Selective Random Walk for Transfer Learning in Heterogeneous Label Spaces

Qiao Xiao1; Yu Zhang2; Qiang Yang3

2024

10.1109/TPAMI.2024.3360118

IEEE Transactions on Pattern Analysis and Machine Intelligence   影响因子和分区

1939-3539

1939-3539

Transfer learning has been widely used in different scenarios, especially in those lacking enough labeled data. However, most of the existing transfer learning methods are based on the assumption that the source and target domains should share the label space entirely or partially, which greatly limits their application scopes. In this article, a Selective Random Walk (SRW) method for transfer learning in heterogeneous label spaces is proposed to make full use of unlabeled auxiliary data, which acts as a bridge for knowledge transfer from the source domain to the target domain. The proposed SRW method can explicitly identify transfer sequences between source and target instances via auxiliary instances based on random walk techniques. Since not all of the transfer sequences generated by random walk are credible for the target task, the SRW method can learn to weight transfer sequences adaptively. Based on the weights of the transfer sequences, the SRW method leverages knowledge by forcing adjacent data points in the transfer sequence to be similar and making the target data point in the sequence represented by other data points in the same sequence. Experiments show that the SRW method outperforms state-of-the-art models in plenty of transfer learning tasks with heterogeneous label spaces constructed within and across several benchmark datasets.

Heterogeneous label spaces selective random walk transfer learning

SCI ; EI

英语

其他

ENGINEERING

2-s2.0-85184335665

IEEE

1.Department of Mathematics and Computer Science, Eindhoven University of Technology, Netherlands
2.Department of Computer Science and Engineering, Southern University of Science and Technology and Peng Cheng Laboratory, USA
3.Department of Computer Science and Engineering, Hong Kong University of Science and Technology, China

Qiao Xiao,Yu Zhang,Qiang Yang. Selective Random Walk for Transfer Learning in Heterogeneous Label Spaces[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,PP(99):1-12.

Qiao Xiao,Yu Zhang,&Qiang Yang.(2024).Selective Random Walk for Transfer Learning in Heterogeneous Label Spaces.IEEE Transactions on Pattern Analysis and Machine Intelligence,PP(99),1-12.

Qiao Xiao,et al."Selective Random Walk for Transfer Learning in Heterogeneous Label Spaces".IEEE Transactions on Pattern Analysis and Machine Intelligence PP.99(2024):1-12.