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/gdl-unive/histogram-intersection-kernel
공식 코드GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection
https://github.com/georgemlp/canonicalization
공식 코드A Canonicalization Perspective on Invariant and Equivariant Learning
https://github.com/georgemlp/laplacian-canonization
공식 코드Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding
https://github.com/geriskenderi/graph-jepa
공식 코드Graph-level Representation Learning with Joint-Embedding Predictive Architectures
https://github.com/giannisnik/cnn-graph-classification
공식 코드https://github.com/giannisnik/k-hop-gnns
공식 코드https://github.com/giannisnik/pi-GNN
공식 코드Permute Me Softly: Learning Soft Permutations for Graph Representations
https://github.com/giannisnik/repset
공식 코드Rep the Set: Neural Networks for Learning Set Representations
https://github.com/googlebaba/disc
공식 코드Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure
https://github.com/goose315/graph_pooling_benchmark
공식 코드A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizability
https://github.com/gqq1210/psp
공식 코드PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks
https://github.com/graphdeeplearning/benchmarking-gnns
공식 코드https://github.com/graphminddartmouth/graph-consistency
공식 코드Exploring Consistency in Graph Representations:from Graph Kernels to Graph Neural Networks
https://github.com/guillaumejaume/edGNN
공식 코드edGNN: a Simple and Powerful GNN for Directed Labeled Graphs
https://github.com/guoji-fu/dignn
공식 코드Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing
https://github.com/gusye1234/pytorch-light-gcn
공식 코드LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
https://github.com/gyshgx868/topo-ter
공식 코드Self-Supervised Graph Representation Learning via Topology Transformations
https://github.com/haidnguyen0909/weightedWWL
공식 코드Learning subtree pattern importance for Weisfeiler-Lehmanbased graph kernels
https://github.com/hamed1375/exphormer
공식 코드https://github.com/harryjo97/EHGNN
공식 코드https://github.com/hashemghanem/OPU_Graph_Classifier
공식 코드https://github.com/hkust-knowcomp/dummynode4graphlearning
공식 코드https://github.com/honoluluuuu/graphattacker
공식 코드https://github.com/hysonlab/multires-graph-transformer
공식 코드https://github.com/idea-iitd/mirage
공식 코드Mirage: Model-Agnostic Graph Distillation for Graph Classification
https://github.com/ifding/uhgr
공식 코드Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization
https://github.com/ihollywhy/FactorGCN.PyTorch
공식 코드https://github.com/inyeoplee77/SAGPool
공식 코드https://github.com/ispamm/mate
공식 코드A Meta-Learning Approach for Training Explainable Graph Neural Networks
https://github.com/iyempissy/rebMIGraph
공식 코드https://github.com/j-adamczyk/ltp
공식 코드Strengthening structural baselines for graph classification using Local Topological Profile
https://github.com/jamesyifan/DisenSemi
공식 코드DisenSemi: Semi-supervised Graph Classification via Disentangled Representation Learning
https://github.com/jeongwhanchoi/panda
공식 코드https://github.com/jesusdaniel/graphclass
공식 코드Network classification with applications to brain connectomics
https://github.com/jhayes14/UAN
공식 코드Learning Universal Adversarial Perturbations with Generative Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.