# Learning Hierarchical Graph Neural Networks for Image Clustering

arXiv: https://arxiv.org/abs/2107.01319 · HTML: https://mlsanity.com/paper/2107.01319/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 64 references that are in the map.
- First posted on arXiv 3 Jul 2021.

## Builds on (most cited first, 30 of 34)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [Learning a Neural Solver for Multiple Object Tracking](https://mlsanity.com/paper/1912.07515/) (2019)
- [Graph-Based Global Reasoning Networks](https://mlsanity.com/paper/1811.12814/) (2018)
- [GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning](https://mlsanity.com/paper/2006.07327/) (2020)
- [Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval](https://mlsanity.com/paper/2007.12163/) (2020)
- [Efficient Parameter-free Clustering Using First Neighbor Relations](https://mlsanity.com/paper/1902.11266/) (2019)
- [The Devil of Face Recognition is in the Noise](https://mlsanity.com/paper/1807.11649/) (2018)
- [HARP: Hierarchical Representation Learning for Networks](https://mlsanity.com/paper/1706.07845/) (2017)
- [Linkage Based Face Clustering via Graph Convolution Network](https://mlsanity.com/paper/1903.11306/) (2019)
- [Learning to Cluster Faces on an Affinity Graph](https://mlsanity.com/paper/1904.02749/) (2019)
- [Learning to Cluster Faces via Confidence and Connectivity Estimation](https://mlsanity.com/paper/2004.00445/) (2020)
- [Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling](https://mlsanity.com/paper/1910.11436/) (2019)
- [Clustering Millions of Faces by Identity](https://mlsanity.com/paper/1604.00989/) (2016)
- [Multi-task Learning of Hierarchical Vision-Language Representation](https://mlsanity.com/paper/1812.00500/) (2018)
- [Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition](https://mlsanity.com/paper/1809.01407/) (2018)
- [A Proximity-Aware Hierarchical Clustering of Faces](https://mlsanity.com/paper/1703.04835/) (2017)

## Built on by (most cited first, 18 of 18)

- [Equivariant Graph Hierarchy-Based Neural Networks](https://mlsanity.com/paper/2202.10643/) (2022)
- [Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection](https://mlsanity.com/paper/2412.15668/) (2024)
- [Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization](https://mlsanity.com/paper/2302.12716/) (2023)
- [VertexSerum: Poisoning Graph Neural Networks for Link Inference](https://mlsanity.com/paper/2308.01469/) (2023)
- [FaceMap: Towards Unsupervised Face Clustering via Map Equation](https://mlsanity.com/paper/2203.10090/) (2022)
- [Hierarchical Material Recognition from Local Appearance](https://mlsanity.com/paper/2505.22911/) (2025)
- [Hierarchical Graph Pattern Understanding for Zero-Shot VOS](https://mlsanity.com/paper/2312.09525/) (2023)
- [Learning for Transductive Threshold Calibration in Open-World Recognition](https://mlsanity.com/paper/2305.12039/) (2023)
- [End-to-End Supervised Hierarchical Graph Clustering for Speaker Diarization](https://mlsanity.com/paper/2401.12850/) (2024)
- [Generalized Category Discovery under the Long-Tailed Distribution](https://mlsanity.com/paper/2506.12515/) (2025)
- [Holistically-Nested Structure-Aware Graph Neural Network for Road Extraction](https://mlsanity.com/paper/2407.02639/) (2024)
- [Spectral Graph Reasoning Network for Hyperspectral Image Classification](https://mlsanity.com/paper/2407.02647/) (2024)
- [Graph-Boosted Attentive Network for Semantic Body Parsing](https://mlsanity.com/paper/2407.05924/) (2024)
- [Graph Clustering with Cross-View Feature Propagation](https://mlsanity.com/paper/2408.06029/) (2024)
- [Cross-Camera Data Association via GNN for Supervised Graph Clustering](https://mlsanity.com/paper/2410.00643/) (2024)
- [ConstellationNet: Reinventing Spatial Clustering through GNNs](https://mlsanity.com/paper/2503.07643/) (2025)
- [DECOR: Deep Embedding Clustering with Orientation Robustness](https://mlsanity.com/paper/2510.03328/) (2025)
- [Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)](https://mlsanity.com/paper/2511.09211/) (2025)

## 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.