Skip to main content

Table 3 Surveyed HTL methods which require no target labels

From: A survey on heterogeneous transfer learning

Methods Characteristics Sections
CT-SVM [70] Symmetric, CCA, transfer SVM CT-SVM
HHTL [71] Asymmetric, requires source-target correspondence data, deep learning, mSDA HHTL
HDCC [76] Symmetric, CCA, group-weighing, video annotation, multi-source HDCC
CL-SCL [78] Symmetric, structural correspondence learning, text classification CL-SCL
HDP [80] Asymmetric through metric selection and matching HDP
FuzzyTL [85] Fuzzy logic, intelligent environments, FIS FuzzyTL
UFSR [12] Asymmetric, domain-dependent metafeatures to compute similarity FSR (IFSR, UFSR, ELFSR)
ELFSR [12] Asymmetric, FSR ensemble, multi-source, voting method FSR (IFSR, UFSR, ELFSR)
RLG, GLG [11] Symmetric, LMM, Grassmann manifold RLG, GLG