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>

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Graph Classification

논문

Graph Contrastive Learning with Cohesive Subgraph Awareness

Graph Transformers without Positional Encodings

GPS: Graph Contrastive Learning via Multi-scale Augmented Views from Adversarial Pooling

Towards Causal Classification: A Comprehensive Study on Graph Neural Networks

EMP: Effective Multidimensional Persistence for Graph Representation Learning

Tensor-view Topological Graph Neural Network

Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification

GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection

Contrastive Learning with Negative Sampling Correction

On the Power of Graph Neural Networks and Feature Augmentation Strategies to Classify Social Networks

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks

Effective backdoor attack on graph neural networks in link prediction tasks

View-based Explanations for Graph Neural Networks

On the Expressive Power of Graph Neural Networks

On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions

Saliency-Aware Regularized Graph Neural Network

Domain Adaptive Graph Classification

Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns

Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity

LightGCN: Evaluated and Enhanced

Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings

Isomorphic-Consistent Variational Graph Auto-Encoders for Multi-Level Graph Representation Learning

On the Initialization of Graph Neural Networks

Recurrent Distance Filtering for Graph Representation Learning

On the Adversarial Robustness of Graph Contrastive Learning Methods

Disentangling the Spectral Properties of the Hodge Laplacian: Not All Small Eigenvalues Are Equal

Hard Label Black Box Node Injection Attack on Graph Neural Networks

Benchmarking Toxic Molecule Classification using Graph Neural Networks and Few Shot Learning

Exploring Graph Classification Techniques Under Low Data Constraints: A Comprehensive Study

Going beyond persistent homology using persistent homology

GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps

Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning

Diversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding

PSP: Pre-Training and Structure Prompt Tuning for Graph Neural Networks

BLIS-Net: Classifying and Analyzing Signals on Graphs