PANE: scalable and effective attributed network embedding
نویسندگان
چکیده
Given a graph G where each node is associated with set of attributes, attributed network embedding (ANE) maps v in to compact vector Xv, which can be used downstream machine learning tasks. Ideally, Xv should capture v's affinity attribute, considers not only own attribute associations, but also those its connected nodes along edges G. It challenging obtain high-utility embeddings that enable accurate predictions; scaling effective ANE computation massive graphs pushes the difficulty problem whole new level. Existing solutions largely fail on such graphs, leading prohibitive costs, low-quality embeddings, or both. This paper proposes PANE, an and scalable approach for achieves state-of-the-art result quality multiple benchmark datasets. PANE obtains high scalability effectiveness through 3 main algorithmic designs. First, it formulates objective based novel random walk model networks. Second, includes highly efficient solver above optimization problem, whose key module carefully designed initialization drastically reduces number iterations required converge. Finally, utilizes multi-core CPUs non-trivial parallelization solver, while retaining resulting embeddings. The performance depends upon attributes input network. To handle large networks numerous we further extend PANE++. Extensive experiments, comparing 10 existing approaches 8 real datasets, demonstrate PANE++ consistently outperform all methods terms quality, being orders magnitude faster.
منابع مشابه
Attributed Social Network Embedding
Embedding network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification and entity retrieval. However, most existing methods focused only on leveraging network structure. For social networks, besides the network structure, there also exists rich information about social actors, such as user profiles of friendship n...
متن کاملAccelerated Attributed Network Embedding
Network embedding is to learn low-dimensional vector representations for nodes in a network. It has shown to be effective in a variety of tasks such as node classification and link prediction. While embedding algorithms on pure networks have been intensively studied, in many real-world applications, nodes are often accompanied with a rich set of attributes or features, aka attributed networks. ...
متن کاملScalable Action Respecting Embedding
ARE is a non-linear dimensionality reduction technique for embedding observation trajectories, which captures state dynamics that traditional methods do not. The core of ARE is a semidefinite optimization with constraints requiring actions to be distance-preserving in the resulting embedding. Unfortunately, these constraints are quadratic in number and non-local (making recent scaling tricks in...
متن کاملScalable Anomaly Ranking of Attributed Neighborhoods
Abstract Given a graph with node attributes, what neighborhoods1 are anomalous? To answer this question, one needs a quality score that utilizes both structure and attributes. Popular existing measures either quantify the structure only and ignore the attributes (e.g., conductance), or only consider the connectedness of the nodes inside the neighborhood and ignore the cross-edges at the boundar...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Vldb Journal
سال: 2023
ISSN: ['0949-877X', '1066-8888']
DOI: https://doi.org/10.1007/s00778-023-00790-4