{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-hierarchical-graph-neural-networks","title":"Learning Hierarchical Graph Neural Networks for Image Clustering","arxiv_id":"2107.01319","date":"2021-07-03","proceeding":"ICCV 2021 10","authors":["Yifan Xing","Tong He","Tianjun Xiao","Yongxin Wang","Yuanjun Xiong","Wei Xia","David Wipf","Zheng Zhang","Stefano Soatto"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2107.01319v2","url_pdf":"https://arxiv.org/pdf/2107.01319v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-hierarchical-graph-neural-networks","repo_url":"https://github.com/dmlc/dgl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"learning-hierarchical-graph-neural-networks","repo_url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/hilander","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"learning-hierarchical-graph-neural-networks","repo_url":"https://github.com/djordjened92/cca-gnnclust","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"face-clustering","task_name":"Face Clustering"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"image-clustering","task_name":"Image Clustering"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"hi-lander","method_name":"Hi-LANDER"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.01319","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}