GraPE: fast and scalable Graph Processing and Embedding

Abstract

Graph Representation Learning methods have enabled a wide range of learning problems to be addressed for data that can be represented in graph form. Nevertheless, several real world problems in economy, biology, medicine and other fields raised relevant scaling problems with existing methods and their software implementation, due to the size of real world graphs characterized by millions of nodes and billions of edges. We present GraPE, a software resource for graph processing and random walk based embedding, that can scale with large and high-degree graphs and significantly speed up-computation. GraPE comprises specialized data structures, algorithms, and a fast parallel implementation that display several orders of magnitude improvement in empirical space and time complexity compared to state of the art software resources, with a corresponding boost in the performance of machine learning methods for edge and node label prediction and for the unsupervised analysis of graphs.GraPE is designed to run on laptop and desktop computers, as well as on high performance computing clusters.Several software libraries have been developed to efficiently process and analyze graphs, including iGraph [10], GraphLab [11], GraphX [12] and SNAP [13]. In addition, several software resources implement graph embedding algorithms based on random walk sampling to map nodes and edges into a vector space [14, 15, 16].These resources, as well as other recent software libraries that implement graph neural networks [17, 18], share the problem of scalability with large graphs. Real-world networks often contain millions of of nodes 1

Unifying the Identification of Biomedical Entities with the Bioregistry

“…Second, we envision the Bioregistry supporting the standardization of structured metadata associated with models and networks derived from data such as mechanistic models (e.g., in the BioModels database 57 ), network-based models (e.g., in Network Data Exchange (NDEx) 44 ), knowledge graphs (e.g., those described by Bonner et al 58 ) , and machine learning models (e.g., such as those trained by GRAPE 48 ) in order to promote their interoperability and reuse. For example, despite the recent proliferation of biomedical knowledge graphs 58 , there has been little convergence on standardized syntax or semantics for identifying nodes and edges.…”

“…Overall, the inclusion of Bioregistry has improved the PheKnowLator Ecosystem and the knowledge graphs it produces. Similarly, the Graph Representation leArning, Predictions and Evaluation (GRAPE) 48 software package uses the Bioregistry to normalize the identifiers in several networks and knowledge graphs (including PheKnowLator).…”

“…Network Data Exchange (NDEx) 44 ), knowledge graphs (e.g., those described by Bonner et al 58 ), and machine learning models (e.g., such as those trained by GRAPE 48 ) in order to promote their interoperability and reuse. For example, despite the recent proliferation of biomedical knowledge graphs 58 , there has been little convergence on standardized syntax or semantics for identifying nodes and edges.…”

Open Biomedical Network Benchmark A Python Toolkit for Benchmarking Datasets with Biomedical Networks

“…• GraPE (Cappelletti et al, 2021) is a fast and scalable Python package written in Rust under the hood for generating node embeddings. It contains many well-known node embedding techniques such as node2vec (Grover and Leskovec, 2016), LINE (Tang et al, 2015), and walklets (Perozzi et al, 2017).…”