Table 12. Fusion embeddings on Citeseer-M10 for link prediction (micro-F1, metric lies between (0,1) and higher value means better results).

% Train Edges	5 %	10 %	30 %	50 %
TADW - BoW	0.50 ± 0.01	0.51 ± 0.02	0.51 ± 0.01	0.52 ± 0.01
TADW - TF-IDF	0.51 ± 0.01	0.51 ± 0.01	0.51 ± 0.01	0.52 ± 0.01
TADW - Sent2Vec	0.52 ± 0.01	0.53 ± 0.00	0.53 ± 0.00	0.54 ± 0.00
TADW - Word2Vec	0.52 ± 0.01	0.52 ± 0.01	0.53 ± 0.00	0.53 ± 0.00
TADW - Ernie	0.74 ± 0.01	0.75 ± 0.01	0.77 ± 0.02	0.78 ± 0.01
GCN - TF-IDF	0.68 ± 0.01	0.69 ± 0.01	0.70 ± 0.01	0.70 ± 0.01
GCN - Sent2Vec	0.59 ± 0.01	0.62 ± 0.01	0.67 ± 0.01	0.68 ± 0.01
GCN - SBERT	0.68 ± 0.01	0.70 ± 0.01	0.72 ± 0.01	0.77 ± 0.01
GCN (Custom)	0.61 ± 0.01	0.67 ± 0.00	0.68 ± 0.01	0.68 ± 0.01
GCN - Ernie	0.67 ± 0.01	0.67 ± 0.01	0.76 ± 0.00	0.78 ± 0.01
GAT - TF-IDF	0.60 ± 0.01	0.63 ± 0.01	0.65 ± 0.01	0.64 ± 0.01
GAT - Sent2Vec	0.59 ± 0.01	0.63 ± 0.01	0.64 ± 0.01	0.63 ± 0.01
GAT - SBERT	0.61 ± 0.01	0.65 ± 0.01	0.71 ± 0.01	0.73 ± 0.01
GAT - Ernie	0.61 ± 0.00	0.64 ± 0.01	0.69 ± 0.01	0.70 ± 0.01
GraphSAGE - TF-IDF	0.66 ± 0.01	0.67 ± 0.01	0.73 ± 0.01	0.78 ± 0.01
GraphSAGE - Sent2Vec	0.64 ± 0.01	0.66 ± 0.01	0.73 ± 0.01	0.78 ± 0.01
GraphSAGE - SBERT	0.61 ± 0.01	0.63 ± 0.01	0.71 ± 0.01	0.83 ± 0.01
GraphSAGE - Ernie	0.63 ± 0.02	0.72 ± 0.01	0.72 ± 0.01	0.80 ± 0.01
GIC - TF-IDF	0.62 ± 0.01	0.66 ± 0.01	0.74 ± 0.01	0.80 ± 0.01
GIC - Sent2Vec	0.62 ± 0.01	0.66 ± 0.01	0.75 ± 0.01	0.81 ± 0.01
GIC - SBERT	0.63 ± 0.01	0.66 ± 0.01	0.75 ± 0.01	0.78 ± 0.01
GIC - Ernie	0.63 ± 0.01	0.66 ± 0.00	0.73 ± 0.01	0.81 ± 0.00

Note:

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