Deep Asymmetric Multi-task Feature Learning

TL;DR

Deep-AMTFL introduces an asymmetric autoencoder approach for multitask learning that enhances shared feature learning, prevents negative transfer, and improves performance on benchmark datasets.

Contribution

It presents a novel asymmetric autoencoder framework for deep multitask learning that effectively mitigates negative transfer and enhances shared feature representations.

Findings

Significantly outperforms existing multitask learning models.

Effectively prevents negative transfer in deep feature learning.

Validates on multiple benchmark datasets for image classification.

Abstract

We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process. Specifically, we introduce an asymmetric autoencoder term that allows reliable predictors for the easy tasks to have high contribution to the feature learning while suppressing the influences of unreliable predictors for more difficult tasks. This allows the learning of less noisy representations, and enables unreliable predictors to exploit knowledge from the reliable predictors via the shared latent features. Such asymmetric knowledge transfer through shared features is also more scalable and efficient than inter-task asymmetric transfer. We validate our Deep-AMTFL model on multiple benchmark datasets for multitask learning and image classification, on which it significantly outperforms existing symmetric and asymmetric multitask learning models, by effectively preventing negative transfer in deep feature learning.