# Sign-regularized Multi-task Learning

arXiv: https://arxiv.org/abs/2102.11191 · HTML: https://mlsanity.com/paper/2102.11191/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 7 of 7)

- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019)
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://mlsanity.com/paper/2012.12397/) (2020)
- [Parallel Multi-Block ADMM with o(1/k) Convergence](https://mlsanity.com/paper/1312.3040/) (2013)
- [On Multiplicative Multitask Feature Learning](https://mlsanity.com/paper/1610.07563/) (2016)
- [Nonconvex Generalization of Alternating Direction Method of Multipliers for Nonlinear Equality Constrained Problems](https://mlsanity.com/paper/1705.03412/) (2017)

## Built on by (most cited first, 4 of 4)

- [Continuous Temporal Domain Generalization](https://mlsanity.com/paper/2405.16075/) (2024)
- [Saliency-Regularized Deep Multi-Task Learning](https://mlsanity.com/paper/2207.01117/) (2022)
- [FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization](https://mlsanity.com/paper/2608.22224/) (2026)
- [Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization](https://mlsanity.com/paper/2610.02822/) (2026)

## Abstract (arXiv)

Multi-task learning is a framework that enforces different learning tasks to share their knowledge to improve their generalization performance. It is a hot and active domain that strives to handle several core issues; particularly, which tasks are correlated and similar, and how to share the knowledge among correlated tasks. Existing works usually do not distinguish the polarity and magnitude of feature weights and commonly rely on linear correlation, due to three major technical challenges in: 1) optimizing the models that regularize feature weight polarity, 2) deciding whether to regularize sign or magnitude, 3) identifying which tasks should share their sign and/or magnitude patterns. To address them, this paper proposes a new multi-task learning framework that can regularize feature weight signs across tasks. We innovatively formulate it as a biconvex inequality constrained optimization with slacks and propose a new efficient algorithm for the optimization with theoretical guarantees on generalization performance and convergence. Extensive experiments on multiple datasets demonstrate the proposed methods' effectiveness, efficiency, and reasonableness of the regularized feature weighted patterns.