AIExplainer
Deep Learning Mathematics Intermediate 2 min read

What is auxiliary loss?

An additional loss function used to train a machine learning model

An auxiliary loss is a secondary objective that a machine learning model is trained to optimize, in addition to its primary objective. This can help the model learn more useful representations of the data, or improve its performance on the primary task.

Think of an auxiliary loss like a secondary goal for a student. The primary goal is to pass the main exam, but the secondary goal is to also learn a new language. By focusing on the secondary goal, the student may become a better overall learner and even perform better on the main exam.

For example, a self-driving car model might be trained with a primary objective of predicting the steering angle, and an auxiliary loss of predicting the location of pedestrians or other cars on the road.

Auxiliary losses are used in multi-task learning, where a model is trained on multiple tasks simultaneously. They can also be used to regularize a model, or to encourage it to learn specific features or patterns in the data.

One common misconception is that auxiliary losses are only used in multi-task learning. However, they can be used in a variety of contexts, including single-task learning and semi-supervised learning.

The concept of auxiliary losses has been around for several decades, but has gained popularity in recent years with the development of deep learning models.

auxiliary objective secondary loss multi-task loss

Three products for different needs — explore what’s relevant to you.