{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-network-embedding-for-graph","title":"Deep Network Embedding for Graph Representation Learning in Signed Networks","arxiv_id":"1901.01718","date":"2019-01-07","proceeding":null,"authors":["Xiao Shen","Fu-Lai Chung"],"abstract":"Network embedding has attracted an increasing attention over the past few\nyears. As an effective approach to solve graph mining problems, network\nembedding aims to learn a low-dimensional feature vector representation for\neach node of a given network. The vast majority of existing network embedding\nalgorithms, however, are only designed for unsigned networks, and the signed\nnetworks containing both positive and negative links, have pretty distinct\nproperties from the unsigned counterpart. In this paper, we propose a deep\nnetwork embedding model to learn the low-dimensional node vector\nrepresentations with structural balance preservation for the signed networks.\nThe model employs a semi-supervised stacked auto-encoder to reconstruct the\nadjacency connections of a given signed network. As the adjacency connections\nare overwhelmingly positive in the real-world signed networks, we impose a\nlarger penalty to make the auto-encoder focus more on reconstructing the scarce\nnegative links than the abundant positive links. In addition, to preserve the\nstructural balance property of signed networks, we design the pairwise\nconstraints to make the positively connected nodes much closer than the\nnegatively connected nodes in the embedding space. Based on the network\nrepresentations learned by the proposed model, we conduct link sign prediction\nand community detection in signed networks. Extensive experimental results in\nreal-world datasets demonstrate the superiority of the proposed model over the\nstate-of-the-art network embedding algorithms for graph representation learning\nin signed networks.","url_abs":"http://arxiv.org/abs/1901.01718v1","url_pdf":"http://arxiv.org/pdf/1901.01718v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-network-embedding-for-graph","repo_url":"https://github.com/shenxiaocam/Deep-network-embedding-for-graph-representation-learning-in-signed-networks","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"community-detection","task_name":"Community Detection"},{"task_slug":"graph-mining","task_name":"Graph Mining"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"link-sign-prediction","task_name":"Link Sign Prediction"},{"task_slug":"network-embedding","task_name":"Network Embedding"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.01718","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}