Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection

TL;DR

This paper introduces Ortho-LoRA, a gradient projection method that reduces task conflicts in multi-task LoRA models, significantly improving performance on benchmarks by orthogonalizing task gradients within the LoRA subspace.

Contribution

It proposes a novel gradient projection technique tailored for LoRA to effectively disentangle task conflicts in multi-task learning scenarios.

Findings

Ortho-LoRA outperforms standard joint training methods.

It recovers 95% of the performance gap between multi-task and single-task baselines.

The method incurs negligible computational overhead.

Abstract

Multi-Task Learning (MTL) combined with Low-Rank Adaptation (LoRA) has emerged as a promising direction for parameter-efficient deployment of Large Language Models (LLMs). By sharing a single adapter across multiple tasks, one can significantly reduce storage overhead. However, this approach suffers from negative transfer, where conflicting gradient updates from distinct tasks degrade the performance of individual tasks compared to single-task fine-tuning. This problem is exacerbated in LoRA due to the low-rank constraint, which limits the optimization landscape's capacity to accommodate diverse task requirements. In this paper, we propose Ortho-LoRA, a gradient projection method specifically tailored for the bipartite structure of LoRA. Ortho-LoRA dynamically projects conflicting task gradients onto the orthogonal complement of each other within the intrinsic LoRA subspace. Extensive experiments on the GLUE benchmark demonstrate that Ortho-LoRA effectively mitigates task interference, outperforming standard joint training and recovering 95\% of the performance gap between multi-task and single-task baselines with negligible computational overhead.