# Learned Cross-Task Relationships in Multi-Task Models

arXiv: https://arxiv.org/abs/2609.28776 · HTML: https://mlsanity.com/paper/2609.28776/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Distributional Reinforcement Learning with Quantile Regression](https://mlsanity.com/paper/1710.10044/) (2017)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Top-K Off-Policy Correction for a REINFORCE Recommender System](https://mlsanity.com/paper/1812.02353/) (2018)
- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising](https://mlsanity.com/paper/2105.08489/) (2021)
- [Learning Deep Latent Spaces for Multi-Label Classification](https://mlsanity.com/paper/1707.00418/) (2017)
- [Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction](https://mlsanity.com/paper/2408.06512/) (2024)

## Abstract (arXiv)

We propose a framework that learns cross-task relationships in multi-task models by approximating the joint distribution of task labels through targeted pairwise relationships. This approach improves performance via transfer learning and enhances information extraction without the intractable complexity of modeling the full joint space. Although our framework applies to any multi-task system, we demonstrate its efficacy within YouTube's production recommendation systems. Experiments across the Notifications, Homepage, and Watch Next surfaces show improvements in both accuracy and user satisfaction metrics. Finally, we propose a workflow template to facilitate broader future implementation.