# Multi-task problems are not multi-objective

arXiv: https://arxiv.org/abs/2110.07301 · HTML: https://mlsanity.com/paper/2110.07301/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Pareto Multi-Task Learning](https://mlsanity.com/paper/1912.12854/) (2019)
- [Learning the Pareto Front with Hypernetworks](https://mlsanity.com/paper/2010.04104/) (2020)
- [An Easy-to-use Real-world Multi-objective Optimization Problem Suite](https://mlsanity.com/paper/2009.12867/) (2020)
- [Controllable Pareto Multi-Task Learning](https://mlsanity.com/paper/2010.06313/) (2020)
- [Scalable Pareto Front Approximation for Deep Multi-Objective Learning](https://mlsanity.com/paper/2103.13392/) (2021)
- [Multi-Gradient Descent for Multi-Objective Recommender Systems](https://mlsanity.com/paper/2001.00846/) (2019)
- [Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization](https://mlsanity.com/paper/2102.04523/) (2021)

## Built on by (most cited first, 3 of 3)

- [Scalarization for Multi-Task and Multi-Domain Learning at Scale](https://mlsanity.com/paper/2310.08910/) (2023)
- [Generalization In Multi-Objective Machine Learning](https://mlsanity.com/paper/2208.13499/) (2022)
- [Multi-Objective Optimization via Wasserstein-Fisher-Rao Gradient Flow](https://mlsanity.com/paper/2311.13159/) (2023)

## Abstract (arXiv)

Multi-objective optimization (MOO) aims at finding a set of optimal configurations for a given set of objectives. A recent line of work applies MOO methods to the typical Machine Learning (ML) setting, which becomes multi-objective if a model should optimize more than one objective, for instance in fair machine learning. These works also use Multi-Task Learning (MTL) problems to benchmark MOO algorithms treating each task as independent objective. In this work we show that MTL problems do not resemble the characteristics of MOO problems. In particular, MTL losses are not competing in case of a sufficiently expressive single model. As a consequence, a single model can perform just as well as optimizing all objectives with independent models, rendering MOO inapplicable. We provide evidence with extensive experiments on the widely used Multi-Fashion-MNIST datasets. Our results call for new benchmarks to evaluate MOO algorithms for ML. Our code is available at: https://github.com/ruchtem/moo-mtl.