Loading...
Loading...
Social network graphs, knowledge graphs, citation networks, molecular graphs for GNN, web link graphs
322 datasets
Mean Average Precision (MAP) scores for link prediction tasks across multiple graph datasets. Results are reported as mean ± standard deviation over five independent runs, with statistical significance noted. The 5.5 KB Excel file was authored by Yucai Jiang and last updated on June 1, 2026.
5.5 KB of tabular results for link prediction tasks, measured by Mean Reciprocal Rank (MRR). The data was authored by Yucai Jiang and last updated on June 1, 2026. Results are reported as mean ± standard deviation over five independent runs, with statistical significance indicators.
A 5.5 KB Excel file summarizing correspondence analysis results from a decade of data from the Chinese social media platform Zhihu. Authored by Kaijiao Zhang and last updated in May 2026, this dataset captures the structural characteristics and phased evolution of social representations of climate change in Chinese public discussion.
Claudio Schill's dataset supports the journal paper "Post-Event Ground Motion Estimation Using Graph Neural Networks." It likely contains ground motion intensity measures and spatial data for forensic analysis of structural damage after earthquakes. The dataset is 2.7 GB in size and was last updated on May 7, 2026.
20 interviews with adolescent girls married before 18 and their network members in three Bangladeshi villages reveal the social dynamics behind early marriage. The dataset, authored by Anja Zinke-Allmang and last updated in May 2026, includes interview transcripts and social network maps from a qualitative social network analysis. It examines how perceptions of a girl's physical growth, maturity, and household economics, rather than age alone, influence marriage timing.
Three villages in Bangladesh provide the setting for this qualitative social network analysis of child marriage decisions. The dataset contains interview transcripts and network maps from 26 participants, including 6 adolescent girls married before 18 and members of their social networks. The study was authored by Anja Zinke-Allmang and published on figshare under a CC-BY-4.0 license in May 2026.
20 interviews with adolescent girls married before 18 and their social network members provide insights into marriage decision-making in Bangladesh. The study, authored by Anja Zinke-Allmang and last updated in May 2026, includes participant-generated social network maps. Findings indicate parents are central decision-makers, with timing influenced by perceptions of a girl's readiness and household economic conditions.
TenderKG is a domain-specific knowledge graph for public procurement, extracted from French public tender notices awarded from 2021 to 2023. It models the procurement ecosystem with entities like public buyers, contracts, lots, and bidding companies, enriched with CPV and NAF codes and geographical information. The dataset is provided in RDF format (TTL) and was created by Yacine Mokhtari.
77,299 single-oracle instances derived from developer-written unit tests across 25 real-world Java projects. The TOGBench artifact, created by Tasfia Tasnim and last updated in April 2026, is a benchmark suite for automated test oracle generation built around the OE25dev dataset. It supports end-to-end executable evaluation through oracle injection, compilation, and mutation-based assessment.
65 antihistamine-refractory chronic spontaneous urticaria patients had serum levels of 15 cytokines measured at baseline and after 6 months of omalizumab treatment. The data, authored by Young-Min Ye and last updated in April 2026, was analyzed to identify cytokine imbalances and network architectures associated with heterogeneous treatment response categories.
6209 metabolites across 17 categories were identified in tubers and stems of Gastrodia elata. The dataset includes 1624 differential metabolites and reveals gastrodin and parishin C accumulation patterns. Jingling Duan published this untargeted metabolomics study on figshare in May 2026.
TOLLPOINT OFFICIAL contains all toll point locations in Saskatchewan, where fees are charged for access to motorways and bridges. Each point geometry has a unique National Identifier (NID) used to manage updates between data producers and users. The dataset is maintained by the Government of Saskatchewan and was last updated on May 20, 2026.
NASA's March through August Ice Edge Positions dataset provides coordinates for the ice edge boundary in the Nordic Seas. It spans over 250 years from 1750 to 2002, combining historical observations from ship logs with modern satellite data from SMMR and SSM/I instruments. The ice edge is defined as the outer limit of areas with at least 30 percent ice concentration.
RTS-Net is a deep learning model for thyroid nodule segmentation in ultrasound images, achieving an 81.66% F1-score on the TN3K dataset. The model integrates dual-path attention and graph convolution, and was trained on TN3K, DDTI, and a large-scale clinical dataset. The dataset, authored by Xiaojie Sun, was last updated on April 13, 2026.
A collection of thyroid ultrasound images used to train and evaluate the RTS-Net segmentation model. The data includes images from the TN3K and DDTI datasets, as well as a large-scale clinical dataset, with model performance metrics provided. The dataset was uploaded by Xiaojie Sun in April 2026.
A data dictionary for version 10 of the Penn World Table, a dataset of macroeconomic observations. It was uploaded by author Marcus Araujo on April 22, 2026. The associated research description references integrating over 500,000 macroeconomic observations from this source with trade data for a 25-year analysis across 183 countries.
The IMAGO Knowledge Graph represents data about Latin geographical literature from the 6th to the 15th centuries. It was developed by the IMAGO project (2020–2024) and contains information on works, authors, libraries, and literary genres. The 4.8 MB graph is available in RDF/XML and Turtle formats, including a version with inferred triples.
5.5 KB of data related to the EGAT (Evolving Graph Attention Networks) model, which evolves the weight of k attention heads at each time step for dynamic link prediction. The dataset was authored by Yucai Jiang and last updated on June 1, 2026. It is shared under a CC-BY-4.0 license on figshare.
Two California traffic datasets, PeMSD4 and PeMSD8, used to benchmark a Transformer-based Hypergraph Convolutional Network for traffic flow prediction. The 5.5 KB XLS files were published by SiWei Wei on figshare under a CC-BY-4.0 license and last updated in April 2026. Experiments described in the metadata involved 5 independent random seed runs to achieve statistically significant performance improvements on core metrics like MAE, RMSE, and MAPE.
A knowledge graph-Bayesian network-driven suspect screening (KGBS) strategy integrates text mining, probabilistic reasoning, and high-resolution mass spectrometry. The framework extracted 54,838 associations between phthalate esters and their metabolites from 3,167 publications to construct a Bayesian inference-embedded knowledge graph. Applied to paired indoor dust and human urine samples, the KGBS platform identified 68 PAEs and 49 metabolites, including 18 PAEs and 14 metabolites newly annotated in the study.