ATL: Autonomous Knowledge Transfer from Many Streaming Processes
This work addresses a novel problem in online unsupervised transfer learning for streaming data, which is incremental as it builds on existing transfer learning approaches but targets a specific, uncharted scenario.
The paper tackles the problem of transferring knowledge across many streaming processes without labeled target data, addressing covariate shift and independent concept drifts, and proposes Autonomous Transfer Learning (ATL), which demonstrates improved performance and significantly faster training speed compared to existing methods.
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. The rigorous numerical evaluation has been conducted along with a comparison against recently published works. ATL demonstrates improved performance while showing significantly faster training speed than its counterparts.