# Multi-task Learning over Graph Structures

arXiv: https://arxiv.org/abs/1811.10211 · HTML: https://mlsanity.com/paper/1811.10211/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 1 of 1)

- [Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction](https://mlsanity.com/paper/2108.04353/) (2021)

## Abstract (arXiv)

We present two architectures for multi-task learning with neural sequence models. Our approach allows the relationships between different tasks to be learned dynamically, rather than using an ad-hoc pre-defined structure as in previous work. We adopt the idea from message-passing graph neural networks and propose a general graph multi-task learning framework in which different tasks can communicate with each other in an effective and interpretable way. We conduct extensive experiments in text classification and sequence labeling to evaluate our approach on multi-task learning and transfer learning. The empirical results show that our models not only outperform competitive baselines but also learn interpretable and transferable patterns across tasks.