Automatic online multi-source domain adaptation

Knowledge transfer across several streaming processes remain challenging problem not only because of different distributions of each stream but also because of rapidly changing and never-ending environments of data streams. Albeit growing research achievements in this area, most of existing works are developed for a single source domain which limits its resilience to exploit multi-source domains being beneficial to recover from concept drifts quickly and to avoid the negative transfer problem. An online domain adaptation technique under multi-source streaming processes, namely automatic online multi-source domain adaptation (AOMSDA), is proposed in this paper. The online domain adaptation strategy of AOMSDA is formulated under a coupled generative and discriminative approach of denoising autoencoder (DAE) where the central moment discrepancy (CMD)-based regularizer is integrated to handle the existence of multi-source domains thereby taking advantage of complementary information sources. The asynchronous concept drifts taking place at different time periods are addressed by a self-organizing structure and a node re weighting strategy. Our numerical study demonstrates that AOMSDA is capable of outperforming its counterparts in 5 of 8 study cases while the ablation study depicts the advantage of each learning component. In addition, AOMSDA is general for any number of source streams. The source code of AOMSDA is shared publicly in https://github.com/RenchunziXie/AOMSDA.git. (c) 2021 Elsevier Inc. All rights reserved.

Automated summary

Despite the challenging problem of knowledge transfer across multiple streaming processes, the proposed automatic online multi-source domain adaptation (AOMSDA) technique effectively addresses the issue by integrating a central moment discrepancy (CMD)-based regularizer under a coupled generative and discriminative approach of denoising autoencoder (DAE). Numerical studies show that AOMSDA outperforms its counterparts in 5 out of 8 cases, with ablation studies highlighting the advantages of each learning component. AOMSDA is also generalizable for any number of source streams and the source code is publicly available.