Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SGC

SGC

Reported on 11 benchmarks across 5 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Text ClassificationonR52
Accuracy· 2019-02-19
94
best: 96.6 (1-6 BertGCN)
SOTA
Simplifying Graph Convolutional Networks arXiv:1902.07153
Text ClassificationonR8
Accuracy· 2019-02-19
97.2
best: 98.451 (DeBERTa)
SOTA
Simplifying Graph Convolutional Networks arXiv:1902.07153
Text Classificationon20NEWS
Accuracy· uses extra data· 2019-02-19
88.5
best: 93 (LinearSVM+TFIDF)
SOTA
Simplifying Graph Convolutional Networks arXiv:1902.07153
Sentiment AnalysisonMR
Accuracy· 2019-02-19
75.9
best: 93.3 (VLAWE)
Simplifying Graph Convolutional Networks arXiv:1902.07153
Text ClassificationonOhsumed
Accuracy· 2019-02-19
68.5
best: 72.8 (RoBERTaGCN)
Simplifying Graph Convolutional Networks arXiv:1902.07153

Methodology4 results

ClassificationonR52
Accuracy· 2019-02-19
94
best: 96.6 (1-6 BertGCN)
SOTA
Simplifying Graph Convolutional Networks arXiv:1902.07153
ClassificationonR8
Accuracy· 2019-02-19
97.2
best: 98.451 (DeBERTa)
SOTA
Simplifying Graph Convolutional Networks arXiv:1902.07153
Classificationon20NEWS
Accuracy· uses extra data· 2019-02-19
88.5
best: 93 (LinearSVM+TFIDF)
SOTA
Simplifying Graph Convolutional Networks arXiv:1902.07153
ClassificationonOhsumed
Accuracy· 2019-02-19
68.5
best: 72.8 (RoBERTaGCN)
Simplifying Graph Convolutional Networks arXiv:1902.07153

Graphs2 results

Graph RegressiononLipophilicity
RMSE· 2019-02-19
0.998
best: 0.58 (ProtoS-L2)
Simplifying Graph Convolutional Networks arXiv:1902.07153
Node Property Predictiononogbn-papers100M
Number of params· 2019-02-19
144044
best: 14215818412 (Node2vec)
Simplifying Graph Convolutional Networks arXiv:1902.07153