# Distributed Multitask Learning

arXiv: https://arxiv.org/abs/1510.00633 · HTML: https://mlsanity.com/paper/1510.00633/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2015.

## Built on by (most cited first, 11 of 11)

- [Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolution](https://mlsanity.com/paper/2204.13062/) (2022)
- [SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks](https://mlsanity.com/paper/2106.02743/) (2021)
- [An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangians](https://mlsanity.com/paper/2102.05320/) (2021)
- [Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits](https://mlsanity.com/paper/2410.02068/) (2024)
- [Shift is Good: Mismatched Data Mixing Improves Test Performance](https://mlsanity.com/paper/2510.25108/) (2025)
- [Less is More -- Towards parsimonious multi-task models using structured sparsity](https://mlsanity.com/paper/2308.12114/) (2023)
- [Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints](https://mlsanity.com/paper/2401.11563/) (2024)
- [Online Parallel Multi-Task Relationship Learning via Alternating Direction Method of Multipliers](https://mlsanity.com/paper/2411.06135/) (2024)
- [Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning](https://mlsanity.com/paper/2403.06535/) (2024)
- [Distributed Networked Multi-task Learning](https://mlsanity.com/paper/2410.03403/) (2024)
- [Adaptive Dual-Mode Distillation with Incentive Schemes for Scalable, Heterogeneous Federated Learning on Non-IID Data](https://mlsanity.com/paper/2509.22507/) (2025)

## Abstract (arXiv)

We consider the problem of distributed multi-task learning, where each machine learns a separate, but related, task. Specifically, each machine learns a linear predictor in high-dimensional space,where all tasks share the same small support. We present a communication-efficient estimator based on the debiased lasso and show that it is comparable with the optimal centralized method.