Papers with Code · CC BY-SA 4.0

PTC

아카이브 평가 37건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
U2GNN (Unsupervised)	Accuracy 91.81%	Universal Graph Transformer Self-Attention Networks 2019-09-26	코드 1
GIUNet	Accuracy 85.7%	Graph isomorphism UNet 2023-08-23	코드 1
GIC	Accuracy 77.64%	Gaussian-Induced Convolution for Graphs 2018-11-11	연결 없음
DUGNN	Accuracy 74.7%	Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning 2019-09-22	코드 1
UGraphEmb-F	Accuracy 73.56%	Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity 2019-04-01	코드 1
sGIN	Accuracy 73.56%	Mutual Information Maximization in Graph Neural Networks 2019-05-21	코드 1 · 코드 2
G_DenseNet	Accuracy 73.24%	When Work Matters: Transforming Classical Network Structures to Graph CNN 2018-07-07	연결 없음
CIN++	Accuracy 73.2%	CIN++: Enhancing Topological Message Passing 2023-06-06	코드 1
CAN	Accuracy 72.8%	Cell Attention Networks 2022-09-16	코드 1
UGraphEmb	Accuracy 72.54%	Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity 2019-04-01	코드 1
TFGW ADJ (L=2)	Accuracy 72.4%	Template based Graph Neural Network with Optimal Transport Distances 2022-05-31	코드 1
DGA	Accuracy 71.24%	Discriminative Graph Autoencoder 2018-11-17	연결 없음
U2GNN	Accuracy 69.63%	Universal Graph Transformer Self-Attention Networks 2019-09-26	코드 1
BC + Capsules	Accuracy 69%	Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations 2019-02-22	연결 없음
SEG-BERT	Accuracy 68.86%	Segmented Graph-Bert for Graph Instance Modeling 2020-02-09	코드 1
Spec-GN	Accuracy 68.05%	A New Perspective on the Effects of Spectrum in Graph Neural Networks 2021-12-14	코드 1
WEGL	Accuracy 67.5%	Wasserstein Embedding for Graph Learning 2020-06-16	코드 1
WWL	Accuracy 66.31%	Wasserstein Weisfeiler-Lehman Graph Kernels 2019-06-04	코드 1 · 코드 2
DropGIN	Accuracy 66.3%	DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks 2021-11-11	코드 1
PPGN	Accuracy 66.17%	Provably Powerful Graph Networks 2019-05-27	코드 1 · 코드 2
Deep WL SGN(0,1,2)	Accuracy 65.88%	Subgraph Networks with Application to Structural Feature Space Expansion 2019-03-21	연결 없음
DGCNN	Accuracy 65.43%	DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model 2017-12-10	연결 없음
hGANet	Accuracy 65.02%	Graph Representation Learning via Hard and Channel-Wise Attention Networks 2019-07-05	코드 1
GIN-0	Accuracy 64.40%	How Powerful are Graph Neural Networks? 2018-10-01	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19
cGANet	Accuracy 63.53%	Graph Representation Learning via Hard and Channel-Wise Attention Networks 2019-07-05	코드 1
DDGK	Accuracy 63.14%	DDGK: Learning Graph Representations for Deep Divergence Graph Kernels 2019-04-21	코드 1
GANet	Accuracy 62.94%	Graph Representation Learning via Hard and Channel-Wise Attention Networks 2019-07-05	코드 1
DAGCN	Accuracy 62.88%	DAGCN: Dual Attention Graph Convolutional Networks 2019-04-04	코드 1
SF + RFC	Accuracy 62.8%	A Simple Baseline Algorithm for Graph Classification 2018-10-22	코드 1 · 코드 2 · 코드 3
δ-2-LWL	Accuracy 62.70%	Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings 2019-04-02	코드 1