Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives

TL;DR

This paper introduces ETR-NLP, a multi-task learning approach that uses non-learnable primitives and explicit task routing to reduce task interference, outperforming existing methods with fewer parameters.

Contribution

It proposes a novel combination of non-learnable primitives and explicit task routing to effectively mitigate task interference in multi-task learning.

Findings

ETR-NLP outperforms state-of-the-art baselines on multiple datasets.

The method achieves better accuracy with fewer learnable parameters.

Experimental results show improved task-specific performance.

Abstract

Multi-task learning (MTL) seeks to learn a single model to accomplish multiple tasks by leveraging shared information among the tasks. Existing MTL models, however, have been known to suffer from negative interference among tasks. Efforts to mitigate task interference have focused on either loss/gradient balancing or implicit parameter partitioning with partial overlaps among the tasks. In this paper, we propose ETR-NLP to mitigate task interference through a synergistic combination of non-learnable primitives (NLPs) and explicit task routing (ETR). Our key idea is to employ non-learnable primitives to extract a diverse set of task-agnostic features and recombine them into a shared branch common to all tasks and explicit task-specific branches reserved for each task. The non-learnable primitives and the explicit decoupling of learnable parameters into shared and task-specific ones afford the flexibility needed for minimizing task interference. We evaluate the efficacy of ETR-NLP networks for both image-level classification and pixel-level dense prediction MTL problems. Experimental results indicate that ETR-NLP significantly outperforms state-of-the-art baselines with fewer learnable parameters and similar FLOPs across all datasets. Code is available at this \href{https://github.com/zhichao-lu/etr-nlp-mtl}.