Learning Functions to Study the Benefit of Multitask Learning

2020-06-09 · Gabriele Bettgenhäuser, Michael A. Hedderich, Dietrich Klakow

We study and quantify the generalization patterns of multitask learning (MTL) models for sequence labeling tasks. MTL models are trained to optimize a set of related tasks jointly. Although multitask learning has achieved improved performance in some problems, there are also tasks that lose performance when trained together. These mixed results motivate us to study the factors that impact the performance of MTL models. We note that theoretical bounds and convergence rates for MTL models exist, but they rely on strong assumptions such as task relatedness and the use of balanced datasets. To remedy these limitations, we propose the creation of a task simulator and the use of Symbolic Regression to learn expressions relating model performance to possible factors of influence. For MTL, we study the model performance against the number of tasks (T), the number of samples per task (n) and the task relatedness measured by the adjusted mutual information (AMI). In our experiments, we could empirically find formulas relating model performance with factors of sqrt(n), sqrt(T), which are equivalent to sound mathematical proofs in Maurer[2016], and we went beyond by discovering that performance relates to a factor of sqrt(AMI).

📄 PDF Abstract BibTeX arXiv:2006.05561

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical ProofsSymbolic Regression

Provable Benefit of Multitask Representation Learning in Reinforcement Learning

2022-06-13 · Yuan Cheng, Songtao Feng, Jing Yang, Hong Zhang 외

As representation learning becomes a powerful technique to reduce sample complexity in reinforcement learning (RL) in practice, theoretical understanding of its advantage is still limited. In this paper, we theoretically…

Offline RL reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Multitask Spectral Learning of Weighted Automata

2017-12-01 · NeurIPS 2017 12 · Guillaume Rabusseau, Borja Balle, Joelle Pineau

We consider the problem of estimating multiple related functions computed by weighted automata~(WFA). We first present a natural notion of relatedness between WFAs by considering to which extent several WFAs can share a…

Generalisation in Multitask Fitted Q-Iteration and Offline Q-learning

2025-12-23 · Kausthubh Manda, Raghuram Bharadwaj Diddigi arxiv

We study offline multitask reinforcement learning in settings where multiple tasks share a low-rank representation of their action-value functions. In this regime, a learner is provided with fixed datasets collected from…

Reinforcement Learning

Multitask Learning for Fine-Grained Twitter Sentiment Analysis

2017-07-12 · Georgios Balikas, Simon Moura, Massih-Reza Amini

Traditional sentiment analysis approaches tackle problems like ternary (3-category) and fine-grained (5-category) classification by learning the tasks separately. We argue that such classification tasks are correlated an…

Classification General Classification Sentiment Analysis Sentiment Classification+1

Offline Multitask Representation Learning for Reinforcement Learning

2024-03-18 · Haque Ishfaq, Thanh Nguyen-Tang, Songtao Feng, Raman Arora 외

We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the sha…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Representation Learning