December 8, detailed schedule online. The Workshop takes place in Harrah's Fallen+Marla room.
November 27, accepted papers are online.
- Poster size. We follow the main
conference NIPS instructions and we advice to use A0-landscape size.
- October 24, paper notifications sent to the authors. The deadline for the camera ready version will be announced soon.
The main objective of the workshop is to document and discuss the recent rise of new research questions on the general problem of learning across domains and tasks. This includes the main topics of transfer and multi-task learning, together with several related variants as domain adaptation and dataset bias.
In the last years there has been an increasing boost of activity in these areas, many of them driven by practical applications, such as object categorization. Different solutions were studied for the considered topics, mainly separately and without a joint theoretical framework. On the other hand, most of the existing theoretical formulations model regimes that are rarely used in practice (e.g. adaptive methods that store all the source samples).
This NIPS 2013 workshop will focus on closing this gap by providing an opportunity for theoreticians and practitioners to get together in one place, to share and debate over current theories and empirical results. The goal is to promote a fruitful exchange of ideas and methods between the different communities, leading to a global advancement of the field.
Transfer Learning - Transfer Learning (TL) refers to the problem of retaining and applying the knowledge available for one or more source tasks, to efficiently develop an hypothesis for a new target task. Each task may contain the same (domain adaptation) or different label sets (across category transfer). A lot of the effort has been devoted to binary classification, while most interesting practical transfer problems are intrinsically multi-class and the number of classes can often increase in time. Hence, it is natural to ask:
- How to formalize knowledge transfer across multi-class tasks and provide theoretical guarantees on this setting?
- Can interclass transfer and incremental class learning be properly integrated?
- Can learning guarantees be provided when the adaptation relies only on pre-trained source hypotheses without explicit access to the source samples, as it is often the case in real world scenarios?
Multi-task Learning - Learning over multiple related tasks can outperform learning each task in isolation. This is the principal assertion of Multi-task learning (MTL) and implies that the learning process may benefit from common information shared across the tasks. In the simplest case, transfer process is symmetric and all the tasks are considered as equally related and appropriate for joint training.
- What happens when this condition does not hold, e.g. how to avoid negative transfer?
- Can RHKS embeddings be adequately integrated into the learning process to estimate and compare the distributions underlying the multiple tasks?
- How may embedding probability distributions help learning from data clouds?
- Can deep learning or multiple kernel learning help to get a step closer towards the complete automatization of multi-task learning?
- How can notions from reinforcement learning such as source task selection be connected to notions from convex multi-task learning such as the task similarity matrix?
Urun Dogan - Skype Labs / Microsoft
Marius Kloft - Courant Institute of Mathematical Sciences & Memorial Sloan-Kettering Cancer Center
Francesco Orabona - Toyota Technological Institute, Chicago
Tatiana Tommasi - KU Leuven