Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
This addresses parameter-efficient deployment for LLMs by mitigating task interference in multi-task learning, though it is incremental as it builds on existing LoRA methods.
The paper tackles negative transfer in multi-task LoRA for LLMs by proposing Ortho-LoRA, a gradient projection method that reduces task conflicts, recovering 95% of the performance gap between multi-task and single-task baselines on the GLUE benchmark.
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.