US 11,727,301 B2
Exploiting local inter-task relationships in adaptive multi-task learning
Bingshui Da, Singapore (SG); Chen Wang, Singapore (SG); Yew Soon Ong, Singapore (SG); and Abhishek Gupta, Singapore (SG)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Jul. 21, 2017, as Appl. No. 15/656,059.
Prior Publication US 2019/0026648 A1, Jan. 24, 2019
Int. Cl. G06N 20/00 (2019.01); G06F 7/14 (2006.01); G06F 16/28 (2019.01); G06N 7/01 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 7/14 (2013.01); G06F 16/285 (2019.01); G06N 7/01 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for adaptive multi-task learning (MTL), the method being executed by one or more processors and comprising:
receiving, by the one or more processors, a dataset, the dataset comprising a plurality of data values;
clustering, by the one or more processors, data values of the plurality of data values into a plurality of input feature clusters in input feature space;
training, by the one or more processors, a local multi-task Gaussian process (MTGP) for each input feature cluster to provide a set of local MTGPs, each local MTGP in the set of local MTGPs being associated with a respective input feature cluster and having optimized hyper-parameters in hyper-parameter space, an optimized hyper parameter being provided for each input feature cluster;
iteratively training a local learning MTGP (LL-MTGP) by:
merging hyper-parameters of two or more local MTGPs to provide a merged cluster representative of merged data values based on the optimized hyper-parameters,
initializing hyper-parameters of a local MTGP of the merged cluster as the hyper-parameters of one of the two or more local MTGPs, and
optimizing the hyper-parameters of the local MTGP of the merged cluster,
wherein iteratively training selectively ceases based on one or more distances between hyper-parameter clusters of the set of hyper-parameter clusters in the hyper-parameter space; and
providing, by the one or more processors, the LL-MTGP model to generate predictions.