# Multi-Task Learning with Prior Information

arXiv: https://arxiv.org/abs/2301.01572 · HTML: https://mlsanity.com/paper/2301.01572/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 4 Jan 2023.

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

- [Federated Multi-Task Learning under a Mixture of Distributions](https://mlsanity.com/paper/2108.10252/) (2021)
- [BAM! Born-Again Multi-Task Networks for Natural Language Understanding](https://mlsanity.com/paper/1907.04829/) (2019)
- [Convex Learning of Multiple Tasks and their Structure](https://mlsanity.com/paper/1504.03101/) (2015)
- [Spherical Principal Component Analysis](https://mlsanity.com/paper/1903.06877/) (2019)
- [Multi-Task Driven Explainable Diagnosis of COVID-19 using Chest X-ray Images](https://mlsanity.com/paper/2008.03205/) (2020)
- [On Multiplicative Multitask Feature Learning](https://mlsanity.com/paper/1610.07563/) (2016)
- [Rethinking Symmetric Matrix Factorization: A More General and Better Clustering Perspective](https://mlsanity.com/paper/2209.02528/) (2022)

## Built on by (most cited first, 1 of 1)

- [On Regularized Sparse Logistic Regression](https://mlsanity.com/paper/2309.05925/) (2023)

## Abstract (arXiv)

Multi-task learning aims to boost the generalization performance of multiple related tasks simultaneously by leveraging information contained in those tasks. In this paper, we propose a multi-task learning framework, where we utilize prior knowledge about the relations between features. We also impose a penalty on the coefficients changing for each specific feature to ensure related tasks have similar coefficients on common features shared among them. In addition, we capture a common set of features via group sparsity. The objective is formulated as a non-smooth convex optimization problem, which can be solved with various methods, including gradient descent method with fixed stepsize, iterative shrinkage-thresholding algorithm (ISTA) with back-tracking, and its variation -- fast iterative shrinkage-thresholding algorithm (FISTA). In light of the sub-linear convergence rate of the methods aforementioned, we propose an asymptotically linear convergent algorithm with theoretical guarantee. Empirical experiments on both regression and classification tasks with real-world datasets demonstrate that our proposed algorithms are capable of improving the generalization performance of multiple related tasks.