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.
Reinforcement Learning For Data Poisoning on Graph Neural Networks
Improving Scene Graph Classification by Exploiting Knowledge from Texts
Enhance Information Propagation for Graph Neural Network by Heterogeneous Aggregations
Learning Graph Representations
Graph Classification Based on Skeleton and Component Features
Efficient Graph Deep Learning in TensorFlow with tf_geometric
Learning Parametrised Graph Shift Operators
Identity-aware Graph Neural Networks
SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism
GraphAttacker: A General Multi-Task GraphAttack Framework
Membership Inference Attack on Graph Neural Networks
Label Contrastive Coding based Graph Neural Network for Graph Classification
Optimisation of Spectral Wavelets for Persistence-based Graph Classification
The Shapley Value of Classifiers in Ensemble Games
LookHops: light multi-order convolution and pooling for graph classification
Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification
On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insights
An Experimental Study of the Transferability of Spectral Graph Networks
Hierarchical Graph Capsule Network
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs
Decimated Framelet System on Graphs and Fast G-Framelet Transforms
CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
LCS Graph Kernel Based on Wasserstein Distance in Longest Common Subsequence Metric Space
A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources
Classification by Attention: Scene Graph Classification with Prior Knowledge
Graph-Based Neural Network Models with Multiple Self-Supervised Auxiliary Tasks
Two-stage Training of Graph Neural Networks for Graph Classification
Parameterized Explainer for Graph Neural Network
Sampling and Recovery of Graph Signals based on Graph Neural Networks
Dark Reciprocal-Rank: Boosting Graph-Convolutional Self-Localization Network via Teacher-to-student Knowledge Transfer
Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
Graph embedding using multi-layer adjacent point merging model
On Graph Neural Networks versus Graph-Augmented MLPs
Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies
GraphMDN: Leveraging graph structure and deep learning to solve inverse problems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.