Leveraging convergence behavior to balance conflicting tasks in
multi-task learning
- URL: http://arxiv.org/abs/2204.06698v1
- Date: Thu, 14 Apr 2022 01:52:34 GMT
- Title: Leveraging convergence behavior to balance conflicting tasks in
multi-task learning
- Authors: Angelica Tiemi Mizuno Nakamura, Denis Fernando Wolf, Valdir Grassi Jr
- Abstract summary: 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.
- Score: 3.6212652499950138
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Multi-Task Learning is a learning paradigm that uses correlated tasks to
improve performance generalization. A common way to learn multiple tasks is
through the hard parameter sharing approach, in which a single architecture is
used to share the same subset of parameters, creating an inductive bias between
them during the training process. Due to its simplicity, potential to improve
generalization, and reduce computational cost, it has gained the attention of
the scientific and industrial communities. However, tasks often conflict with
each other, which makes it challenging to define how the gradients of multiple
tasks should be combined to allow simultaneous learning. To address this
problem, we use the idea of multi-objective optimization to 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. The
result of this method is to give more attention to the tasks that are diverging
or that are not being benefited during the last iterations, allowing to ensure
that the simultaneous learning is heading to the performance maximization of
all tasks. As a result, we empirically show that the proposed method
outperforms the state-of-art approaches on learning conflicting tasks. Unlike
the adopted baselines, our method ensures that all tasks reach good
generalization performances.
Related papers
- Saliency-Regularized Deep Multi-Task Learning [7.3810864598379755]
Multitask learning enforces multiple learning tasks to share knowledge to improve their generalization abilities.
Modern deep multitask learning can jointly learn latent features and task sharing, but they are obscure in task relation.
This paper proposes a new multitask learning framework that jointly learns latent features and explicit task relations.
arXiv Detail & Related papers (2022-07-03T20:26:44Z) - Learning Multi-Task Transferable Rewards via Variational Inverse
Reinforcement Learning [10.782043595405831]
We extend an empowerment-based regularization technique to situations with multiple tasks based on the framework of a generative adversarial network.
Under the multitask environments with unknown dynamics, we focus on learning a reward and policy from unlabeled expert examples.
Our proposed method derives the variational lower bound of the situational mutual information to optimize it.
arXiv Detail & Related papers (2022-06-19T22:32:41Z) - In Defense of the Unitary Scalarization for Deep Multi-Task Learning [121.76421174107463]
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.
arXiv Detail & Related papers (2022-01-11T18:44:17Z) - Variational Multi-Task Learning with Gumbel-Softmax Priors [105.22406384964144]
Multi-task learning aims to explore task relatedness to improve individual tasks.
We propose variational multi-task learning (VMTL), a general probabilistic inference framework for learning multiple related tasks.
arXiv Detail & Related papers (2021-11-09T18:49:45Z) - Conflict-Averse Gradient Descent for Multi-task Learning [56.379937772617]
A major challenge in optimizing a multi-task model is the conflicting gradients.
We introduce Conflict-Averse Gradient descent (CAGrad) which minimizes the average loss function.
CAGrad balances the objectives automatically and still provably converges to a minimum over the average loss.
arXiv Detail & Related papers (2021-10-26T22:03:51Z) - Measuring and Harnessing Transference in Multi-Task Learning [58.48659733262734]
Multi-task learning can leverage information learned by one task to benefit the training of other tasks.
We analyze the dynamics of information transfer, or transference, across tasks throughout training.
arXiv Detail & Related papers (2020-10-29T08:25:43Z) - 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) - Multitask Learning with Single Gradient Step Update for Task Balancing [4.330814031477772]
We propose an algorithm to balance between tasks at the gradient level by applying gradient-based meta-learning to multitask learning.
We apply the proposed method to various multitask computer vision problems and achieve state-of-the-art performance.
arXiv Detail & Related papers (2020-05-20T08:34:20Z) - 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.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.