Embedding social network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification, node clustering, link prediction and network visualization. However, the information contained in these vector embeddings remains abstract and hard to interpret. Methods for inspecting embeddings usually rely on visualization methods, which do not work on a larger scale and do not give concrete interpretations of vector embeddings in terms of preserved network properties (e.g., centrality or betweenness measures). In this paper, we study and investigate network properties preserved by recent random walk-based embedding procedures like node2vec, DeepWalk or LINE. We propose a method that applies learning to rank in order to relate embeddings to network centralities. We evaluate our approach with extensive experiments on real-world and artificial social networks. Experiments show that each embedding method learns different network properties. In addition, we show that our graph embeddings in combination with neural networks provide a computationally efficient way to approximate the Closeness Centrality measure in social networks.
Computing shortest path distances between nodes lies at the heart of many graph algorithms and applications. Traditional exact methods such as breadth-first-search (BFS) do not scale up to contemporary, rapidly evolving today's massive networks. Therefore, it is required to find approximation methods to enable scalable graph processing with a significant speedup. In this paper, we utilize vector embeddings learnt by deep learning techniques to approximate the shortest paths distances in large graphs. We show that a feedforward neural network fed with embeddings can approximate distances with relatively low distortion error. The suggested method is evaluated on the Facebook, BlogCatalog, Youtube and Flickr social networks.
Online social networks (OSNs) are websites that allow users to build connections and relationships to other Internet users. Social networks store information remotely, rather than on a user's personal computer. They can be used to keep in touch with friends, make new contacts and find people with similar interests and ideas. Nowadays the popularity of online social networks is growing rapidly. Many people besides friends and acquaintances are interested in the information people post on social networks. Identity thieves, scam artists, debt collectors, stalkers, and corporations looking for a market advantage are using social networks to gather information about consumers. Companies that operate social networks are themselves collecting a variety of data about their users, both to personalize the services for the users and to sell to advertisers. The concern of leakage of privacy and security is extremely growing in social networks in these days .The identity theft attacks (ICAs) by creating clone identities in OSNs try to steal users' personal information and nowadays it is very important in cyberspace. If no protection mechanism is applied it effects on users' activity, trust and reliance relations that establish with other users. In this paper, first profile cloning and identity theft attack are introduced, and then a framework for detection suspicious identity is proposed. This approach is based on attribute similarity and friend network similarity. According to similarity measures which are computed in each step and by having predetermined threshold, it will be decided which profile is clone which one is genuine.
Graph embedding has recently gained momentum in the research community, in particular after the introduction of random walk and neural network based approaches. However, most of the embedding approaches focus on representing the local neighborhood of nodes and fail to capture the global graph structure, i.e. to retain the relations to distant nodes. To counter that problem, we propose a novel extension to random walk based graph embedding, which removes a percentage of least frequent nodes from the walks at different levels. By this removal, we simulate farther distant nodes to reside in the close neighborhood of a node and hence explicitly represent their connection. Besides the common evaluation tasks for graph embeddings, such as node classification and link prediction, we evaluate and compare our approach against related methods on shortest path approximation. The results indicate, that extensions to random walk based methods (including our own) improve the predictive performance only slightly -if at all.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.