DeepAI AI Chat
Log In Sign Up

Gradient Surgery for Multi-Task Learning

by   Tianhe Yu, et al.

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 to enable more efficient learning. However, the multi-task setting presents a number of optimization challenges, making it difficult to realize large efficiency gains compared to learning tasks independently. The reasons why multi-task learning is so challenging compared to single-task learning are not fully understood. In this work, we identify a set of three conditions of the multi-task optimization landscape that cause detrimental gradient interference, and develop a simple yet general approach for avoiding such interference between task gradients. 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. On a series of challenging multi-task supervised and multi-task RL problems, this approach leads to substantial gains in efficiency and performance. Further, it is model-agnostic and can be combined with previously-proposed multi-task architectures for enhanced performance.


Multi-task Learning for Continuous Control

Reliable and effective multi-task learning is a prerequisite for the dev...

Conflict-Averse Gradient Descent for Multi-task Learning

The goal of multi-task learning is to enable more efficient learning tha...

Adaptive Weight Assignment Scheme For Multi-task Learning

Deep learning based models are used regularly in every applications nowa...

Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains

As deep learning applications continue to become more diverse, an intere...

Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models

Massively multilingual models subsuming tens or even hundreds of languag...

Towards automatic construction of multi-network models for heterogeneous multi-task learning

Multi-task learning, as it is understood nowadays, consists of using one...

Curbing Task Interference using Representation Similarity-Guided Multi-Task Feature Sharing

Multi-task learning of dense prediction tasks, by sharing both the encod...

Code Repositories


Code for "Gradient Surgery for Multi-Task Learning"

view repo


Pytorch reimplementation for "Gradient Surgery for Multi-Task Learning"

view repo


PyTorch implementation for "Gradient Surgery for Multi-Task Learning"

view repo