![]() |
| |||||||||||||||
TLWorkshop 2015 : (Deadline Extended to 10/16/2015) NIPS 2015 Workshop on Transfer and Multi-Task Learning: Trends and New Perspectives | |||||||||||||||
Link: https://sites.google.com/site/tlworkshop2015/ | |||||||||||||||
| |||||||||||||||
Call For Papers | |||||||||||||||
[CFP] NIPS 2015 Workshop on Transfer and Multi-Task Learning: Trends and New Perspectives
Call for Participation We invite researchers and practitioners from machine learning, computer vision, natural language processing and related fields to participate in the: NIPS 2015 Workshop on Transfer and Multi-Task Learning: Trends and New Perspectives Saturday December 12th, 2015, Montreal, Canada https://sites.google.com/site/tlworkshop2015 Submission deadline: October 16th, 2015 1. Call for Papers Transfer and multi-task learning methods aim to better exploit the available data during training and adapt previously learned knowledge to new domains or tasks. This mitigates the burden of human labeling for emerging applications and enables learning from very few labeled examples. This workshop explores new discoveries and directions in the main areas of transfer and multi-task learning, as well as several related variants such as domain adaptation and dataset bias, and deep learning based approaches. In the past years there has been increasing activity in these areas, mainly driven by practical applications (e.g. object recognition, sentiment analysis) as well as advances in deep learning. Of the recently proposed practical solutions, most lack theoretical justifications, especially approaches based on deep learning. On the other hand, most of the existing theoretically justified approaches are rarely used in practice. This NIPS 2015 workshop will focus on closing the gap between theory and practice by providing an opportunity for researchers and practitioners to get together, to share ideas and debate current theories and empirical results. The goal is to promote a fruitful exchange of ideas across different communities, leading to a global advancement of the field. We invite submission of extended abstracts to the workshop on all topics related to transfer and multi-task learning, with special interest in: New perspectives or theories on transfer and multi-task learning Dataset bias and concept drift Transfer learning and domain adaptation Multi-task learning Zero-shot or one-shot learning Feature based approaches Instance based approaches Deep architectures for transfer and multi-task learning Transferability of deep representations Transfer across different architectures, e.g. CNN to RNN Transfer across different modalities, e.g. image to text Transfer across different tasks, e.g. object recognition and detection Transfer from weakly labeled or noisy data, e.g. Web data Transfer in practical settings, e.g. online, active, and large-scale learning Innovative applications, e.g. in machine translation, computational biology Datasets, benchmarks, and open-source packages Submissions should be no longer than 4 pages in the NIPS style (plus 1 additional page containing references only). However, it is the authors’ responsibility to make sure they did not violate any dual submission policy if they want to publish it in a future conference (e.g. CVPR 2016). Style files and formatting instructions can be found on the NIPS website. The extended abstract may be accompanied by an unlimited appendix and other supplementary material, with the understanding that anything beyond 4 pages may be ignored. Topics that were recently published or presented elsewhere are allowed, provided that the extended abstract mentions this explicitly. Submission Deadline for Paper Submission: Fri Oct 16, 2015 23:00 PM UTC. Submit at: https://cmt.research.microsoft.com/TLW2015/ Important: As per workshop tradition, reviews are not double-blind, and author names and affiliations should be listed. Accepted papers will be made available on this website. However, the workshop's proceedings can be considered non-archival, meaning contributors are free to publish their work in archival journals or conferences. All accepted papers will have a poster presentation. A selected number of papers will be featured in an oral presentation or spotlight presentation. There will also be a best paper award. 2. Speakers Yoshua Bengio, University of Montreal Shai Ben-David, University of Waterloo Percy Liang, Stanford University Mehryar Mohri, New York University Massimiliano Pontil, University College London Ruslan Salakhutdinov, University of Toronto Qiang Yang, Hong Kong University of Science and Technology 3. Important Dates Submission deadline: October 16th, 2015 Acceptance decision: October 23rd, 2015 Camera-ready: November 13rd, 2015 Workshop: Saturday December 12th, 2015 4. Organizers Anastasia Pentina, Institute of Science and Technology, Austria Christoph Lampert, Institute of Science and Technology, Austria Sinno Jialin Pan, Nanyang Technological University, Singapore Mingsheng Long, Tsinghua University and UC Berkeley Judy Hoffman, UC Berkeley Baochen Sun, University of Massachusetts Lowell Kate Saenko, University of Massachusetts Lowell |
|