PK PyTorchKR Papers
Papers with Code · CC BY-SA 4.0

Node Classification

2,279 평가 기록 163 datasets

Node Classification is a machine learning task in graph-based data analysis, where the goal is to assign labels to nodes in a graph based on the properties of nodes and the relationships between them.

Node Classification models aim to predict non-existing node properties (known as the target property) based on other node properties. Typical models used for node classification consists of a large family of graph neural networks. Model performance can be measured using benchmark datasets like Cora, Citeseer, and Pubmed, among others, typically using Accuracy and F1.

<span style="color:grey; opacity: 0.6">( Image credit: Fast Graph Representation Learning With PyTorch Geometric )</span>

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode
SSP
Accuracy: 90.16% ± 0.59%
논문 코드
ACMII-Snowball-2
Accuracy: 82.07 ± 1.04
논문 -
NCGCN
Accuracy: 91.64 ± 0.53
논문 코드
5-HiGCN
Accuracy: 94.99±0.65
논문 코드
NCSAGE
Accuracy: 43.89 ± 1.33
논문 코드
RDGNN-S
Accuracy: 94.59 ± 5.97
논문 -
DJ-GNN
Accuracy: 80.48±1.46
논문 코드
RDGNN-I
Accuracy: 92.72 ± 5.88
논문 -
FaberNet
Accuracy: 76.71±1.92
논문 코드
OGC
Accuracy: 77.5
논문 코드
GNNDLD
1:1 Accuracy: 79.78±1.66
논문 -
GNNDLD
1:1 Accuracy: 75.69±0.78
논문 -

데이터셋

163개
CoraCiteseerPubmedWisconsinActorTexasChameleonCornellSquirrelCiteSeer with Public Split: fixed 20 nodes per classChameleon (60%/20%/20% random splits)Film (60%/20%/20% random splits)

논문

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/benedekrozemberczki/karateclub 4 논문
github.com/shenweichen/GraphEmbedding 4 논문
github.com/liuxinkai94/Graph-embedding 3 논문
github.com/printfer/CS6490_NetworkSecurity_FinalProject 2 논문
github.com/Robotmurlock/Deepwalk-and-Node2vec 2 논문
github.com/leihuayi/NetworkEmbedding 2 논문
github.com/ninoxjy/graph-embedding 2 논문
github.com/zxhhh97/ABot 2 논문

하위 태스크

NC Node Classification on Non-Homophilic (Heterophilic) Graphs 15 데이터셋 · 401 rows HN Heterogeneous Node Classification 7 데이터셋 · 66 rows AN Atomic number classification 2 데이터셋 · 18 rows GS Graph structure learning 1 데이터셋 · 1 rows DN Dynamic Node Classification 0 데이터셋 · 0 rows