Skip to main content

Table 1 Summary of the proposed formulations. DKL KL u MathType@MTEF@5@5@+=feaafiart1ev1aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacPC6xNi=xH8viVGI8Gi=hEeeu0xXdbba9frFj0xb9qqpG0dXdb9aspeI8k8fiI+fsY=rqGqVepae9pg0db9vqaiVgFr0xfr=xfr=xc9adbaqaaeGaciGaaiaabeqaaeqabiWaaaGcbaGaeeiraqKaee4saSKaeeitaW0aa0baaSqaaiabbUealjabbYeambqaaiabbwha1baaaaa@32FA@

From: Adaptive diffusion kernel learning from biological networks for protein function prediction

Algorithm Single task Multiple tasks Convexity Constraint
DKL  
DKLKL   
DKL KL u MathType@MTEF@5@5@+=feaafiart1ev1aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacPC6xNi=xH8viVGI8Gi=hEeeu0xXdbba9frFj0xb9qqpG0dXdb9aspeI8k8fiI+fsY=rqGqVepae9pg0db9vqaiVgFr0xfr=xfr=xc9adbaqaaeGaciGaaiaabeqaaeqabiWaaaGcbaGaeeiraqKaee4saSKaeeitaW0aa0baaSqaaiabbUealjabbYeambqaaiabbwha1baaaaa@32FA@    
mDKL  
mDKLKL    
mDKL KL u MathType@MTEF@5@5@+=feaafiart1ev1aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacPC6xNi=xH8viVGI8Gi=hEeeu0xXdbba9frFj0xb9qqpG0dXdb9aspeI8k8fiI+fsY=rqGqVepae9pg0db9vqaiVgFr0xfr=xfr=xc9adbaqaaeGaciGaaiaabeqaaeqabiWaaaGcbaGaeeyBa0MaeeiraqKaee4saSKaeeitaW0aa0baaSqaaiabbUealjabbYeambqaaiabbwha1baaaaa@345B@     
  1. These formulations are categorized in terms of the number of tasks, convexity, and whether the weights on kernels are constrained. DKLKL, DKL, and DKL KL u MathType@MTEF@5@5@+=feaafiart1ev1aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacPC6xNi=xH8viVGI8Gi=hEeeu0xXdbba9frFj0xb9qqpG0dXdb9aspeI8k8fiI+fsY=rqGqVepae9pg0db9vqaiVgFr0xfr=xfr=xc9adbaqaaeGaciGaaiaabeqaaeqabiWaaaGcbaGaeeiraqKaee4saSKaeeitaW0aa0baaSqaaiabbUealjabbYeambqaaiabbwha1baaaaa@32FA@ denote formulations using the Kullback-Leibler (KL) divergence criterion, the KL divergence criterion with the log term removed and the unconstrained version for single task, respectively. A lower case m is added before each method to denote the corresponding formulations for multiple tasks.