A Fast Clustering Algorithm for Data with a Few Labeled Instances

Table 1

The information of benchmark datasets.

Dataset	Abbr.	#Class	#Attr	Size
Balance	Bal	3	4	625
Breast Cancer Wisconsin	BCW	2	9	699
Credit	Cre	2	15	653
Ecoli	Eco	8	7	336
Hepatitis	Hep	2	19	155
Housing	Hou	3	13	506
Ionosphere	Ion	2	34	351
Iris	Iri	3	4	150
mfeat-fac	Mff	10	216	2000
mfeat-pix	Mfp	10	240	2000
Pima	Pim	2	8	768
Promoters	Pro	2	57	106
Segmentation	Seg	7	19	2310
Sick	Sic	2	29	3772
Soybean	Soy	4	35	47
Splice	Spl	3	60	3175
Voting	Vot	2	16	435
Wine	Win	3	13	178
Yeast	Yea	10	8	1484
Zoo	Zoo	7	17	101