Table 4. Clustering performance of multi-SNE variations.

For each data set, bold highlights the multi-SNE variation with the best performance - highest accuracy (ACC). Perplexity was optimised for all variations. The mean performance (and its standard deviation) is depicted for the synthetic data sets NDS and MCS).

Variation	Handwritten digits	Cancer types	Caltech7 original	Caltech7 balanced	NDS	MCS
Multi-SNE without weight-adjustment	0.822	0.964	0.506	0.733	0.989 (0.006)	0.919 (0.046)
Multi-SNE with weight-adjustment	0.883	0.994	0.543	0.742	0.999 (0.002)	0.922 (0.019)
Multi-CCA multi-SNE without weight-adjustment	0.901	0.526	0.453	0.713	0.996(0.002)	0.993 (0.005)
Multi-CCA multi-SNE with weight-adjustment	0.914	0.562	0.463	0.754	0.996 (0.002)	0.993 (0.005)