Corpus ID: 52178286

edge2vec: Learning Node Representation Using Edge Semantics

@article{Gao2018edge2vecLN,
  title={edge2vec: Learning Node Representation Using Edge Semantics},
  author={Zheng Gao and Gang Fu and Chunping Ouyang and Satoshi Tsutsui and Xiaozhong Liu and Ying Ding},
  journal={ArXiv},
  year={2018},
  volume={abs/1809.02269}
}
Representation learning for networks provides a new way to mine graphs. [...] Key Method An edge-type transition matrix is optimized from an Expectation-Maximization (EM) framework as an extra criterion of a biased node random walk on networks, and a biased skip-gram model is leveraged to learn node embeddings based on the random walks afterwards. edge2vec is validated and evaluated using three medical domain problems on an ensemble of complex medical networks (more than 10 node- \& edge- types): medical entity…Expand
Edge-Aware Graph Attention Network for Ratio of Edge-User Estimation in Mobile Networks
TLDR
This paper proposes an Edge-Aware Graph Attention Network (EAGAT), which is able to fuse the node features and edge features for REU estimation and demonstrates the superiority of the EAGAT approach to several state-of-the-art methods. Expand
Efficient personalized community detection via genetic evolution
TLDR
A genetic model including an offline and an online step is proposed to solve the personalized community detection task in an efficient way and outperforms the state-of-arts with significantly reduced running time. Expand
Identifying Illicit Accounts in Large Scale E-payment Networks - A Graph Representation Learning Approach
TLDR
This paper proposes an end-to-end Graph Convolution Network (GCN)-based algorithm to learn the embeddings of the nodes and edges of a large-scale time-evolving graph to detect abnormal/ suspicious financial transactions in real-world e-payment networks. Expand
A CPU-GPU hybrid algorithm for embedding large graphs
TLDR
This work proposes a hybrid CPU-GPU graph embedding algorithm that enables arbitrarily large graphs to be embedded using a single GPU even when the GPU’s memory capabilities fall short. Expand
AMAD: adversarial multiscale anomaly detection on high-dimensional and time-evolving categorical data
TLDR
A unified end-to-end approach to solve anomaly detection challenges by combining the advantages of Adversarial Autoencoder and Recurrent Neural Network is proposed, on which an enhanced two-resolution anomaly detector is developed for both instances and data blocks. Expand
Communities of support: social support exchange in a HIV online forum
  • Zheng Gao, Patrick C. Shih
  • Psychology
  • Proceedings of the Seventh International Symposium of Chinese CHI on - Chinese CHI '19
  • 2019
Analysis of social support in online forums for people living with HIV has been relying, for the most part, on self-report instrumentation and manual coding of data. Our study applies a fullyExpand
MERL: Multi-View Edge Representation Learning in Social Networks
TLDR
This paper proposes a new methodology, MERL, that captures asymmetry in multiple views by learning well-defined edge representations that are responsive to the difference between the source and destination node roles, and incorporates textual communications to identify multiple source of social signals that moderate the impact of different views between users. Expand

References

SHOWING 1-10 OF 34 REFERENCES
metapath2vec: Scalable Representation Learning for Heterogeneous Networks
TLDR
Two scalable representation learning models, namely metapath2vec and metapATH2vec++, are developed that are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, but also discern the structural and semantic correlations between diverse network objects. Expand
node2vec: Scalable Feature Learning for Networks
TLDR
In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods. Expand
Community-enhanced Network Representation Learning for Network Analysis
TLDR
This work proposes a novel NRL model by introducing community information of vertices to learn more discriminative network representations, named as Community-enhanced Network Representation Learning (CNRL). Expand
GraRep: Learning Graph Representations with Global Structural Information
TLDR
A novel model for learning vertex representations of weighted graphs that integrates global structural information of the graph into the learning process and significantly outperforms other state-of-the-art methods in such tasks. Expand
LINE: Large-scale Information Network Embedding
TLDR
A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures. Expand
An Empirical Study of Locally Updated Large-scale Information Network Embedding (LINE)
  • Yiwei Xu
  • Computer Science, Mathematics
  • 2017
TLDR
The novel network embedding method called the ''LINE'' is studied, which optimizes a carefully designed objective function that preserves both the local and global network structures and demonstrates the embeddings on several multi-label network classification tasks for social networks such as BlogCatalog and YouTube. Expand
Predicting drug target interactions using meta-path-based semantic network analysis
TLDR
The proposed framework has been demonstrated as a powerful alternative to SLAP in order to predict DTIs using the semantic network that integrates chemical, pharmacological, genomic, biological, functional, and biomedical information into a unified framework. Expand
Network representation learning: an overview
Networks are important ways of representing objects and their relationships. A key problem in the study of networks is how to represent the network information properly. With the developments inExpand
DeepWalk: online learning of social representations
TLDR
DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection. Expand
PathSim: Meta Path-Based Top-K Similarity Search in Heterogeneous Information Networks
TLDR
Under the meta path framework, a novel similarity measure called PathSim is defined that is able to find peer objects in the network (e.g., find authors in the similar field and with similar reputation), which turns out to be more meaningful in many scenarios compared with random-walk based similarity measures. Expand
...
1
2
3
4
...