Gradient-free Algorithms for Graph Embedding

Qu, Liang; Shi, Yuhui

10.1109/CEC.2019.8790139

2019

978-1-7281-2154-3

2019 IEEE Congress on Evolutionary Computation, CEC 2019

2746-2752

10-13 June 2019

Wellington, New zealand

345 E 47TH ST, NEW YORK, NY 10017 USA

Institute of Electrical and Electronics Engineers Inc.

Graph-based data are very ubiquitous in many real-world scenarios, and it is usually difficult to mine valuable information from the large scale graphs because of traditional sparse and high-dimension representations of nodes in the graphs. To address this issue, the graph embedding techniques which aim to map the nodes of the graph into a low-dimension dense vector space are proposed. These vectors can act as the features of nodes for many graph analytics tasks. However, most existing graph embedding algorithms highly rely on gradient information, which largely restricts the flexibility and universality of algorithms and easily reaches local optimum. In this paper, we propose a general and flexible gradient-free (e.g. particle swarm optimization and differential evolution) graph embedding algorithmic framework, which introduces how to apply gradient-free algorithms on graph embedding problems. Furthermore, the experiments on three large scale real-world network datasets for nodes classification and nodes multi-label classification tasks show that the gradient-free graph embedding algorithms can obtain promising results.
© 2019 IEEE.

gradient-free graph embedding particle swarm optimization differential evolution

第一 ; 通讯

英语

EI ; CPCI-S

Science and Technology Innovation Committee Foundation of Shenzhen[ZDSYS201703031748284]

Engineering ; Mathematical & Computational Biology

Engineering, Electrical & Electronic ; Mathematical & Computational Biology

WOS:000502087102098

20193507373867

Classification (of information) ; Embeddings ; Graphic methods ; Large dataset ; Particle swarm optimization (PSO) ; Vector spaces

Information Theory and Signal Processing:716.1 ; Computer Software, Data Handling and Applications:723 ; Mathematics:921 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4

EV Compendex

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China

Qu, Liang,Shi, Yuhui. Gradient-free Algorithms for Graph Embedding[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:Institute of Electrical and Electronics Engineers Inc.,2019:2746-2752.