2019/12/17 by Artem Lutov, Lutov, Artem, Dingqi Yang +3
Computer Science · Neuroscience · Physics and Astronomy · #05C60 (Primary) #05C85 (Secondary) #14E25 #30L05 #54C25 #57N35 #62G35 (Secondary) #68T30 (Secondary) #91C20 (Secondary) #91D30 (Secondary) #Advanced Graph Neural Networks #Complex Network Analysis Techniques #E.1 #F.2.2 #FOS: Computer and information sciences #Functional Brain Connectivity Studies #H.3.4 #I.2.6 #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.1912.08808
openalex publication_date 2019/12/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Graph embedding has become a key component of many data mining and analysis\nsystems. Current graph embedding approaches either sample a large number of\nnode pairs from a graph to learn node embeddings via stochastic optimization or\nfactorize a high-order proximity/adjacency matrix of the graph via\ncomputationally expensive matrix factorization techniques. These approaches\ntypically require significant resources for the learning process and rely on\nmultiple parameters, which limits their applicability in practice. Moreover,\nmost of the existing graph embedding techniques operate effectively in one\nspecific metric space only (e.g., the one produced with cosine similarity), do\nnot preserve higher-order structural features of the input graph and cannot\nautomatically determine a meaningful number of embedding dimensions. Typically,\nthe produced embeddings are not easily interpretable, which complicates further\nanalyses and limits their applicability. To address these issues, we propose\nDAOR, a highly efficient and parameter-free graph embedding technique producing\nmetric space-robust, compact and interpretable embeddings without any manual\ntuning. Compared to a dozen state-of-the-art graph embedding algorithms, DAOR\nyields competitive results on both node classification (which benefits form\nhigh-order proximity) and link prediction (which relies on low-order proximity\nmostly). Unlike existing techniques, however, DAOR does not require any\nparameter tuning and improves the embeddings generation speed by several orders\nof magnitude. Our approach has hence the ambition to greatly simplify and speed\nup data analysis tasks involving graph representation learning.\n