Table 4 Performance comparison of different models on the FB15K-237 and WN18RR datasets with m=60%.

From: An enhanced framework for knowledge graph embedding based on negative sample analogical reasoning

Model

FB15K-237

WN18RR

MRR

Hit@1

Hit@3

Hit@10

MRR

Hit@1

Hit@3

Hit@10

TransE7

0.329

0.230

0.368

0.526

0.223

0.014

0.401

0.530

RotatE9

0.337

0.241

0.374

0.531

0.473

0.427

0.495

0.568

ANALOGY20

0.256

0.165

0.290

0.436

0.405

0.363

0.429

0.474

HAKE10

0.349

0.252

0.385

0.545

0.496

0.452

0.513

0.580

Rot-Pro36

0.344

0.246

0.383

0.540

0.457

0.397

0.482

0.577

PairRE24

0.348

0.254

0.384

0.539

0.455

0.413

0.469

0.539

DualE27

0.365

0.268

0.400

0.559

0.492

0.444

0.513

0.584

CompGCN32

0.355

0.264

0.390

0.535

0.479

0.443

0.494

0.546

SE-GNN33

0.365

0.271

0.399

0.549

0.484

0.446

0.509

0.572

KBGAT17

0.365

0.268

0.400

0.559

0.492

0.444

0.513

0.584

PUDA18

0.369

0.268

0.408

0.578

0.481

0.436

0.498

0.582

REP19

0.354

0.262

0.388

0.540

0.488

0.439

0.505

0.588

AnKGE20

0.385

0.288

0.428

0.572

0.500

0.454

0.515

0.587

Ne_AnKGE (Ours)

0.394

0.286

0.443

0.606

0.505

0.455

0.526

0.603

  1. The bold and italic mean the best and the second best results for each metric, respectively.
Back to article page