# Deep Multi-Task Learning via Generalized Tensor Trace Norm

arXiv: https://arxiv.org/abs/2002.04799 · HTML: https://mlsanity.com/paper/2002.04799/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 6 of 6)

- [Variational Multi-Task Learning with Gumbel-Softmax Priors](https://mlsanity.com/paper/2111.05323/) (2021)
- [Multi-Task Neural Processes](https://mlsanity.com/paper/2111.05820/) (2021)
- [Learning Multi-Tasks with Inconsistent Labels by using Auxiliary Big Task](https://mlsanity.com/paper/2201.02305/) (2022)
- [Tensorized LSSVMs for Multitask Regression](https://mlsanity.com/paper/2303.02451/) (2023)
- [Low-Rank Multitask Learning based on Tensorized SVMs and LSSVMs](https://mlsanity.com/paper/2308.16056/) (2023)
- [Association Graph Learning for Multi-Task Classification with Category Shifts](https://mlsanity.com/paper/2210.04637/) (2022)

## Abstract (arXiv)

The trace norm is widely used in multi-task learning as it can discover low-rank structures among tasks in terms of model parameters. Nowadays, with the emerging of big datasets and the popularity of deep learning techniques, tensor trace norms have been used for deep multi-task models. However, existing tensor trace norms cannot discover all the low-rank structures and they require users to manually determine the importance of their components. To solve those two issues together, in this paper, we propose a Generalized Tensor Trace Norm (GTTN). The GTTN is defined as a convex combination of matrix trace norms of all possible tensor flattenings and hence it can discover all the possible low-rank structures. In the induced objective function, we will learn combination coefficients in the GTTN to automatically determine the importance. Experiments on real-world datasets demonstrate the effectiveness of the proposed GTTN.