Access the full text.
Sign up today, get DeepDyve free for 14 days.
M. Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, P. Vandergheynst (2016)
Geometric Deep Learning: Going beyond Euclidean dataIEEE Signal Process. Mag., 34
S. Bonnabel (2011)
Stochastic Gradient Descent on Riemannian ManifoldsIEEE Transactions on Automatic Control, 58
A. Ungar (2001)
Hyperbolic trigonometry and its application in the Poincaré ball model of hyperbolic geometryComputers & Mathematics With Applications, 41
Richard Wilson, E. Hancock, E. Pekalska, R. Duin (2014)
Spherical and Hyperbolic Embeddings of DataIEEE Transactions on Pattern Analysis and Machine Intelligence, 36
Jeffrey Lee, Jeffrey Marc Lee (2009)
Manifolds and Differential Geometry, Vol
Zhipeng Huang, N. Mamoulis (2017)
Heterogeneous Information Network Embedding for Meta Path based ProximityArXiv, abs/1701.05291
C. Shi, Binbin Hu, Wayne Zhao, Philip Yu (2017)
Heterogeneous Information Network Embedding for RecommendationIEEE Transactions on Knowledge and Data Engineering, 31
Daixin Wang, Peng Cui, Wenwu Zhu (2016)
Structural Deep Network EmbeddingProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Binbin Hu, C. Shi, Wayne Zhao, Philip Yu (2018)
Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention ModelProceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
M. Law, Renjie Liao, Jake Snell, R. Zemel (2019)
Lorentzian Distance Learning for Hyperbolic Representations
(2011)
Proceedings of the 2nd International Workshop on Information Heterogeneity and Fusion in Recommender Systems, HetRec '11, Chicago, Illinois, USA, October 27, 2011
Junshan Wang, Zhicong Lu, Guojie Song, Yue Fan, Lun Du, Wei Lin (2019)
Tag2Vec: Learning Tag Representations in Tag NetworksThe World Wide Web Conference
Jian Tang, Meng Qu, Q. Mei (2015)
PTE: Predictive Text Embedding through Large-scale Heterogeneous Text NetworksProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
A. Ungar (2009)
A Gyrovector Space Approach to Hyperbolic Geometry
Lawrence Hubert, Phipps Arabie (1985)
Comparing partitionsJournal of Classification, 2
Frederic Sala, Chris De Sa, Albert Gu, Christopher Re (2018)
Representation tradeoffs for hyperbolic embeddingsProceedings of the 35th International Conference on Machine Learning
Bhuwan Dhingra, Christopher Shallue, Mohammad Norouzi, Andrew Dai, George Dahl (2018)
Embedding Text in Hyperbolic Spaces
O. Ganea, Gary Bécigneul, Thomas Hofmann (2018)
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
Hongxu Chen, Hongzhi Yin, Weiqing Wang, Hao Wang, Quoc Nguyen, Xue Li (2018)
PME: Projected Metric Embedding on Heterogeneous Networks for Link PredictionProceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Tomas Mikolov, I. Sutskever, Kai Chen, G. Corrado, J. Dean (2013)
Distributed Representations of Words and Phrases and their Compositionality
M. Belkin, P. Niyogi (2001)
Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering
Peng Cui, Xiao Wang, J. Pei, Wenwu Zhu (2017)
A Survey on Network EmbeddingIEEE Transactions on Knowledge and Data Engineering, 31
Yizhou Sun, Jiawei Han, Xifeng Yan, Philip Yu, Tianyi Wu (2011)
PathSim: Meta Path-Based Top-K Similarity Search in Heterogeneous Information NetworksProc. VLDB Endow., 4
Yu Shi, Qi Zhu, Fang Guo, Chao Zhang, Jiawei Han (2018)
Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information NetworksProceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
C. Shi, Yitong Li, Jiawei Zhang, Yizhou Sun, Philip Yu (2015)
A Survey of Heterogeneous Information Network AnalysisIEEE Transactions on Knowledge and Data Engineering, 29
Linchuan Xu, Xiaokai Wei, Jiannong Cao, Philip Yu (2017)
Embedding of Embedding (EOE): Joint Embedding for Coupled Heterogeneous NetworksProceedings of the Tenth ACM International Conference on Web Search and Data Mining
Frederic Sala, Christopher Sa, Albert Gu, Christopher Ré (2018)
Representation Tradeoffs for Hyperbolic EmbeddingsProceedings of machine learning research, 80
Silvere Bonnabel (2013)
Stochastic gradient descent on riemannian manifoldsStochastic gradient descent on riemannian manifolds.IEEE Transactions on Automatic Control, 58
Zhicheng He, Jie Liu, Na Li, Yalou Huang (2019)
Learning Network-to-Network Model for Content-rich Network EmbeddingProceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Hongwei Wang, Fuzheng Zhang, Min Hou, Xing Xie, M. Guo, Qi Liu (2017)
SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link PredictionProceedings of the Eleventh ACM International Conference on Web Search and Data Mining
Maximilian Nickel, Douwe Kiela (2017)
Poincaré Embeddings for Learning Hierarchical RepresentationsArXiv, abs/1705.08039
Shiyu Chang, Wei Han, Jiliang Tang, Guo-Jun Qi, C. Aggarwal, Thomas Huang (2015)
Heterogeneous Network Embedding via Deep ArchitecturesProceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
M. Cugmas, A. Ferligoj (2015)
On comparing partitionsInternational Federation of Classification Societies
Bryan Perozzi, Rami Al-Rfou, S. Skiena (2014)
DeepWalk: online learning of social representationsProceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining
David Gu (1996)
HYPERBOLIC GEOMETRY
Maximilian Nickel, Douwe Kiela (2018)
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic GeometryArXiv, abs/1806.03417
(2011)
2nd workshop on information heterogeneity and fusion in recommender systems
Tao-yang Fu, Wang-Chien Lee, Zhen Lei (2017)
HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation LearningProceedings of the 2017 ACM on Conference on Information and Knowledge Management
Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, Q. Mei (2015)
LINE: Large-scale Information Network EmbeddingProceedings of the 24th International Conference on World Wide Web
David McDonald, Shan He (2019)
HEAT: Hyperbolic Embedding of Attributed NetworksArXiv, abs/1903.03036
Dmitri Krioukov, Fragkiskos Papadopoulos, M. Kitsak, Amin Vahdat, M. Boguñá (2010)
Hyperbolic Geometry of Complex NetworksPhysical review. E, Statistical, nonlinear, and soft matter physics, 82 3 Pt 2
M. Balasubramanian, E. Schwartz (2002)
The isomap algorithm and topological stability.Science, 295 5552
Yuxiao Dong, N. Chawla, A. Swami (2017)
metapath2vec: Scalable Representation Learning for Heterogeneous NetworksProceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
S. Helgason (1978)
Differential Geometry, Lie Groups, and Symmetric Spaces
Aditya Grover, J. Leskovec (2016)
node2vec: Scalable Feature Learning for NetworksProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Tom Fawcett (2006)
An introduction to ROC analysisPattern Recognit. Lett., 27
Xiaotian Han, C. Shi, Senzhang Wang, Philip Yu, L. Song (2018)
Aspect-Level Deep Collaborative Filtering via Heterogeneous Information Networks
Ivana Balazevic, Carl Allen, Timothy Hospedales (2019)
Multi-relational Poincaré Graph Embeddings
Ryota Suzuki, Ryusuke Takahama, Shunzo Onoda (2019)
Hyperbolic Disk Embeddings for Directed Acyclic Graphs
Ke Tu, Jianxin Ma, Peng Cui, J. Pei, Wenwu Zhu (2019)
AutoNE: Hyperparameter Optimization for Massive Network EmbeddingProceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
J. Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, Jie Tang (2017)
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vecProceedings of the Eleventh ACM International Conference on Web Search and Data Mining
Iván Cantador, Peter Brusilovsky, Tsvi Kuflik (2011)
2nd workshop on information heterogeneity and fusion in recommender systems (HetRec 2011)Proceedings of the 5th ACM Conference on Recommender Systems.
A. Ungar (2008)
Analytic Hyperbolic Geometry and Albert Einstein's Special Theory of Relativity
Heterogeneous information network (HIN) embedding, aiming to project HIN into a low-dimensional space, has attracted considerable research attention. Most of the existing HIN embedding methods focus on preserving the inherent network structure and semantic correlations in Euclidean spaces. However, one fundamental problem is whether the Euclidean spaces are the intrinsic spaces of HIN? Recent researches find the complex network with hyperbolic geometry can naturally reflect some properties, e.g., hierarchical and power-law structure. In this article, we make an effort toward embedding HIN in hyperbolic spaces. We analyze the structures of three HINs and discover some properties, e.g., the power-law distribution, also exist in HINs. Therefore, we propose a novel HIN embedding model HHNE. Specifically, to capture the structure and semantic relations between nodes, HHNE employs the meta-path guided random walk to sample the sequences for each node. Then HHNE exploits the hyperbolic distance as the proximity measurement. We also derive an effective optimization strategy to update the hyperbolic embeddings iteratively. Since HHNE optimizes different relations in a single space, we further propose the extended model HHNE++. HHNE++ models different relations in different spaces, which enables it to learn complex interactions in HINs. The optimization strategy of HHNE++ is also derived to update the parameters of HHNE++ in a principle manner. The experimental results demonstrate the effectiveness of our proposed models.
ACM Transactions on Knowledge Discovery from Data (TKDD) – Association for Computing Machinery
Published: Sep 4, 2021
Keywords: Heterogeneous information network
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.