Multi-Label Feature Selection with Conditional Mutual Information

Table 3

Average Precision of results after applying multi-label feature selection algorithms on ten datasets.

Algorithms	CRMIL	SCLS	D2F	FIMF	PMU	AMI	NMDG	FSSL	MFS-MCDM
Corel5k	0.0161	0.0139	0.0139	0.0138	0.0139	0.0139	0.0139	0.0140	0.0138
Delicious	0.0317	0.0238	0.0195	0.0203	0.0205	0.0292	0.0245	0.0258	0.0241
Flags	0.7852	0.6405	0.6947	0.7620	0.6986	0.7060	0.7122	0.7291	0.6972
Medical	0.1130	0.0553	0.0770	0.0553	0.0771	0.0589	0.0649	0.0692	0.0625
Scene	0.7487	0.7222	0.7085	0.6408	0.7048	0.6441	0.7256	0.7283	0.7204
Enron	0.5467	0.5138	0.5109	0.5017	0.5083	0.4892	0.5591	0.5337	0.5273
GenBase	0.8628	0.7549	0.7428	0.7025	0.7136	0.7813	0.8072	0.8114	0.7739
Social	0.5832	0.5479	0.5212	0.5153	0.5159	0.5427	0.5576	0.5593	0.5491
Yeast	0.7832	0.7582	0.7419	0.7404	0.7327	0.7493	0.7701	0.7679	0.7620
Emotions	0.7933	0.7701	0.7628	0.7634	0.7593	0.7631	0.7729	0.7814	0.7796
Average	0.5264	0.4801	0.4793	0.4716	0.4745	0.4778	0.5008	0.5020	0.4910