Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
14
datasets available to search
ShareScore release 0.9.0
Dataset results
14 results for “graph representation”
CNN Wild Park - Graph Neural Networks for Learning Equivariant Representations of Neural Networks
<p>This repository contains the <strong>CNN Wild Park</strong> dataset from the paper:</p> <blockquote> <p><strong>Graph Neural Networks for Learning Equivariant Representations of Neural Networks</strong><br><a href="https://mkofinas.github.io/">Miltiadis Kofinas</a>*, <a href="https://bknyaz.github.io/">Boris Knyazev</a>, <a href="https://www.cyanogenoid.com/">Yan Zhang</a>, <a href="https://yunlu-chen.github.io/">Yunlu Chen</a>, <a href="https://gertjanburghouts.github.io/">Gertjan J. Burghouts</a>, <a href="https://egavves.com/">Efstratios Gavves</a>, <a href="https://www.ceessnoek.info/">Cees G. M. Snoek</a>, <a href="https://davzha.netlify.app/">David W. Zhang</a>*<br><em>ICLR 2024</em> (oral)<br><a href="https://arxiv.org/abs/2403.12143">https://arxiv.org/abs/2403.12143</a><br><a href="https://github.com/mkofinas/neural-graphs">https://github.com/mkofinas/neural-graphs</a><br>*Joint first and last authors</p> </blockquote> <p>We introduce a new dataset of CNNs, which we term <em>CNN Wild Park</em>.<br>The dataset consists of 117,241 checkpoints from 2,800 CNNs, trained for up to 1,000 epochs on CIFAR10.<br>The CNNs vary in the number of layers, kernel sizes, activation functions, and residual connections between arbitrary layers.</p> <p>More specifically, we construct the CNN Wild Park dataset by training 2,800 small CNNs with different architectures for 200 to 1,000 epochs on CIFAR10. We retain a checkpoint of its parameters every 10 steps and also record the test accuracy. The CNNs vary by:</p> <ul> <li>Number of layers L in [2, 3, 4, 5] (note that this does not count the input layer).</li> <li>Number of channels per layer c_l in [4, 8, 16, 32].</li> <li>Kernel size of each convolution k_l in [3, 5, 7].</li> <li>Activation functions at each layer are one of ReLU, GeLU, tanh, sigmoid, leaky ReLU, or the identity function.</li> <li>Skip connections between two layers with at least one layer in between. Each layer can have at most one incoming skip connection. We allow for skip connections even in the case when the number of channels differ, to increase the variety of architectures and ensure independence between different architectural choices. We enable this by adding the skip connection only to the min(c_n, c_m) nodes.</li> </ul> <p>We divide the dataset into train/val/test splits such that checkpoints from the same run are <strong>not</strong> contained in both the train and test splits. </p> <div> </div> <div> </div>
Graph construction method impacts variation representation and analyses in a bovine super-pangenome
<p>Pangenomes for minigraph, pggb, and cactus containing assemblies from</p> <ul> <li>Hereford (cattle reference genome)</li> <li>Highland</li> <li>Brown Swiss</li> <li>Angus</li> <li>Simmental</li> <li>Original Braunvieh</li> <li>Piedmontese</li> <li>Nellore</li> <li>Brahman</li> <li>Yak</li> <li>Bison</li> <li>Gaur</li> </ul> <p> </p> <p>Also contains the genomic region classifications for the ARS-UCD1.2 reference genome for</p> <ul> <li>Satellites</li> <li>Tandem repeats</li> <li>Low mappability</li> <li>Repetitive regions</li> <li>Normal (everything else)</li> </ul>
A graph-based representation of the Hack Forums using Neo4j
<p>A graph-based representation of the Hack Forums using Neo4j.</p> <p>This dataset contains data to complement the paper "A Graph-based Stratified Sampling Methodology for the Analysis of (Underground) Forums" to appear in IEEE Transactions on Information Forensics and Security (TIFS). </p> <p>Due to ethical reasons, the data is anonymized and access to the actual content stored in the graph is subject to a formal data-sharing agreement with the Cambridge Cybercrime Centre. Please visit <a href="https://www.cambridgecybercrime.uk/process.html">this page</a> for more details on the process. </p>
A hierarchical graph-based model for mobility data representation and analysis
<p>Hierarchical representations of transportation networks should provide a better understanding of mobility patterns and the underlying structures at various abstraction levels. A hierarchical graph-based model allows representing moving objects and trajectories according to multiple spatial, temporal and semantic scales. The latter model is implemented here in a Neo4j graph database (version 4.4.0) and experimented with historical maritime data covering Brittany Bay in France.</p>
PGB: A PubMed Graph Benchmark for Heterogeneous Network Representation Learning
<p>PubMed Graph Benchmark (PGB) aggregates the metadata associated with the biomedical articles from PubMed into a unified source. The benchmark contains metadata including title, abstract, authors, in/out citations, MeSH terms, MeSH hierarchy, venue, publication type, and chemicals.</p>
BRAIN Journal-Right-Linear Languages Generated in Systems of Knowledge Representation based on LSG-Right-Figure 3. Representation of the grammar G1 in the labelled graph G0 1
<p>If we take the labeled graph G0 1 given in Figure 3 and construct the stratified graph structure over (99) such that (100) we obtain (101), (102). </p> <p>In this paper, we proposed a new system for formal language generation by means of stratified graphs structures. This mechanism can generate languages of the first type and of the second type. More precisely, we propose a new system for formal language generation by means of a system of knowledge based on stratified graphs. We exemplified that, using an interpretation system specially defined for stratified graphs representations, a particular formal language can be obtained by means of the resulted accepted structured paths.</p>
Speos: An ensemble graph representation framework to predict core genes for complex diseases (Datasets)
<p>the "data.tar.gz" tarball contains the unprocessed or minimally processed data used by Speos. If you intend to use the framework or want to inspect the data, download this part of the dataset.</p> <p>The "final_datasets.tar.gz" tarball contains tsv-formatted, processed data matrices which are directly used as input features for the ensemble models. </p> <p>There are two tsv-files per disease, one labeled "normal", which contains the p input features alongside the gene identifiers and a column which indicates if the gene is labeled as Mendelian or not, and another file labeled "with_n2v_vectors", which also contains the 100-dimensional vectors produced by Node2Vec so the N2V+MLP method can be reproduced with the exact same parameters. </p> <p>All files contain a header row which describes the column and no index column.</p> <p>The "model_parameters.tar.gz" tarball contains the model parameters for all ensemble models used to produce the candidate genes.</p>
Graph Fourier transform for spatially resolved omics representation and analyses
<p>The file is a CODEX image of a human tonsil. They contain:</p> <ol> <li>Whole image: entire tissue image of human tonsil.</li> <li>Raw image data: six field of view (FOV) are deposited in this figure</li> <li>Processed data: the pixel-level data of six FOVs are deposited in the Seurat object and H5AD file.</li> </ol> <p><span>The following anti-bodies were used for CODEX profiling:</span></p> <p><span>BCL-2 (124, Novus Biologicals), CCR6 (polyclonal, Novus Biologicals), CD11b (EPR1344, Abcam), CD11c (EP1347Y, Abcam), CD15 (MMA, BD Biosciences), CD16 (D1N9L, Cell Signaling Technology), CD162 (HECA-452, Novus Biologicals), CD163 (EDHu-1, Novus Biologicals), CD2 (RPA-2.10, Biolegend), CD20 (rIGEL/773, Novus Biologicals), CD206 (polyclonal, R&D Systems), CD25 (4C9, Cell Marque), CD30 (BerH2, Cell Marque), CD31 (C31.3+C31.7+C31.10, Novus Biologicals), CD4 (EPR6855, Abcam), CD44 (IM-7, Biolegend), CD45 (B11+PD7/26, Novus Biologicals), CD45RA (HI100, Biolegend),<span> </span>CD45RO (UCH-L1, Biolegend), CD5 (UCHT2, Biolegend), CD56 (MRQ-42, Cell Marque), CD57 (HCD57, Biolegend), CD68 (KP-1, Biolegend), CD69 (polyclonal, R&D Systems), CD7 (MRQ-56, Cell Marque), CD8 (C8/144B, Novus Biologicals), collagen IV (polyclonal, Abcam), cytokeratin (C11, Biolegend), EGFR (D38B1, Cell Signaling Technology), FoxP3 (236A/E7, Abcam), granzyme B (EPR20129-217, Abcam), HLA-DR (EPR3692, Abcam), IDO-1 (D5J4E, Cell Signaling Technology), LAG-3 (D2G4O, Cell Signaling Technology), mast cell tryptase (AA1, Abcam), MMP-9 (L51/82, Biolegend), MUC-1 (955, Novus Biologicals), PD-1 (D4W2J, Cell Signaling Technology), PD-L1 (E1L3N, Cell Signaling Technology), podoplanin (D2-40, Biolegend), T-bet (D6N8B, Cell Signaling Technology), TCR β (G11, Santa Cruz Biotechnology), TCR-γ/δ (H-41, Santa Cruz Biotechnology), Tim-3 (polyclonal, Novus Biologicals), Vimentin (RV202, BD Biosciences), VISTA (D1L2G, Cell Signaling Technology), α-SMA (polyclonal, Abcam), and β-catenin (14, BD Biosciences). </span></p>
Deep Clustering Representation for Spatially Resolved Transcriptomics Data via Multi-view Variational Graph Auto-Encoders with Consensus Clustering
Open the record for dataset details and reuse information.
Descriptor and Graph-based Molecular Representations in Prediction of Copolymer Properties using Machine Learning
<p>This dataset accompanies a study that investigates the use of machine learning (ML) approaches for predicting seven different physical properties of 140 binary copolymers. Two computational methods were employed: a random forest (RF) model based on molecular descriptors and a Graph Neural Network (GNN) using 2D polymer graphs. These methods were applied in both single- and multi-task settings to explore the strengths of each approach in capturing various polymer properties.</p> <p>The dataset includes two files:</p> <ol> <li> <p><strong>Dataset.xlsx</strong>: Contains the following information for each of the 140 copolymers:</p> <ul> <li>Polymer names</li> <li>SMILES notation of the monomers</li> <li>Fraction of monomers in each copolymer</li> <li>Simulated values (calculated using molecular dynamics simulation) and experimental values of various physical properties, including density, specific heat capacity at constant pressure ad volume ,radius of gyration, linear expansion coefficient, volume expansion coefficient, and bulk modulus .</li> </ul> </li> <li> <p><strong>Descriptors.xlsx</strong>: Provides the molecular descriptors calculated using PaDEL-Descriptor software, which were used as input for the RF model to predict polymer properties.</p> </li> </ol> <p>This work provides insight into the comparative strengths of descriptor- and graph-based representations in machine learning models for predicting material properties. It also highlights the importance of selecting appropriate molecular representations based on the nature of the properties being predicted.</p>
Comparison of Knowledge Graph Representations for Consumer Scenarios - Datasets
<p>These are the datasets used for the evaluations carried out in the submission "Comparison of Knowledge Graph Representations for Consumer Scenarios" to ISWC 2023</p>
Bottom-up Graph Representation Learning for Symbolic Expression Solving
Open the record for dataset details and reuse information.
Graph Representations of Intersectional Identity in Elye Bokher's 'Bovo D'Antona'
Open the record for dataset details and reuse information.
Broadening the Scope of Graph Regression: Introducing a Dataset with Multiple Representation Settings
<p>Replication package for Broadening the Scope of Graph Regression: Introducing a Dataset with Multiple Representation Settings</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.