arXiv research

Small parameterized towers improve multi-task learning efficiency and generalization.

In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination o…

Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not exhibited the same level of success as in other domains, such as computer vision. In…

While deep learning and deep reinforcement learning (RL) systems have demonstrated impressive results in domains such as image classification, game playing, and robotic control, data efficiency remains a major challenge. Multi-task learning has emerged as a promising approach for sharing structure across multiple tasks…

Multi-task learning is a learning paradigm which seeks to improve the generalization performance of a learning task with the help of some other related tasks. In this paper, we propose a regularization formulation for learning the relationships between tasks in multi-task learning. This formulation can be viewed as a n…

Multi-task learning uses auxiliary data or knowledge from relevant tasks to facilitate the learning in a new task. Multi-task optimization applies multi-task learning to optimization to study how to effectively and efficiently tackle multiple optimization problems simultaneously. Evolutionary multi-tasking, or multi-fa…

This paper reviews dMTL and methods for selecting auxiliary tasks.

Survey on multi-task learning for deep neural networks.

Disentangled representations naturally emerge in multi-task learning.

SON-GOKU uses graph coloring to improve multi-task learning by partitioning tasks into compatible groups.

Research explores the trade-off between multi-task learning and multitasking in deep neural networks.

A new framework integrates classification and regression tasks in multi-task learning.

Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-task learning, one needs to centralize data from all the tasks to a single machine. However, in many real-world applications, data of differen…

Improves shared encoder representations for better multi-task learning performance.

New method generates continuous Pareto sets for multi-task learning.

Multi-task sparse feature learning aims to improve the generalization performance by exploiting the shared features among tasks. It has been successfully applied to many applications including computer vision and biomedical informatics. Most of the existing multi-task sparse feature learning algorithms are formulated a…

Near-optimal rates for multi-task learning with shared representations.

Develops a method for fairness in multi-task learning using Wasserstein barycenters.

This paper proposes a method to reveal task relationships in multi-task learning models using sparse graphs.

This paper investigates multi-task reinforcement learning in non-Markovian decision making, showing benefits in sample efficiency.

Wide neural networks can benefit from multi-task learning in their infinite-width limit.

New method learns multiple reward functions for complex tasks.

Study improves GMM learning performance through multi-task and transfer learning.

Algorithm learns which weights to share in deep multi-task learning.

Deep multi-task learning benefits from low intrinsic dimensionality, leading to better generalization.

PAC-Bayesian analysis improves lifelong learning in multi-armed bandits.

New research shows Multi-Task Learning does not behave like Multi-Objective Optimization.

This work improves trace norm regularization for multi-task learning with limited data.

Multi-label learning studies the problem where an instance is associated with a set of labels. By treating single-label learning problem as one task, the multi-label learning problem can be casted as solving multiple related tasks simultaneously. In this paper, we propose a novel Multi-task Gradient Descent (MGD) algor…

This work benchmarks MARL algorithms in cooperative tasks.

Paper introduces a new model to handle multi-task learning across different input domains.

Method learns graph structure for multi-task learning, revealing interpretable relationships.

Framework for multi-task learning with semiparametric models and nuisance parameters.

Proposes a transductive matrix completion method with calibration for multi-task learning.

Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously. However, it is often impossible to find one single solution to optimize all the tasks, since different tasks might conflict with each other. Recently, a novel method is proposed to find one single Pareto optimal solution with…

This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of vision and language. However, establishing large scale dataset for multi-modal video question answeri…

MT-HAL learns features and task associations for multiple tasks with a shared sparse structure.

Flexible multi-task learning framework using summary statistics.

Develops a new method to improve performance in multi-objective learning problems.

Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach…

Paper tackles multi-task learning for molecular property prediction with limited data.

We study the stability properties of nonlinear multi-task regression in reproducing Hilbert spaces with operator-valued kernels. Such kernels, a.k.a. multi-task kernels, are appropriate for learning prob- lems with nonscalar outputs like multi-task learning and structured out- put prediction. We show that multi-task ke…

Multi-task learning has shown to significantly enhance the performance of multiple related learning tasks in a variety of situations. We present the fused logistic regression, a sparse multi-task learning approach for binary classification. Specifically, we introduce sparsity inducing penalties over parameter differenc…

Study multi-task learning with low-rank representation in stochastic linear bandits.

CMDE uses deep learning to estimate causal effects from complex data.

Proposes Ada-Sit method for mortality prediction of rare diseases.

We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence cl…

Bayesian approach improves network lasso for multi-task learning.