# Learning Multiple Tasks with Multilinear Relationship Networks

arXiv: https://arxiv.org/abs/1506.02117 · HTML: https://mlsanity.com/paper/1506.02117/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2015.

## Built on by (most cited first, 11 of 11)

- [Collaborative Intelligence: Challenges and Opportunities](https://mlsanity.com/paper/2102.06841/) (2021)
- [Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives](https://mlsanity.com/paper/2308.02066/) (2023)
- [UFO: Unified Feature Optimization](https://mlsanity.com/paper/2207.10341/) (2022)
- [Shared Multi-Task Imitation Learning for Indoor Self-Navigation](https://mlsanity.com/paper/1808.04503/) (2018)
- [Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip](https://mlsanity.com/paper/2106.05458/) (2021)
- [Feature Pyramid Network for Multi-task Affective Analysis](https://mlsanity.com/paper/2107.03670/) (2021)
- [Modeling Task Relationships in Multi-variate Soft Sensor with Balanced Mixture-of-Experts](https://mlsanity.com/paper/2305.16360/) (2023)
- [Simultaneous face detection and 360 degree headpose estimation](https://mlsanity.com/paper/2111.11604/) (2021)
- [Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost](https://mlsanity.com/paper/2405.05695/) (2024)
- [Boosting Supervised Learning Performance with Co-training](https://mlsanity.com/paper/2111.09797/) (2021)
- [Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning](https://mlsanity.com/paper/2301.07316/) (2023)

## Abstract (arXiv)

Deep networks trained on large-scale data can learn transferable features to promote learning multiple tasks. Since deep features eventually transition from general to specific along deep networks, a fundamental problem of multi-task learning is how to exploit the task relatedness underlying parameter tensors and improve feature transferability in the multiple task-specific layers. This paper presents Multilinear Relationship Networks (MRN) that discover the task relationships based on novel tensor normal priors over parameter tensors of multiple task-specific layers in deep convolutional networks. By jointly learning transferable features and multilinear relationships of tasks and features, MRN is able to alleviate the dilemma of negative-transfer in the feature layers and under-transfer in the classifier layer. Experiments show that MRN yields state-of-the-art results on three multi-task learning datasets.