Deep Multi-task Representation Learning: A Tensor Factorisation Approach

@article{Yang2017DeepMR,
  title={Deep Multi-task Representation Learning: A Tensor Factorisation Approach},
  author={Yongxin Yang and Timothy M. Hospedales},
  journal={CoRR},
  year={2017},
  volume={abs/1605.06391}
}
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… CONTINUE READING
Tweets
This paper has been referenced on Twitter 8 times. VIEW TWEETS

Citations

Publications citing this paper.
SHOWING 1-10 OF 54 CITATIONS, ESTIMATED 37% COVERAGE

144 Citations

050201720182019
Citations per Year
Semantic Scholar estimates that this publication has 144 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Similar Papers

Loading similar papers…