The Network Data Repository with Interactive Graph Analytics and Visualization

By Ryan A. Rossi, Nesreen K. Ahmed. AAAI Conference on Artificial Intelligence, 2015

3,002 citations recorded by the source corpus.

NetworkRepository (NR) is the first interactive data repository with a web-based platform for visual interactive analytics. Unlike other data repositories (e.g., UCI ML Data Repository, and SNAP), the network data repository (networkrepository.com) allows users to not only download, but to interactively analyze and visualize such data using our web-based interactive graph analytics platform. Users can in real-time analyze, visualize, compare, and explore data along many different dimensions. The aim of NR is to make it easy to discover key insights into the data extremely fast with little effort while also providing a medium for users to share data, visualizations, and insights. Other key factors that differentiate NR from the current data repositories is the number of graph datasets, their size, and variety. While other data repositories are static, they also lack a means for users to collaboratively discuss a particular dataset, corrections, or challenges with using the data for certain applications. In contrast, NR incorporates many social and collaborative aspects that facilitate scientific research, e.g., users can discuss each graph, post observations, and visualizations.

Subfields: Computer Vision and Pattern Recognition, Molecular Biology, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/93ee8e1c05d11d63aa3d61653b2c8bae75e0aecd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Molecular Biology

In Statistical and Nonlinear Physics

Citations in the corpus

Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, background): “FB-FORUM25:This dataset comes from a Facebook-like online community of students at the University of California, Irvine and was collected in 2004 [175, 193].”
Linear Algebra and its Applications (2010, neutral): “For formulating our exponential integrator we rewrite the semi-discrete system (1.2) as where J = M − 1 A and f ( t ) = M − 1 g ( t ) and w , M , A and g ( t ) are deﬁned as in (3.4).”
Representation Tradeoffs for Hyperbolic Embeddings (2018, background): “, 2016), available at Sanderson et al. (1994). Nearly tree-like hierarchies include the WordNet hypernym graph (the largest connected component from Nickel & Kiela (2017)) and a graph of Ph.”
UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks (2021, methodology): “Datasets We use the standard academic network datasets: DBLP [Rossi and Ahmed, 2015], Pubmed, Citeseer and Cora [Sen et al. , 2008] for all the experiments.”
A Comprehensive Survey on Community Detection With Deep Learning (2021, background): “Dynamic structures and temporal semantic features mean nodes and edges may be added or removed as time passes, which changes community structures [189], [190].”
Artificial Intelligence and the Implementation Challenge (2019, neutral): “The first pair is privacy and consent and the second is representative data and algorithmic bias.”
Representation Learning for Dynamic Graphs: A Survey (2019, methodology): “Sarkar et al. (2007) use Kalman filters to track the embeddings of the nodes through time for a bipartite graph.”
STREETS: A Novel Camera Network Dataset for Traffic Flow (2019, methodology): “Popular datasets in graph signal processing include the Minnesota highway road network [34] and a taxi-ride dataset in New York city [35].”
Nine quick tips for analyzing network data (2019, background): “Browser-based visualization [14] recently emerged as an intermediate category, mostly based on a collection of javascript libraries (e.”
Graph Neural Networks with Heterophily (2020, background): “However, the vast majority of graph data does not have such node-level features (Rossi and Ahmed 2015), which greatly limits the utility of the methods proposed in prior work that assume such features are available.”
Continuous-Time Dynamic Network Embeddings (2018, positive): “All data was obtained from NetworkRepository [58].”