Call For Papers
This half-day workshop (in conjunction with IEEE Big Data 2018) is a continuation of our pre-vious Big Data Transfer Learning (BDTL) workshops (1st BDTL, 2nd BDTL) which will provide a focused international forum to bring together researchers and research groups to review the status of transfer learning, domain adaptation, and multi-view learning. Specifically, we will discuss the challenges given enormous weakly labeled source/auxiliary data for learning tasks on the target data, and to explore future directions particularly in the unconstrained social environments, such as social media data in the cloud, Facebook and YouTube applications. The workshop will consist of one to two invited talks together with peer-reviewed regular papers (oral and poster). Original high-quality papers are solicited on a wide range of topics including:
1. New perspective, concepts, or theories on transfer learning, or domain adaptation
2. Web-scale transfer learning, especially from loosely organized source to unlabeled target data
3. Novel applications of transfer learning in the emerging fields
4. Real-time knowledge transfer for large-scale social stream
5. Large-scale transfer learning with latent, complex, or noisy source domain
6. Unsupervised multi-view learning, multi-view clustering, multi-view anomaly detec-tion
7. Multi-view feature learning, and feature selection
8. Supervised multi-view learning, zero-shot learning, and view-unknown learning
9. Deep architecture and modeling for transfer learning, domain adaptation, multi-view learning
10. New datasets, benchmarks, and open-source software for transfer learning and mul-ti-view learning