DLKT - The 1st Pacific Asia Workshop on Deep Learning for Knowledge Transfer
- Fuzhen Zhuang (Institute of Computing Technology, Chinese Academy of Sciences, China)
- Deqing Wang (Beihang university, China)
- Pengpeng Zhao (Soochow University, China)
email@example.com; firstname.lastname@example.org; email@example.com.
Previous supervised learning algorithms mainly assume that there are plenty of i.i.d. sampled labeled data to train a good model for test data. However, this assumption does not always hold in real-world applications, since labeling data is time consuming and labor tedious. Furthermore, the test data are usually sampled the distribution which is different from the one of training data. The advanced algorithms based on knowledge transfer or sharing provide an effective way to handle this issue, e.g., transfer learning, multi-task learning and multi-view learning, since they either try to handle the distribution mismatch problem or the shortage of labeled data.
In recent years, deep learning has been proved to have the ability to learn powerful representations for various kinds of tasks. On the one hand, although there are large amount of previous works based on knowledge transfer or sharing, there are only small amount of them applying deep learning techniques. In this workshop, we aim to bring researchers and practitioners who work on various aspects of advanced knowledge transfer algorithms based on deep learning techniques, to discuss on the state-of-the-art and open problems, to share their expertise and exchange the ideas, and to offer them an opportunity to identify new promising research directions.
This workshop solicits papers whose topics fall into (but not limited to) the following categories:
- Transfer learning based on deep learning techniques.
- Multi-task learning based on deep learning techniques.
- Multi-view learning based on deep learning techniques.
- The applications of knowledge transfer and sharing algorithms in real worlds.
- Knowledge transfer for zero-shot learning.
- Applications of deep learning and knowledge transfer for recommender systems.
**** This workshop will be co-held with the PAKDD 2019 in Macau, China, and conference date is
April 14-17, 2019.
**** The submission deadline is extended to Dec 22, 2018 (one week later than the original date Dec 15, 2018), and the submission website is:
**** The notification date is Jan 20, 2019.
**** Some excellent DLKT 2019 papers will be selected to extended to International Journal of Machine Learning and Computing ( IJMLC ), which is indexed by SCI.