Loading...
Loading...
Social network graphs, knowledge graphs, citation networks, molecular graphs for GNN, web link graphs
428 datasets
Research on graph neural networks focuses on improving performance under temperature variations and reducing latency. The work likely involves hardware acceleration using 3-D magnetic technology. The dataset's specific size, origin, and temporal coverage are not provided in the input.
Metadata for a knowledge graph derived from a Catholic encyclopedia. The dataset contains structured information categorized with tags including Encyclopedia, Text, Graph, and Theology. Specific details on row count, column structure, and authorship are not provided in the input.
This dataset supports molecular property prediction, specifically pIC50 values, using graph neural network ensembles. It is derived from the ChEMBL database and is tagged for graph and tabular analysis. The specific row count, column count, and data volume are not provided in the input.
A source of a graph representation of the Bengaluru metro network, including geospatial data and connectivity information. It is sourced from Kaggle and tagged for public transport, graph analysis, and the Bengaluru region.
281,903 nodes and 2,312,497 directed edges representing the hyperlink structure of Stanford University's web domain. The data captures a historical snapshot of web connectivity from 2002, organized as a directed graph where nodes are pages and edges are links.
schochastics developed this R package collection of multiple network datasets, which was last updated in March 2026. It provides a variety of graph structures for researchers and practitioners performing network analysis within the R ecosystem.
Multi-factor economic indicators are provided for risk and connectivity modeling. The dataset is sourced from Kaggle and is associated with data analytics and cleaning tasks. Specific details on volume, authorship, and temporal coverage are unavailable.
A collection of a large-scale collection of residential floor plans structured as vector-graphs. The data captures architectural layouts and spatial connectivity to facilitate graph-based computational design and structural analysis.
MetaCogBench-tasks is a dataset hosted on Kaggle. The title suggests it contains a collection of tasks designed for benchmarking cognitive or metacognitive capabilities, likely in AI or psychology contexts. No further metadata is available to confirm its specific contents, size, or origin.
KG20C is a benchmark dataset for scholarly knowledge graphs, published on Kaggle. The dataset likely contains structured relationships between academic entities such as papers, authors, and institutions. Its exact size, creation date, and authorship are unknown.
1,000,000,000 network event records categorized into normal traffic and three specific attack types: DDoS, SQL injection (SQLi), and BruteForce. The dataset includes a pre-trained CatBoost model achieving 99.9% detection accuracy across these security event classes.
36 Water Distribution Networks (WDNs) each contain 1,000 distinct scenarios. Each scenario is a timeseries of directed shared-topology graphs, representing a spatiotemporal graph where nodes and edges are multivariate time series. The dataset was created by author 'rugds' and was last updated on 2025-11-25.
CAGNN Sum v6 Checkpoints are pre-trained model weights published on Kaggle. The dataset's specific architecture, training data, and performance metrics are not detailed in the provided metadata. Users must download the checkpoints to verify their intended application and compatibility.
A collection of tabular data describing the nodes and edges of causal networks derived from participatory modeling with local actors. It covers 26 territorial units across six intervention areas of the PACTE project, elucidating cause-and-effect relationships between policy, environmental, socioeconomic dynamics, and livelihood strategies.
CAGNN Sum v6 checkpoints are a set of pre-trained model weights for a Graph Neural Network, likely for graph classification or node representation tasks. The dataset is hosted on Kaggle and is tagged as a 'Pre Trained Model'. Specific details on the architecture, training data, and performance are not provided in the metadata.
Social network advertising data, likely containing user demographics and ad interaction metrics. The dataset is hosted on Kaggle, but its specific origin, size, and creation details are not provided in the available metadata. Further details about the columns, sample data, and license require verification after download.
Kaggle hosts this dataset, which likely contains information related to advertising on social media platforms. The specific variables, data collection method, and creator are not detailed in the available metadata. Its content and scale require verification after download.
A dataset likely containing graph-structured data for training or benchmarking Graph Neural Networks (GNNs). It is hosted on Kaggle, but the specific content, size, and creator are unknown. The dataset's last update date is also unknown.
A dataset for training and evaluating Graph Neural Network (GNN) models, published on Kaggle. The specific content, scale, and origin are not detailed in the available metadata. Users must download the dataset to verify its structure, features, and intended applications.
CAGNN Sum Checkpoints likely contain saved model states for a Graph Neural Network architecture. The dataset is hosted on Kaggle and is tagged as a 'Pre Trained Model'. Specific details on the model's architecture, training data, and performance are not provided in the available metadata.