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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/skyorca/opengda
공식 코드OpenGDA: Graph Domain Adaptation Benchmark for Cross-network Learning
https://github.com/smartdata-polito/gcnh
공식 코드GCNH: A Simple Method For Representation Learning On Heterophilous Graphs
https://github.com/smeznar/SNoRe
공식 코드SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations
https://github.com/snap-research/MLPInit-for-GNNs
공식 코드MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
https://github.com/snap-research/graphless-neural-networks
공식 코드Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
https://github.com/snap-research/largegt
공식 코드https://github.com/snap-stanford/ogb
공식 코드OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
https://github.com/sofiperez91/lase
공식 코드https://github.com/songw-sw/cosmic
공식 코드https://github.com/songw-sw/glitter
공식 코드https://github.com/songw-sw/tent
공식 코드https://github.com/songw-sw/x-fnc
공식 코드Few-shot Node Classification with Extremely Weak Supervision
https://github.com/songyyyy/gspt
공식 코드A Pure Transformer Pretraining Framework on Text-attributed Graphs
https://github.com/sonnyachten/gckm
공식 코드Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classification
https://github.com/sqrhussain/structure-in-gnn
공식 코드On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks
https://github.com/sra2/spell
공식 코드Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
https://github.com/sserranw/abg-nas
공식 코드ABG-NAS: Adaptive Bayesian Genetic Neural Architecture Search for Graph Representation Learning
https://github.com/stadlmax/Graph-Posterior-Network
공식 코드Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
https://github.com/stellargraph/FisherGCN
공식 코드https://github.com/steve30572/bsg
공식 코드https://github.com/submissionconff/g2gnn
공식 코드Imbalanced Graph Classification via Graph-of-Graph Neural Networks
https://github.com/suchanunp/eq_detector
공식 코드Spatio-Temporal Graph Structure Learning for Earthquake Detection
https://github.com/sukwonyun/s-mixup
공식 코드https://github.com/sung-won-kim/teg
공식 코드https://github.com/sunilkmaurya/FSGNN
공식 코드Improving Graph Neural Networks with Simple Architecture Design
https://github.com/superallen13/puma
공식 코드PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation
https://github.com/superca729/pl-ufg
공식 코드Generalized Laplacian Regularized Framelet Graph Neural Networks
https://github.com/superlouis/NODE-SELECT
공식 코드NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique
https://github.com/susheels/gnns-and-local-assortativity
공식 코드https://github.com/syleeheal/aero-gnn
공식 코드Towards Deep Attention in Graph Neural Networks: Problems and Remedies
https://github.com/syvail/PairE-Graph-Representation-Learning-Beyond-Node-and-Homophily
공식 코드https://github.com/taihasegawa/degnn
공식 코드DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
https://github.com/tailvyuanliang/h2tne
공식 코드$\text{H}^2\text{TNE}$: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces
https://github.com/tangjianpku/LINE
공식 코드https://github.com/tangxianfeng/PA-GNN
공식 코드Transferring Robustness for Graph Neural Network Against Poisoning Attacks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.