Deep Multi-task Representation Learning: A Tensor Factorisation Approach
This addresses the need for more flexible and automated multi-task learning in deep learning, offering a novel solution for both homogeneous and heterogeneous tasks.
The paper tackles the problem of multi-task learning (MTL) in deep networks by proposing a tensor factorisation approach that automatically learns cross-task sharing at every layer, eliminating the need for user-defined sharing strategies. Experiments show it achieves higher accuracy and requires fewer design choices compared to existing methods.
Most contemporary multi-task learning methods assume linear models. This setting is considered shallow in the era of deep learning. In this paper, we present a new deep multi-task representation learning framework that learns cross-task sharing structure at every layer in a deep network. Our approach is based on generalising the matrix factorisation techniques explicitly or implicitly used by many conventional MTL algorithms to tensor factorisation, to realise automatic learning of end-to-end knowledge sharing in deep networks. This is in contrast to existing deep learning approaches that need a user-defined multi-task sharing strategy. Our approach applies to both homogeneous and heterogeneous MTL. Experiments demonstrate the efficacy of our deep multi-task representation learning in terms of both higher accuracy and fewer design choices.