Label Distribution Learning by Regularized Sample Self-Representation

Table 4

Clark Distance (mean std) × 10³ of different algorithms on the twelve datasets. The best results are enlightened in bold and the second best results are italicized.

Algorithms	PT-SVM	AA-BP	SA-IIS	SA-BFGS	RSSR-LDL2	RSSR-LDL21
Movie	871.2 77.4	643.8 11.8	553.6 12.9	551.8 10.7	521.4 5.4	514.7 10.6
SBU-3DFE	430.1 16.3	469.7 25.2	410.0 9.0	348.5 11.4	390.2 5.6	380.0 2.9
SJAFFE	437.9 26.8	508.0 46.4	417.6 18.1	420.0 36.6	366.9 36.3	348.5 18.1
Yeast-alpha	220.9 5.1	752.2 54.1	260.4 4.2	210.0 6.7	209.3 5.3	209.2 5.9
Yeast-cdc	228.1 8.9	585.1 27.1	258.9 4.6	215.8 3.5	215.1 5.5	214.7 5.7
Yeast-cold	155.9 10.0	156.9 5.7	153.1 5.7	139.5 6.3	139.3 4.8	139.0 5.7
Yeast-diau	235.3 20.4	270.7 12.0	222.2 7.0	200.5 6.9	200.3 5.1	200.1 6.2
Yeast-dtt	104.7 6.3	121.6 6.5	116.3 5.2	98.3 5.5	98.0 3.9	97.9 4.9
Yeast-elu	210.9 4.5	528.0 40.0	240.5 7.1	198.9 5.8	198.3 5.3	198.3 4.2
Yeast-heat	190.3 5.8	242.0 20.4	200.5 4.7	182.7 5.0	182.3 6.2	182.0 4.1
Yeast-spo	272.4 11.3	287.5 12.5	263.7 5.8	249.6 11.9	249.4 11.4	248.7 8.5
Yeast-spo5	187.0 8.6	192.1 8.8	190.1 4.8	184.3 7.2	183.7 8.8	183.7 6.9