Table 11. Fusion embeddings on Cora for link prediction (micro-F1, metric lies between (0,1) and higher value means better results).

% Train Edges	5%	10%	30%	50%
TADW - BoW	0.72 ± 0.02	0.72 ± 0.01	0.73 ± 0.01	0.73 ± 0.01
TADW - TF-IDF	0.73 ± 0.02	0.74 ± 0.01	0.74 ± 0.01	0.75 ± 0.01
TADW - Sent2Vec	0.70 ± 0.01	0.70 ± 0.01	0.71 ± 0.00	0.73 ± 0.00
TADW - Word2Vec	0.64 ± 0.01	0.68 ± 0.00	0.71 ± 0.01	0.72 ± 0.01
TADW - Ernie	0.51 ± 0.01	0.53 ± 0.01	0.54 ± 0.01	0.54 ± 0.01
GCN - TF-IDF	0.78 ± 0.01	0.78 ± 0.01	0.79 ± 0.01	0.80 ± 0.01
GCN - Sent2Vec	0.69 ± 0.01	0.71 ± 0.01	0.73 ± 0.01	0.75 ± 0.01
GCN - SBERT	0.67 ± 0.01	0.69 ± 0.01	0.71 ± 0.01	0.73 ± 0.01
GCN (Custom)	0.72 ± 0.01	0.75 ± 0.01	0.75 ± 0.01	0.75 ± 0.01
GCN - Ernie	0.62 ± 0.01	0.63 ± 0.00	0.63 ± 0.00	0.68 ± 0.01
GAT - TF-IDF	0.71 ± 0.01	0.73 ± 0.01	0.75 ± 0.01	0.75 ± 0.01
GAT - Sent2Vec	0.61 ± 0.01	0.61 ± 0.01	0.65 ± 0.01	0.68 ± 0.01
GAT - SBERT	0.65 ± 0.01	0.69 ± 0.01	0.72 ± 0.01	0.74 ± 0.01
GAT - Ernie	0.56 ± 0.01	0.56 ± 0.02	0.59 ± 0.01	0.62 ± 0.01
GraphSAGE - TF-IDF	0.75 ± 0.01	0.78 ± 0.01	0.79 ± 0.01	0.80 ± 0.01
GraphSAGE - Sent2Vec	0.66 ± 0.01	0.70 ± 0.01	0.74 ± 0.01	0.75 ± 0.01
GraphSAGE - SBERT	0.58 ± 0.01	0.62 ± 0.01	0.69 ± 0.01	0.64 ± 0.01
GraphSAGE - Ernie	0.50 ± 0.01	0.50 ± 0.01	0.53 ± 0.01	0.56 ± 0.01
GIC - TF-IDF	0.73 ± 0.01	0.75 ± 0.01	0.77 ± 0.01	0.78 ± 0.01
GIC - Sent2Vec	0.74 ± 0.01	0.75 ± 0.01	0.77 ± 0.01	0.78 ± 0.01
GIC - SBERT	0.74 ± 0.01	0.76 ± 0.01	0.78 ± 0.01	0.80 ± 0.01
GIC - Ernie	0.65 ± 0.01	0.69 ± 0.01	0.69 ± 0.01	0.74 ± 0.01

Note:

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