The Network Data Repository with Interactive Graph Analytics and Visualization

Authors: Ryan Rossi, Nesreen Ahmed

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 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.
Researcher Affiliation Academia Ryan A. Rossi and Nesreen K. Ahmed Dept. of Computer Science Purdue University West Lafayette, IN 47906
Pseudocode No No pseudocode or algorithm blocks are present in the paper.
Open Source Code No The paper describes a web-based platform (networkrepository.com) but does not provide specific statements or links to the open-source code for the methodology or platform itself. It only states that users can download data from it.
Open Datasets Yes NR currently has 500+ graphs from 19 general collections (social, information, and biological networks, among others) that span a wide range of types (bipartite, time-series, etc.) and domains (social sciences, physics, bioinformatics). Unlike other data repositories (e.g., UCI ML Repository, SNAP), NR allows users to not only download, but to interactively analyze and visualize the data in real-time on the web (e.g., see Figure 2). Scientific progress depends on standard datasets for which claims, hypotheses, and algorithms can be compared and evaluated. For the purpose of reproducible research, we encourage users to upload data (including a reference to the published paper).
Dataset Splits No The paper describes a data repository and interactive visualization platform and does not specify training, validation, or test dataset splits for model training or evaluation.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) are mentioned in the paper regarding the system or any experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library names and versions) for the platform or any related experiments.
Experiment Setup No The paper describes an interactive data repository and visualization platform, but it does not detail specific experimental setup parameters such as hyperparameters, training configurations, or system-level settings.