A Graph Embedding Technique for Weighted Graphs Based on LSTM Autoencoders
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
A graph is a data structure consisting of nodes and edges between these nodes. Graph embedding is to generatea low dimensional vector for a given graph that best represents the characteristics of the graph. Recently, therehave been studies on graph embedding, especially using deep learning techniques. However, until now, mostdeep learning-based graph embedding techniques have focused on unweighted graphs. Therefore, in this paper,we propose a graph embedding technique for weighted graphs based on long short-term memory (LSTM)autoencoders. Given weighted graphs, we traverse each graph to extract node-weight sequences from the graph. Each node-weight sequence represents a path in the graph consisting of nodes and the weights between thesenodes. We then train an LSTM autoencoder on the extracted node-weight sequences and encode each nodeweightsequence into a fixed-length vector using the trained LSTM autoencoder. Finally, for each graph, wecollect the encoding vectors obtained from the graph and combine them to generate the final embedding vectorfor the graph. These embedding vectors can be used to classify weighted graphs or to search for similarweighted graphs. The experiments on synthetic and real datasets show that the proposed method is effective inmeasuring the similarity between weighted graphs.
Abstract
A graph is a data structure consisting of nodes and edges between these nodes. Graph embedding is to generatea low dimensional vector for a given graph that best represents the characteristics of the graph. Recently, therehave been studies on graph embedding, especially using deep learning techniques. However, until now, mostdeep learning-based graph embedding techniques have focused on unweighted graphs. Therefore, in this paper,we propose a graph embedding technique for weighted graphs based on long short-term memory (LSTM)autoencoders. Given weighted graphs, we traverse each graph to extract node-weight sequences from the graph. Each node-weight sequence represents a path in the graph consisting of nodes and the weights between thesenodes. We then train an LSTM autoencoder on the extracted node-weight sequences and encode each nodeweightsequence into a fixed-length vector using the trained LSTM autoencoder. Finally, for each graph, wecollect the encoding vectors obtained from the graph and combine them to generate the final embedding vectorfor the graph. These embedding vectors can be used to classify weighted graphs or to search for similarweighted graphs. The experiments on synthetic and real datasets show that the proposed method is effective inmeasuring the similarity between weighted graphs.
참고문헌 (19)
- M. J. J. Ghrabat, "An effective image retrieval based on optimized genetic algorithm utilized a novel SVM-based convolutional neural network classifier", Human-centric Computing and Information Sciences, 9, pp.31~ (2019)
- 이대원, "Future Trends of AI-based Smart Systems and Services: Challenges, Opportunities, and Solutions", JIPS(Journal of Information Processing Systems), 15(4), pp.717~723 (2019), 한국정보처리학회[DOI]
- E. Gultepe, "Improving clustering performance using independent component analysis and unsupervised feature learning", Human-centric Computing and Information Sciences, 8, pp.25~ (2018)
- H. Cai, "A comprehensive survey of graph embedding : problems, techniques, and applications", IEEE Transactions on Knowledge and Data Engineering, 30(9), pp.1616~1637 (2018)
- P. Goyal, "Graph embedding techniques, applications, and performance : a survey", Knowledge-Based Systems, 151, pp.78~94 (2018)
- S. V. N. Vishwanathan, "Graph kernels", Journal of Machine Learning Research, 11, pp.1201~1242 (2010)
- F. Scarselli, "The graph neural network model", IEEE Transactions on Neural Networks, 20(1), pp.61~80 (2009)
- T. N. Kipf, "Semi-supervised classification with graph convolutional networks", Proceedings of International Conference on Learning Representations (ICLR) (2017)
- A. Taheri, "Learning graph representations with recurrent neural network autoencoders", Proceedings of the 24th ACM SIGKDD Conference of Knowledge Discovery and Data Mining: Deep Learning Day (2018)
- P. Yanardag, "Deep graph kernels", Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.1364~1374 (2015)
- A. Narayanan, "graph2vec : learning distributed representations of graphs", Proceedings of 13th International Workshop on Mining and Learning with Graphs (MLG) (2017)
- Q. Le, "Distributed representations of sentences and documents", Proceedings of International Conference on Machine Learning, pp.1188~1196 (2014)
- "Efficient estimation of word representations in vector space" (2013)[URL]
- M. Seo, "A weighted graph embedding technique based on LSTM autoencoders", Proceedings of the Korea Software Congress (KSC) (2019)
- S. Hochreiter, "Long short-term memory", Neural computation, 9(8), pp.1735~1780 (1997)
- M. A. Kramer, "Nonlinear principal component analysis using autoassociative neural networks", AIChE Journal, 37(2), pp.233~243 (1991)
- Sayan Maity, "Multimodal Biometrics Recognition from Facial Video with Missing Modalities Using Deep Learning", JIPS(Journal of Information Processing Systems), 16(1), pp.6~29 (2020), 한국정보처리학회[DOI]
- A. Grover, "node2vec : scalable feature learning for networks", Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.855~864 (2016)
- "PubChem: an open chemistry database at the National Institutes of Health"[URL]