Loading...
Loading...
Social network graphs, knowledge graphs, citation networks, molecular graphs for GNN, web link graphs
322 datasets
A dataset of 1842 molecules used to train a Graph Neural Network model for predicting PC-SAFT equation-of-state parameters from molecular structure. The model was developed by Wildson Bernardino de Brito Lima and last updated in May 2026, achieving a liquid density mean absolute percentage error of 8.21% on a test set of 1642 unseen molecules. It demonstrated improved accuracy over traditional group contribution methods for complex solvents like ionic liquids and deep eutectic solvents.
A Graph Neural Network model predicts Perturbed-Chain Statistical Associating Fluid Theory (PC-SAFT) parameters for 1842 molecules based on molecular structure. The model, trained on experimental vapor pressure and saturated liquid density data, demonstrated superior performance on a test set of 1642 unseen molecules and a subset of 122 molecules compared to a traditional group contribution method. Created by Wildson Bernardino de Brito Lima and last updated on 2026-05-28, the dataset supports the application of the PC-SAFT equation of state to complex, low-volatility solvents.
A dataset of 1842 molecules used to train a Graph Neural Network model for predicting PC-SAFT equation-of-state parameters from molecular structure. The model was developed by Wildson Bernardino de Brito Lima and last updated in May 2026, achieving a liquid density mean absolute percentage error of 8.21% on a test set of 1642 unseen molecules. It demonstrated improved accuracy over traditional group contribution methods for complex solvents like ionic liquids and deep eutectic solvents.
22 online semi-structured interviews with men who have sex with men in Australia, conducted as part of a process evaluation for a social network-based HIV self-testing intervention. The data, authored by Ying Zhang and last updated in June 2026, includes thematic analysis of facilitators and barriers to implementation using the Consolidated Framework for Implementation Research (CFIR). Interviews explored perceptions of acceptability, feasibility, and contextual appropriateness of peer-led test kit distribution.
Simon Lee's study investigates the relationship between ResearchGate platform quality and scholars' research performance. The dataset, 60.9 KB in size, likely contains survey responses analyzing system, information, service, and collaboration quality. It was last updated on May 28, 2026.
Evolving Graph Attention Networks (EGAT) are proposed for learning from dynamic graphs where nodes and edges change over time. The 5.5 KB XLS file, authored by Yucai Jiang and last updated in June 2026, likely contains performance metrics from experiments comparing EGAT to other models. The results demonstrate that the proposed model outperforms state-of-the-art baselines on benchmark datasets.
Yucai Jiang published a dataset on figshare in 2026. The dataset contains statistics for benchmark datasets used to evaluate the EGAT model for dynamic graph representation learning. The file is 5.5 KB in size and is available in XLS format.
25 stakeholders were identified and analyzed for Abu Dhabi's National Bullying Prevention Strategy. The dataset, created by Alfan Al-Ketbi and last updated in May 2026, maps the influence and roles of 17 organizations using semantic and social network analysis. It benchmarks findings against international models from Finland, Norway, Australia, the USA, Japan, and Singapore.
IV-SAKG is a scenario-aware knowledge graph dataset constructed for vulnerability reasoning in industrial control systems. It contains entities, relations, and triples built upon public vulnerability sources like CVE, CISA, and CNVD. The dataset was authored by ling zhang and last updated on 2026-05-25.
Data supporting a hierarchical framework for predicting acute, intra-day public transport demand surges during mega-events. The dataset was created by Juan Angel Lucio Rojas and relates to FIFA World Cup 2026 host cities Mexico City and the New York/New Jersey metropolitan area. It was last updated on May 27, 2026.
Legacy deposit note: This Figshare record is an earlier archive copy and is not the current recommended version of the Samuel & Audrey Photography Metadata Archive. The 39.8 MB ZIP file contains an earlier version of metadata records, CSV and JSONL exports, and documentation from a travel photography archive hosted on SmugMug. Author Samuel Jeffery deposited this legacy version, which is retained for continuity and historical version tracking.
Samuel Jeffery deposited a 23.2 KB legacy archive of a dataset directory for the Samuel & Audrey Media Network on figshare. The ZIP file contains a small machine-readable registry and README file from an earlier version of the network's dataset-index work. This record was last updated on 2026-05-30 and is retained for historical continuity, not as the current active directory.
Argentina-focused travel coverage, article records, video transcript records, photography metadata, and media references from the Samuel & Audrey Media Network. This 184.2 MB legacy deposit includes CSV and JSONL exports, compressed data files, documentation, and LLM-oriented text files from an earlier version of the archive. The record is retained for continuity and historical version tracking, with the current active dataset maintained across multiple platforms.
A 2.3 MB PDF review authored by Abir Khazaal, published on figshare under a CC-BY-4.0 license in May 2026. The document synthesizes concepts, inference, and validation methods for modeling biological systems as time-indexed graphs.
Southeastern Iran provided 267 clinically labeled pressure injury images collected from hospitalized patients between 2023 and 2024. Images were captured using mobile phone cameras under varying lighting conditions to reflect real-world clinical settings. Each image was annotated by three wound care specialists according to NPIAP guidelines, covering Stages 1 to 4.
A 5.5 KB Excel file uploaded by Chung-Yuan Huang on 2026-05-19. It provides a structural comparison of three opinion dynamics models: the HK model, the Deffuant Relative Agreement model, and a proposed mechanism. The proposed model uses a pairwise random interaction structure with a fixed global confidence threshold on an explicit network topology, conditioned on agent adoption statuses.
A knowledge graph constructed in 2026 integrates multi-source biomedical data to elucidate complex disease mechanisms. It contains 15 entity types (245,235 entities) and 52 relation types (7,155,373 triples), covering 709 core Type 2 Diabetes genes. The dataset was created by Zekun Zhou and is available under a CC-BY-4.0 license.
Zekun Zhou published a cross-medicine knowledge graph (CMKG) for Type 2 Diabetes Mellitus (T2DM) drug discovery on figshare in May 2026. The graph contains 15 entity types (245,235 entities) and 52 relation types (7,155,373 triples), integrating data from sources like Hetionet, SymMap, TCMBank, STRING, and TTD. It was constructed to enable interpretable prioritization of drug candidates using graph embedding models and a unified path scoring framework.
Zekun Zhou published an entity ID naming table on 2026-05-13. The table is part of a study constructing a cross-medicine knowledge graph containing 245,235 entities and 7,155,373 triples to elucidate mechanisms of Type 2 Diabetes Mellitus. The 5.5 KB XLS file provides identifiers for entities integrated from sources like Hetionet, SymMap, TCMBank, STRING, and TTD.
A biomedical knowledge graph constructed by Zekun Zhou, integrating multi-source data from Hetionet, SymMap, TCMBank, STRING, and TTD. It contains 15 entity types (245,235 entities) and 52 relation types (7,155,373 triples), covering 709 core Type 2 Diabetes Mellitus genes. The dataset was last updated on May 13, 2026.