Robust Analysis of Multi-Task Learning Efficiency: New Benchmarks on Light-Weighed Backbones and Effective Measurement of Multi-Task Learning Challenges by Feature Disentanglement

TL;DR

This paper evaluates multi-task learning efficiency on lightweight backbones, introduces new benchmarks, and proposes feature disentanglement as a novel method to identify challenges in MTL.

Contribution

It provides large-scale experiments on smaller backbones, assesses the generalizability of gradient approximation techniques, and introduces feature disentanglement and ranking similarity as new evaluation tools.

Findings

Lightweight backbones affect MTL performance.

Fast gradient surrogate technique has limited generalizability.

Feature Disentanglement effectively identifies MTL challenges.

Abstract

One of the main motivations of MTL is to develop neural networks capable of inferring multiple tasks simultaneously. While countless methods have been proposed in the past decade investigating robust model architectures and efficient training algorithms, there is still lack of understanding of these methods when applied on smaller feature extraction backbones, the generalizability of the commonly used fast approximation technique of replacing parameter-level gradients with feature level gradients, and lack of comprehensive understanding of MTL challenges and how one can efficiently and effectively identify the challenges. In this paper, we focus on the aforementioned efficiency aspects of existing MTL methods. We first carry out large-scale experiments of the methods with smaller backbones and on a the MetaGraspNet dataset as a new test ground. We also compare the existing methods with and without using the fast gradient surrogate and empirically study the generalizability of this technique. Lastly, we propose Feature Disentanglement measure as a novel and efficient identifier of the challenges in MTL, and propose Ranking Similarity score as an evaluation metric for different identifiers to prove the faithfulness of our method.