Table 1. Text methods on Cora for node classification (micro-F1, metric lies between (0,1) and higher value means better results).

% Labels	5%	10%	30%	50%
BoW	0.63 ± 0.01	0.68 ± 0.01	0.76 ± 0.01	0.78 ± 0.01
TF-IDF	0.35 ± 0.01	0.49 ± 0.01	0.70 ± 0.01	0.76 ± 0.01
LDA	0.49 ± 0.01	0.57 ± 0.01	0.60 ± 0.01	0.61 ± 0.01
SBERT pretrained	0.57 ± 0.01	0.61 ± 0.01	0.68 ± 0.01	0.70 ± 0.01
Word2Vec pretrained	0.34 ± 0.01	0.44 ± 0.01	0.59 ± 0.01	0.63 ± 0.01
Word2Vec (d = 300)	0.64 ± 0.01	0.68 ± 0.01	0.70 ± 0.01	0.71 ± 0.01
Word2Vec (d = 64)	0.65 ± 0.01	0.68 ± 0.01	0.70 ± 0.01	0.72 ± 0.01
Doc2Vec pretrained	0.54 ± 0.01	0.61 ± 0.00	0.65 ± 0.01	0.67 ± 0.01
Doc2Vec (d = 300)	0.49 ± 0.01	0.58 ± 0.01	0.66 ± 0.01	0.68 ± 0.01
Doc2Vec (d = 64)	0.50 ± 0.02	0.58 ± 0.01	0.65 ± 0.00	0.67 ± 0.01
Sent2Vec pretrained	0.63 ± 0.02	0.69 ± 0.01	0.74 ± 0.01	0.77 ± 0.01
Sent2Vec (d = 600)	0.68 ± 0.02	0.72 ± 0.01	0.75 ± 0.01	0.77 ± 0.01
Sent2Vec (d = 64)	0.68 ± 0.02	0.72 ± 0.01	0.75 ± 0.01	0.77 ± 0.01
Ernie pretrained	0.43 ± 0.01	0.52 ± 0.01	0.62 ± 0.01	0.65 ± 0.01

Note:

The best values with respect to confidence intervals are highlighted in bold.