Related papers: In Defense of the Unitary Scalarization for Deep Multi-Task Learning

In Defense of the Unitary Scalarization for Deep Multi-Task Learning

URL: http://arxiv.org/abs/2201.04122v1
Date: Tue, 11 Jan 2022 18:44:17 GMT
Title: In Defense of the Unitary Scalarization for Deep Multi-Task Learning
Authors: Vitaly Kurin, Alessandro De Palma, Ilya Kostrikov, Shimon Whiteson, M. Pawan Kumar
Abstract summary: We present a theoretical analysis suggesting that many specialized multi-tasks can be interpreted as forms of regularization. We show that, when coupled with standard regularization and stabilization techniques, unitary scalarization matches or improves upon the performance of complex multitasks.
Score: 121.76421174107463
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses. Several ad-hoc multi-task optimization algorithms have instead been proposed, inspired by various hypotheses about what makes multi-task settings difficult. The majority of these optimizers require per-task gradients, and introduce significant memory, runtime, and implementation overhead. We present a theoretical analysis suggesting that many specialized multi-task optimizers can be interpreted as forms of regularization. Moreover, we show that, when coupled with standard regularization and stabilization techniques from single-task learning, unitary scalarization matches or improves upon the performance of complex multi-task optimizers in both supervised and reinforcement learning settings. We believe our results call for a critical reevaluation of recent research in the area.

Related papers

Multi-Task Learning with Multi-Task Optimization [31.518330903602095]
We show that a set of optimized yet well-distributed models embody different trade-offs in one algorithmic pass. We investigate the proposed multi-task learning with multi-task optimization for solving various problem settings.
arXiv Detail & Related papers (2024-03-24T14:04:40Z)
Contrastive Multi-Task Dense Prediction [11.227696986100447]
A core objective in design is how to effectively model cross-task interactions to achieve a comprehensive improvement on different tasks. We introduce feature-wise contrastive consistency into modeling the cross-task interactions for multi-task dense prediction. We propose a novel multi-task contrastive regularization method based on the consistency to effectively boost the representation learning of the different sub-tasks.
arXiv Detail & Related papers (2023-07-16T03:54:01Z)
Leveraging convergence behavior to balance conflicting tasks in multi-task learning [3.6212652499950138]
Multi-Task Learning uses correlated tasks to improve performance generalization. Tasks often conflict with each other, which makes it challenging to define how the gradients of multiple tasks should be combined. We propose a method that takes into account temporal behaviour of the gradients to create a dynamic bias that adjust the importance of each task during the backpropagation.
arXiv Detail & Related papers (2022-04-14T01:52:34Z)
New Tight Relaxations of Rank Minimization for Multi-Task Learning [161.23314844751556]
We propose two novel multi-task learning formulations based on two regularization terms. We show that our methods can correctly recover the low-rank structure shared across tasks, and outperform related multi-task learning methods.
arXiv Detail & Related papers (2021-12-09T07:29:57Z)
Multi-Task Learning with Sequence-Conditioned Transporter Networks [67.57293592529517]
We aim to solve multi-task learning through the lens of sequence-conditioning and weighted sampling. We propose a new suite of benchmark aimed at compositional tasks, MultiRavens, which allows defining custom task combinations. Second, we propose a vision-based end-to-end system architecture, Sequence-Conditioned Transporter Networks, which augments Goal-Conditioned Transporter Networks with sequence-conditioning and weighted sampling.
arXiv Detail & Related papers (2021-09-15T21:19:11Z)
Small Towers Make Big Differences [59.243296878666285]
Multi-task learning aims at solving multiple machine learning tasks at the same time. A good solution to a multi-task learning problem should be generalizable in addition to being Pareto optimal. We propose a method of under- parameterized self-auxiliaries for multi-task models to achieve the best of both worlds.
arXiv Detail & Related papers (2020-08-13T10:45:31Z)
Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference [75.95287293847697]
Two common challenges in developing multi-task models are often overlooked in literature. First, enabling the model to be inherently incremental, continuously incorporating information from new tasks without forgetting the previously learned ones (incremental learning) Second, eliminating adverse interactions amongst tasks, which has been shown to significantly degrade the single-task performance in a multi-task setup (task interference)
arXiv Detail & Related papers (2020-07-24T14:44:46Z)
Gradient Surgery for Multi-Task Learning [119.675492088251]
Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks. The reasons why multi-task learning is so challenging compared to single-task learning are not fully understood. We propose a form of gradient surgery that projects a task's gradient onto the normal plane of the gradient of any other task that has a conflicting gradient.
arXiv Detail & Related papers (2020-01-19T06:33:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.