Papers with Code 아카이브
Graph Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 72
- 보존된 평가 기록
- 808
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.
<span style="color:grey; opacity: 0.6">( Image credit: Hierarchical Graph Pooling with Structure Learning )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/daiquocnguyen/Graph-Transformer
공식 코드https://github.com/daiquocnguyen/QGNN
공식 코드https://github.com/danielegrattarola/decimation-pooling
공식 코드Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
https://github.com/danielegrattarola/spektral
공식 코드https://github.com/david-leon/HAG-Net
공식 코드Enhance Information Propagation for Graph Neural Network by Heterogeneous Aggregations
https://github.com/davidlamprecht/autordf2gml
공식 코드AutoRDF2GML: Facilitating RDF Integration in Graph Machine Learning
https://github.com/dawenzi123/DAGCN
공식 코드https://github.com/devnkong/FLAG
공식 코드Robust Optimization as Data Augmentation for Large-scale Graphs
https://github.com/diningphil/continual_learning_for_graphs
공식 코드Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification
https://github.com/diningphil/e-cgmm
공식 코드https://github.com/diningphil/gnn-comparison
공식 코드A Fair Comparison of Graph Neural Networks for Graph Classification
https://github.com/divelab/DIG
공식 코드https://github.com/divelab/sopool
공식 코드https://github.com/dj408/infogain
공식 코드InfoGain Wavelets: Furthering the Design of Diffusion Wavelets for Graph-Structured Data
https://github.com/dmirlab-group/mgnn
공식 코드https://github.com/dmis-lab/hats
공식 코드HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction
https://github.com/dogregor/graph-fakenewsnet
공식 코드Exploring Fake News Detection with Heterogeneous Social Media Context Graphs
https://github.com/domenicocinque/spm
공식 코드https://github.com/dshi3553usyd/curvature_enhanced_graph_convolution
공식 코드https://github.com/egyptdj/graph-neural-mapping
공식 코드Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis
https://github.com/elmspace/neext
공식 코드https://github.com/erdemUB/LEN
공식 코드Large Engagement Networks for Classifying Coordinated Campaigns and Organic Twitter Trends
https://github.com/erdemub/ecmlpkdd25
공식 코드https://github.com/facebookresearch/SEAL_OGB
공식 코드Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
https://github.com/fanyun-sun/InfoGraph
공식 코드https://github.com/fengrui-z/ecal
공식 코드Catch Causal Signals from Edges for Label Imbalance in Graph Classification
https://github.com/filippomb/total-variation-graph-neural-networks
공식 코드https://github.com/flandolfi/k-mis-pool
공식 코드https://github.com/flyingdoog/PGExplainer
공식 코드https://github.com/foisunt/hyperaggregation
공식 코드HyperAggregation: Aggregating over Graph Edges with Hypernetworks
https://github.com/forkkr/HIBPool
공식 코드Structure-Aware Hierarchical Graph Pooling using Information Bottleneck
https://github.com/frareba/gradualweisfeilerleman
공식 코드https://github.com/fzx-oss/wwls
공식 코드https://github.com/gasmichel/pathnns_expressive
공식 코드Path Neural Networks: Expressive and Accurate Graph Neural Networks
https://github.com/gbouritsas/graph-substructure-networks
공식 코드Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.