 0
  3. 2024Cross-Camera Data Association via GNN for Supervised Graph Clusteringcited by 0
  4. 2025ConstellationNet: Reinventing Spatial Clustering through GNNscited by 0
  5. 2025DECOR: Deep Embedding Clustering with Orientation Robustnesscited by 0
  6. 2025Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)cited by 0