Large-Scale Embedding Learning in Heterogeneous Event Data
By Huan Gui, Jialu Liu, Fangbo Tao, Meng Jiang, Brandon Norick, Jiawei Han. 2016
88 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Kevin Chen-Chuan Chang
- Vincent Wenchen Zheng
- Jie Yang
- Hongyun Cai
- Philippe Cudré-Mauroux
- Wang-Chien Lee
- Yejin Bang
- Tao-Yang Fu
In Statistical and Nonlinear Physics
- Philippe Cudré-Mauroux
- Kevin Chen-Chuan Chang
- Vincent Wenchen Zheng
- Dingqi Yang
- Bingqing Qu
- Jie Yang
- Hongyun Cai
- Wang-Chien Lee
Citations in the corpus
- A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “dimensional vector. Node classification is conducted by applying a classifier on the set of labelled node embedding for training. The example classifiers include SVM ( [1], [20], [33], [34], [41], [42], [45], [56], [57], [60], [73], [75], [81], [87]), logistic regression ( [1], [17], [19], [20], [21], ”
- Revisiting User Mobility and Social Relationships in LBSNs: A Hypergraph Embedding Approach (2019, background): “• LINE [29] explicitly defines 1st and 2nd-order node proximity embeddings of dimension d , it first learns two sets of d / 2-dimension • HEBE [14] learns node embeddings for heterogeneous event data using tensor modeling, where a heterogeneous hyper-edge • (S) : Only the Social network is considere”
- A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, unknown): “HEBE [67] is another hyperedge-based method, which aims to maximize the proximity between the node and the hyperedge it belongs to.”
- Regions, Periods, Activities: Uncovering Urban Dynamics via Cross-Modal Representation Learning (2017, unknown): “graph nodes [29, 33, 32], and heterogeneous events [12].”
- HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning (2017, background): “There are also several existing works on representation learning in HINs [8, 11, 13, 25, 27].”
- High-Dimension Human Value Representation in Large Language Models (2024, background): “In parallel, computer vision benefited from embedding techniques to capture object representations [65, 66, 67], with recent expansions into sub-object embeddings [68] demonstrating the approach’s versatility.”