ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning

TL;DR

ForkMerge is a novel method that addresses negative transfer in auxiliary-task learning by dynamically managing model branches and task weights, leading to improved target task performance.

Contribution

It introduces ForkMerge, a new approach that mitigates negative transfer by periodically forking, searching optimal task weights, and merging branches based on validation errors.

Findings

Outperforms existing methods on auxiliary-task learning benchmarks.

Effectively mitigates negative transfer in multi-task learning.

Improves target task accuracy by managing task conflicts dynamically.

Abstract

Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by leveraging the knowledge obtained from related tasks. Occasionally, learning multiple tasks simultaneously results in lower accuracy than learning only the target task, which is known as negative transfer. This problem is often attributed to the gradient conflicts among tasks, and is frequently tackled by coordinating the task gradients in previous works. However, these optimization-based methods largely overlook the auxiliary-target generalization capability. To better understand the root cause of negative transfer, we experimentally investigate it from both optimization and generalization perspectives. Based on our findings, we introduce ForkMerge, a novel approach that periodically forks the model into multiple branches, automatically searches the varying task weights by minimizing target validation errors, and dynamically merges all branches to filter out detrimental task-parameter updates. On a series of auxiliary-task learning benchmarks, ForkMerge outperforms existing methods and effectively mitigates negative transfer.