# Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains

arXiv: https://arxiv.org/abs/1906.00097 · HTML: https://mlsanity.com/paper/1906.00097/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2019.

## Built on by (most cited first, 13 of 13)

- [Learning the Effect of Registration Hyperparameters with HyperMorph](https://mlsanity.com/paper/2203.16680/) (2022)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Block Contextual MDPs for Continual Learning](https://mlsanity.com/paper/2110.06972/) (2021)
- [Principled Weight Initialization for Hypernetworks](https://mlsanity.com/paper/2312.08399/) (2023)
- [HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks](https://mlsanity.com/paper/2103.09439/) (2021)
- [Example-based Hypernetworks for Out-of-Distribution Generalization](https://mlsanity.com/paper/2203.14276/) (2022)
- [Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions](https://mlsanity.com/paper/2203.06852/) (2022)
- [Exploring Distributional Shifts in Large Language Models for Code Analysis](https://mlsanity.com/paper/2303.09128/) (2023)
- [Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives](https://mlsanity.com/paper/2502.04358/) (2025)
- [Transferring Unconditional to Conditional GANs with Hyper-Modulation](https://mlsanity.com/paper/2112.02219/) (2021)
- [Modularity in Deep Learning: A Survey](https://mlsanity.com/paper/2310.01154/) (2023)
- [Interpretable Multi-task Learning with Shared Variable Embeddings](https://mlsanity.com/paper/2405.06330/) (2024)
- [Leveraging Hypernetworks and Learnable Kernels for Consumer Energy Forecasting Across Diverse Consumer Types](https://mlsanity.com/paper/2502.05104/) (2025)

## Abstract (arXiv)

As deep learning applications continue to become more diverse, an interesting question arises: Can general problem solving arise from jointly learning several such diverse tasks? To approach this question, deep multi-task learning is extended in this paper to the setting where there is no obvious overlap between task architectures. The idea is that any set of (architecture,task) pairs can be decomposed into a set of potentially related subproblems, whose sharing is optimized by an efficient stochastic algorithm. The approach is first validated in a classic synthetic multi-task learning benchmark, and then applied to sharing across disparate architectures for vision, NLP, and genomics tasks. It discovers regularities across these domains, encodes them into sharable modules, and combines these modules systematically to improve performance in the individual tasks. The results confirm that sharing learned functionality across diverse domains and architectures is indeed beneficial, thus establishing a key ingredient for general problem solving in the future.