Mahardhika Pratama, Marcus De Carvalho, Renchunzi Xie, Edwin Lughofer, Jie Lu,
"ATL: Autonomous Knowledge Transfer from Many Streaming Processes"
: Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM) 2019, Serie Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM), ACM press, 2019
Original Titel:
ATL: Autonomous Knowledge Transfer from Many Streaming Processes
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM) 2019
Original Kurzfassung:
Transferring knowledge across many streaming processes remains
an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the target domain, covariate shift of source and target domain, different period of drifts in the source and target domains. Autonomous transfer learning (ATL) is proposed in this paper as a flexible deep learning approach for the online unsupervised transfer learning problem across many streaming
processes. ATL offers an online domain adaptation strategy
via the generative and discriminative phases coupled with the KL divergence based optimization strategy to produce a domain invariant network while putting forward an elastic network structure. It automatically evolves its network structure from scratch with/without the presence of ground truth to overcome independent concept drifts in the source and target domain. Rigorous numerical evaluation has been conducted along with comparison against recently published works. ATL demonstrates improved performance while showing significantly faster training speed than its counterparts.
Sprache der Kurzfassung:
Englisch
Veröffentlicher:
ACM press
Serie:
Proceedings of the 28th ACM International Conference on Information and Knowledge Management (CIKM)