GRACE

Reported on 4 benchmarks across 3 tasks · 2 papers · 3 SOTA

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

Natural Language Processing3 results

Sentiment AnalysisonSemEval 2014 Task 4 Subtask 1+2
F1· 2020-09-22
70.71
best: 83.76 (gpt-3.5 finetuned)
SOTA
GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis arXiv:2009.10557
Aspect-Based Sentiment Analysis (ABSA)onSemEval 2014 Task 4 Subtask 1+2
F1· 2020-09-22
70.71
best: 83.76 (gpt-3.5 finetuned)
SOTA
GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis arXiv:2009.10557
Sentiment AnalysisonSemEval 2014 Task 4 Subtask 1+2
F1· 2020-09-22
70.71
best: 83.76 (gpt-3.5 finetuned)
GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis arXiv:2009.10557

Graphs2 results

Node ClassificationonPPI
Micro-F1· 2020-06-07
66.2
SOTA
Deep Graph Contrastive Representation Learning arXiv:2006.04131
Node ClassificationonPPI
F1· 2020-06-07
66.2
best: 99.71 (g2-MLP)
Deep Graph Contrastive Representation Learning arXiv:2006.04131