Graph Classification is a task that involves classifying a graph-structured data into different classes or categories. Graphs are a powerful way to represent relationships and interactions between different entities, and graph classification can be applied to a wide range of applications, such as social network analysis, bioinformatics, and recommendation systems. In graph classification, the input is a graph, and the goal is to learn a classifier that can accurately predict the class of the graph.
For benchmarking, please refer to its variant UPFD-POL and UPFD-GOS. The dataset has been integrated with Pytorch Geometric (PyG) and Deep Graph Library (DGL). You can load the dataset after installing the latest versions of PyG or DGL. The UPFD dataset includes two sets of tree-structured graphs curated for evaluating binary graph classification, graph anomaly detection, and fake/real news detection tasks. The dataset is dumped in the form of Pytorch-Geometric dataset object. You can easily load the data and run various GNN models using PyG. The dataset includes fake&real news propagation (retweet) networks on Twitter built according to fact-check information from Politifact and Gossipcop. The news retweet graphs were originally extracted by FakeNewsNet. Each graph is a hierarchical tree-structured graph where the root node represents the news; the leaf nodes are Twitter users who retweeted the root news. A user node has an edge to the news node if he/she retweeted the news tweet. Two user nodes have an edge if one user retweeted the news tweet from the other user. We crawled near 20 million historical tweets from users who participated in fake news propagation in FakeNewsNet to generate node features in the dataset. We incorporate four node feature types in the dataset, the 768-dimensional bert and 300-dimensional spacy features are encoded using pretrained BERT and spaCy word2vec, respectively. The 10-dimensional profile feature is obtained from a Twitter account's profile. You can refer to profile_feature.py for profile feature extraction. The 310-dimensional content feature is composed of a 300-dimensional user comment word2vec (spaCy) embedding plus a 10-dimensional profile feature. The dataset statistics is shown below: | Data | #Graphs | #Fake News| #Total Nodes | #Total Edges | #Avg. Nodes per Graph | |-------|--------|--------|--------|--------|--------| | Politifact | 314 | 157 | 41,054 | 40,740 | 131 | | Gossipcop | 5464 | 2732 | 314,262 | 308,798 | 58 | Please refer to the paper for more details about the UPFD dataset. Due to the Twitter policy, we could not release the crawled user's historical tweets publicly. To get the corresponding Twitter user information, you can refer to the news lists under \data in our github repo and map the news id to FakeNewsNet. Then, you can crawl the user information by following the instruction on FakeNewsNet. In the UPFD project, we use Tweepy and Twitter Developer API to get the user information.
The Maximum Unbiased Validation (MUV) dataset is a benchmark dataset selected from PubChem BioAssay. It was created by applying a refined nearest-neighbor analysis. The MUV dataset is specifically designed for the validation of virtual screening techniques.
ApisTox contains molecules in SMILES format for predicting pesticides toxicity to honey bees. The binary classification task is to predict whether a pesticide molecule is acutely toxic to honey bees or not.
The CHILI-100K dataset is a large-scale graph dataset (with overall >183M nodes, >1.2B edges) of nanomaterials generated from experimentally determined crystal structures. The crystal structures used in CHILI-100K are obtained from a curated subset from the Crystallography Open Database (COD) and has a broad chemical scope covering database entries for 68 metals and 11 non-metals.
The CHILI-3K dataset is a medium-scale graph dataset (with overall >6M nodes, >49M edges) of mono-metallic oxide nanomaterials generated from 12 selected crystal types. This dataset has a narrow chemical scope focused on an interesting part of chemical space with a lot of active research.
GVLQA is the first vision-language QA dataset for general graph reasoning. Contains a base set GVLQA-BASE and four image-augmented subsets GVLQA-AUGLY, GVLQA-AUGNO, GVLQA-AUGNS, GVLQA-AUGET, where the samples are relatively corresponding with the base set. Contains 7 graph reasoning tasks: detecting cycle, connectivity, computing topological ordering, shortest path, maximum flow, bipartite matching num, and Hamilton path. Utility: 1) evaluate the graph reasoning capabilities of VLMs or LLMs; 2) help models acquire fundamental graph comprehension and reasoning abilities as a pretraining dataset.
Lifespan HCP Release 2.0 includes cross-sectional visit 1 (V1) preprocessed structural and functional imaging data, unprocessed V1 imaging data for all included modalities (structural, high-res hippocampal T2, resting state fMRI, task fMRI, diffusion, and ASL), and non-imaging demographic and behavioral assessment data from 725 HCP-Aging (HCP-A, ages 36-100+) healthy participants (22+ TB of data).
UK Biobank participants have generously provided a very wide range of information about their health and well-being since recruitment began in 2006. This has been added to in the following ways: Imaging: Brain, heart and full body MR imaging, plus full body DEXA scan of the bones and joints and an ultrasound of the carotid arteries. The goal is to image 100,000 participants, and to invite participants back for a repeat scan some years later.
The AIDS Antiviral Screen dataset is a dataset of screens checking tens of thousands of compounds for evidence of anti-HIV activity. The available screen results are chemical graph-structured data of these various compounds. Source: Graph Neural Processes Towards Bayesian Graph Neural Networks
B-XAIC consists of 50K small molecules represented as graphs and includes 7 graph classification tasks, each with ground truth labels and corresponding explanations.
Synthetic graph classification datasets with the task of recognizing the connectivity of same-colored nodes in 4 graphs of varying topology. * The four Color-connectivity datasets were created by taking a graph and randomly coloring half of its nodes one color, e.g., red, and the other nodes blue, such that the red nodes either form a single connected island or two disjoint islands. The binary classification task is then distinguishing between these two cases. The node colorings were sampled by running two red-coloring random walks starting from two random nodes. * For the underlying graph topology we used: 1) 16x16 2D grid, 2) 32x32 2D grid, 3) Euroroad road network (Šubelj et al. 2011), and 4) Minnesota road network. * We sampled a balanced set of 15,000 coloring examples for each graph, except for Minnesota network for which we generated 6,000 examples due to memory constraints. * The Color-connectivity task requires combination of local and long-range graph information processing to which most existing message-passing Graph Neural Networks (GNNs) do not scale. These datasets can serve as a common-sense validation for new and more powerful GNN methods. These testbed datasets can still be improved, as the node features are minimal (only a binary color) and recognition of particular topological patterns (e.g., rings or other subgraphs) is not needed to solve the task.
The SPOTS-10 dataset is an extensive collection of grayscale images showcasing diverse patterns found in ten animal species. Specifically, SPOTS-10 contains 50,000 32 x 32 grayscale images, divided into ten categories, with 5,000 images per category. The training set comprises 40,000 images, while the test set contains 10,000 images. The SPOTS-10 dataset is freely available on the project GitHub page: https://github.com/amotica/spots-10 by cloning the repository.
This dataset accompanies the paper `Learning the mechanisms of network growth' by the same authors. The dataset contains 6733 networks of size 20,000 each generated in accordance to different combination of three mechanisms: fitness, aging and preferential attachment. The goal is to use machine learning to identify the combination of mechanisms that was used to create the network. The dataset includes static features from the literature and two version of our newly developed dynamic features. net