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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Semi-Supervised Hierarchical Graph Classification
Fundamental Limits in Formal Verification of Message-Passing Neural Networks
Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction
Metric Based Few-Shot Graph Classification
A Simple yet Effective Method for Graph Classification
Multi-scale Wasserstein Shortest-path Graph Kernels for Graph Classification
Shortest Path Networks for Graph Property Prediction
Approximate Network Motif Mining Via Graph Learning
Automatic Relation-aware Graph Network Proliferation
Template based Graph Neural Network with Optimal Transport Distances
CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning
Recipe for a General, Powerful, Scalable Graph Transformer
Compressing Deep Graph Neural Networks via Adversarial Knowledge Distillation
High-Order Pooling for Graph Neural Networks with Tensor Decomposition
Asynchronous Neural Networks for Learning in Graphs
GraphMAE: Self-Supervised Masked Graph Autoencoders
KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification
Towards Explanation for Unsupervised Graph-Level Representation Learning
Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis
Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis
Label-invariant Augmentation for Semi-Supervised Graph Classification
GraphHD: Efficient graph classification using hyperdimensional computing
Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower Bound
Spatial-temporal associations representation and application for process monitoring using graph convolution neural network
NDGGNET-A Node Independent Gate based Graph Neural Networks
Data-Free Adversarial Knowledge Distillation for Graph Neural Networks
Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees
Clustered Graph Matching for Label Recovery and Graph Classification
FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs
Spiking Graph Convolutional Networks
HL-Net: Heterophily Learning Network for Scene Graph Generation
FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation
DOTIN: Dropping Task-Irrelevant Nodes for GNNs
LiftPool: Lifting-based Graph Pooling for Hierarchical Graph Representation Learning
Reinforced Causal Explainer for Graph Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.