HARP: Hierarchical Representation Learning for Networks

Chen, Haochen; Perozzi, Bryan; Hu, Yifan; Skiena, Steven

doi:10.48550/arxiv.1706.07845

Cited by 44 publications

(26 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, our hierarchy is formed by multiple k-NN graphs recurrently built with clustering and node aggregation, which are learnt from the meta-training set. Hierarchical representation has also been explored in the graph representation learning literature [63,9,4,19,18,26]. There, the focus is to learn a stronger feature representation to classify graph [63] or input nodes [18] into a closed set of class labels.…”

Section: Related Work and Contributionsmentioning

confidence: 99%

Learning Hierarchical Graph Neural Networks for Image Clustering

Xing¹,

Xiao

et al. 2021

Preprint

View full text Add to dashboard Cite

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, stateof-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 here.

show abstract

Section: Related Work and Contributionsmentioning

confidence: 99%

Learning Hierarchical Graph Neural Networks for Image Clustering

Xing¹,

Xiao

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…There are number of other studies which considers context of links and nodes (Tu, Liu, Liu, & Sun, 2017), node attributes (Huang, Li, & Hu, 2017); or focuses on developing a meta-strategy (Chen, Perozzi, Hu, & Skiena, 2017). On the other hand, Tu, Zhang, Liu & Sun (2016) and Wang, Cui, & Zhu (2016) develop semi-supervised representation learning algorithms.…”

Section: Related Workmentioning

confidence: 99%

Predicting Diffusion Reach Probabilities via Representation Learning on Social Networks

Gursoy¹,

Durahim²

2019

View full text Add to dashboard Cite

Diffusion reach probability between two nodes on a network is defined as the probability of a cascade originating from one node reaching to another node. An infinite number of cascades would enable calculation of true diffusion reach probabilities between any two nodes. However, there exists only a finite number of cascades and one usually has access only to a small portion of all available cascades. In this work, we addressed the problem of estimating diffusion reach probabilities given only a limited number of cascades and partial information about underlying network structure. Our proposed strategy employs node representation learning to generate and feed node embeddings into machine learning algorithms to create models that predict diffusion reach probabilities. We provide experimental analysis using synthetically generated cascades on two real-world social networks. Results show that proposed method is superior to using values calculated from available cascades when the portion of cascades is small.

show abstract

“…Closely related to our model, HARP [33] first coarsens the graph, and after that, the new graph consists of supernodes. Afterward, network embedding methods are applied to learn the representations of supernodes, and then with the learned representation as the initial value of the supernodes' constituent nodes, the embedding methods are run over finer-grained subgraphs again.…”

Section: Network Representation Learningmentioning

confidence: 99%

“…HARP [33] and MILE [34] have used Graph Coarsening to find a smaller network which approximates the global structure of its input and learn coarse embeddings from the small network, which serve as good initializations for learning representation in the input network. Graph Coarsening coarsens a network without counting the number of origin nodes that belong to a coarsen group.…”

Section: Graph Partitioningmentioning

confidence: 99%

COSINE: Compressive Network Embedding on Large-scale Information Networks

Zhang

Yang

Liu

et al. 2018

Preprint

View full text Add to dashboard Cite

There is recently a surge in approaches that learn low-dimensional embeddings of nodes in networks. As there are many large-scale real-world networks, it's inefficient for existing approaches to store amounts of parameters in memory and update them edge after edge. With the knowledge that nodes having similar neighborhood will be close to each other in embedding space, we propose COSINE (COmpresSIve NE) algorithm which reduces the memory footprint and accelerates the training process by parameters sharing among similar nodes. COSINE applies graph partitioning algorithms to networks and builds parameter sharing dependency of nodes based on the result of partitioning. With parameters sharing among similar nodes, COSINE injects prior knowledge about higher structural information into training process which makes network embedding more efficient and effective. COSINE can be applied to any embedding lookup method and learn high-quality embeddings with limited memory and shorter training time. We conduct experiments of multi-label classification and link prediction, where baselines and our model have the same memory usage. Experimental results show that COSINE gives baselines up to 23% increase on classification and up to 25% increase on link prediction. Moreover, time of all representation learning methods using COSINE decreases from 30% to 70%.

show abstract

HARP: Hierarchical Representation Learning for Networks

Cited by 44 publications

References 5 publications

Learning Hierarchical Graph Neural Networks for Image Clustering

Learning Hierarchical Graph Neural Networks for Image Clustering

Predicting Diffusion Reach Probabilities via Representation Learning on Social Networks

COSINE: Compressive Network Embedding on Large-scale Information Networks

Contact Info

Product

Resources

About