Papers with Code 아카이브

Node Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
5
평가표
138
보존된 평가 기록
1,793

Node Classification is a machine learning task in graph-based data analysis, where the goal is to assign labels to nodes in a graph based on the properties of nodes and the relationships between them.

Node Classification models aim to predict non-existing node properties (known as the target property) based on other node properties. Typical models used for node classification consists of a large family of graph neural networks. Model performance can be measured using benchmark datasets like Cora, Citeseer, and Pubmed, among others, typically using Accuracy and F1.

<span style="color:grey; opacity: 0.6">( Image credit: Fast Graph Representation Learning With PyTorch Geometric )</span>

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

ChEMBL

ChEMBL is a manually curated database of bioactive molecules with drug-like properties. It brings together chemical, bioactivity and genomic data to aid the translation of genomic information into effective new drugs.

CHILI-100K

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.

CHILI-3K

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.

City-Networks

City-Networks, a transductive learning dataset for testing long-range dependencies in Graph Neural Networks (GNNs). In particular, the dataset contains four large-scale city maps: Paris, Shanghai, L.A., and London, where nodes represent intersections and edges represent road segments.

Electronics

This data was collected by performing a breadth-first search on the user-product-review graph until termination, meaning that it is a fairly comprehensive collection of English-language product data. We split the full dataset into top-level categories, e.g. Books, Movies, Music. We do this mainly for practical reasons, as it allows each model and dataset to fit in memory on a single machine (requiring around 64GB RAM and 2-3 days to run our largest experiment). Note that splitting the data in this way has little impact on performance, as there are few links that cross top-level categories, and the hierarchical nature of our model means that few parameters are shared across categories. To obtain ground-truth for pairs of substitutable and complementary products we also crawl graphs of four types from Amazon: 1. 'Users who viewed x also viewed y'; 91M edges. 2. 'Users who viewed x eventually bought y'; 8.18M edges. 3. 'Users who bought x also bought y'; 133M edges. 4. 'Users frequently bought x and y together'; 4.6M edges. We refer to edges of type 1 and 2 as substitutes and edges of type 3 or 4 as complements, though we focus on 'also viewed' and 'also bought' links in our experiments, since these form the vast majority of the dataset. Note the minor differences between certain edge types, e.g. edges of type 4 indicate that two items were purchased as part of a single basket, rather than across sessions.

FDCompCN

A new fraud detection dataset FDCompCN for detecting financial statement fraud of companies in China. We construct a multi-relation graph based on the supplier, customer, shareholder, and financial information disclosed in the financial statements of Chinese companies. These data are obtained from the China Stock Market and Accounting Research (CSMAR) database. We select samples between 2020 and 2023, including 5,317 publicly listed Chinese companies traded on the Shanghai, Shenzhen, and Beijing Stock Exchanges.

HeriGraph

The dataset contains constructed multi-modal features (visual and textual), pseudo-labels (on heritage values and attributes), and graph structures (with temporal, social, and spatial links) constructed using User-Generated Content data collected from Flickr social media platform in three global cities containing UNESCO World Heritage property (Amsterdam, Suzhou, Venice). The motivation of data collection in this project is to provide datasets that could be both directly applicable for ML communities as test-bed, and theoretically informative for heritage and urban scholars to draw conclusions on for planning decision-making.

NBA

NBA: This is extended from a Kaggle dataset * containing around 400 NBA basketball players. The performance statistics of players in the 2016-2017 season and other various information e.., nationality, age, and salary are provided. To obtain the graph that links the NBA players together, we collect the relationships of the NBA basketball players on Twitter with its official crawling API 2. We binarize the nationality to two categories, i.e., U.S. players and oversea players, which is used as sensitive attribute. The classification task is to predict whether the salary of the player is over median. 1. https://www.kaggle.com/noahgift/social-power-nba 2. https://developer.twitter.com/en

CellTypeGraph Benchmark

Classifying all cells in an organ is a relevant and difficult problem from plant developmental biology. We here abstract the problem into a new benchmark for node classification in a geo-referenced graph. Solving it requires learning the spatial layout of the organ including symmetries. To allow the convenient testing of new geometrical learning methods, the benchmark of Arabidopsis thaliana ovules is made available as a PyTorch data loader, along with a large number of precomputed features.

Financial Dynamic Knowledge Graph

FinDKG: The Global Financial Dynamic Knowledge Graph Dataset FinDKG is an open-source dataset focused on creating a temporally-resolved Financial Dynamic Knowledge Graph. Designed to bridge the gap in industry-specific knowledge graphs, particularly in the financial sector, FinDKG provides a high-touch, temporally-aware representation of global economic and market dynamics. This repository includes comprehensive details about the dataset, methodology, and schema, aiming to facilitate academic research and actionable insights in global financial markets. ## Background While general-purpose knowledge graphs are abundant, industry-specific ones are comparatively rare, especially in the financial sector. FinDKG aims to fill this void by offering a resource for researchers and professionals looking to leverage knowledge graph technology in finance. ## FinDKG Dataset The dataset's foundation lies in an extensive news corpus curated to capture both qualitative and quantitative indicators in the financial landscape. We utilized the Wayback Machine to amass a dataset comprising global financial news. ## Dataset Structure - Temporal Knowledge Graph (TKG) with daily-resolved event triplets - Event triplets are tagged with specific timestamps corresponding to their release dates - Training, validation, and test splits organized chronologically - Weekly aggregation of event triplets as the basic unit of time ### Data Format /FinDKG is the default study dataset folder including the graph dataset and the corresponding data splits. The graph dataset is organized in the following structure: * 'train.txt', 'valid.txt', and 'test.txt': The first four columns correspond to subject, relation, object, and time. The fifth column is ignored. * 'stat.txt': The first two columns correspond to the number of entities and relations, respectively. Test set is held-out for evaluating the model performance. This should match the results of the original paper regarding the Temporal Link Prediction evaluation. /FinDKG-full: The full dataset including a larger size of the event triplets. This graph dataset adopts the same format as /FinDKG while is left for future extended research. * 'time2id.txt': This time mapping table further provided the mapping from time ID to realistic date for real-world application. ## Usage The dataset is designed for graph-based AI methods aiming to generate actionable insights in the financial domain. It is freely available for academic and research purposes. Refer details to our designated FinDKG website. (Description from Dataset Repo)

MAPLE

The MAPLE benchmark constructed by us contains 20 datasets across 19 fields for scientific literature tagging. It also has a graph format, which can be used for graph mining tasks (e.g., node classification, link prediction). Refer to its homepage for more details.

SAGC-A68

The analysis of building models for usable area, building safety, and energy efficiency requires accurate classification data of spaces and space elements. To reduce input model preparation effort and errors, automated classification of spaces and space elements is desirable. Although existing space function classifiers use space adjacency or connectivity graphs as input, the application of Graph Deep Learning (GDL) to space layout element classification has not been extensively researched due to the lack of suitable datasets. To bridge this gap, we introduce a dataset named SAGC-A68, which comprises access graphs automatically generated from 68 digital 3D models of space layouts of apartment buildings designed or built between 1952 and 2019 in 13 countries. Each access graph contains nodes representing spaces and space elements and edges representing the connection between them. Nodes are uniquely identified and characterized by 16 features including “Position X”, “Position Y”, “Position Z”, “Width”, “Height”, “Depth”, “Area”, “Volume”, “Is_internal”, “Door_opening_quantity”, “Window_quantity”, “Max_door_width”,” Encloses_ws”, “Is_contained_in_ws”, ”bounding_box”, and “Label” (28 identified labels are shown in bold type in Table 1). Edges are identified by a unique ID and characterized by three features, including “Z_angle”, “Delta_z”, and “Length”. In total, the dataset comprises 4871 nodes and 4566 edges, including disconnected nodes representing shafts. It is suitable for developing GDL models for space element and space function classification in Building information modeling (BIM) authoring systems.

Twitter-HyDrug

Twitter-HyDrug is a real-world hypergraph data that describes the drug trafficking communities on Twitter. We first crawl the metadata (275,884,694 posts and 40,780,721 users) through the official Twitter API from Dec 2020 to Aug 2021. Afterward, we generate a drug keyword list that covers 21 drug types that may cause drug overdose or drug addiction problems to filter the tweets that contain drug-relevant information. Based on the keyword list, we obtain 266,975 filtered drug-relevant posts by 54,680 users. Moreover, we define six types of drug communities, i.e., cannabis, opioid, hallucinogen, stimulant, depressant, and others communities, based on the drug functions. Six researchers spent 62 days annotating these Twitter users into six communities based on the annotation rules discussed in the next section. With the specific criteria, six researchers annotated the filtered metadata separately. For these Twitter users with disagreed labels, we conducted further discussion among annotators for cross-validation. To conclude, we obtained the drug hypergraph including 2,936 user nodes and 33,892 hyperedges.

Twitter-HyDrug-UR

This benchmark hypergraph dataset, Twitter-HyDrug-UR, is derived from Twitter-HyDrug by HyGCL-DC. Twitter-HyDrug-UR is a real-world hypergraph data that describes the drug trafficking on Twitter. Unlike HyGCL-DC, which targets a drug trafficking community detection task (a multi-label node classification), we aim to identify drug user roles in drug trafficking activities on social media. To this end, we categorize node labels into four distinct roles: drug seller, drug buyer, drug user, and drug discussant, and each node is assigned to one and only one label. Consequently, we frame the problem for Twitter-HyDrug-UR as a multi-class node classification task.

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.