A heterogeneous Mixture-of-Adapters (MoA) approach enhances parameter-efficient fine-tuning in LLMs by integrating diverse adapter experts, outperforming homogeneous MoE-LoRA methods.
Recent studies integrate Low-Rank Adaptation (LoRA) and Mixture-of-Experts
(MoE) to further enhance the performance of parameter-efficient fine-tuning
(PEFT) methods in Large Language Model (LLM) applications. Existing methods
employ homogeneous MoE-LoRA architectures composed of LoRA experts with
either similar or identical structures and capacities. However, these
approaches often suffer from representation collapse and expert load imbalance,
which negatively impact the potential of LLMs. To address these challenges, we
propose a heterogeneous Mixture-of-Adapters (MoA) approach.
This method dynamically integrates PEFT adapter experts with diverse
structures, leveraging their complementary representational capabilities to
foster expert specialization, thereby enhancing the effective transfer of
pre-trained knowledge to downstream tasks. MoA supports two variants:
(i) Soft MoA achieves fine-grained integration by performing
a weighted fusion of all expert outputs; (ii) Sparse MoA
activates adapter experts sparsely based on their contribution, achieving this
with negligible performance degradation. Experimental results demonstrate that
heterogeneous MoA outperforms homogeneous MoE-LoRA methods in both performance
and parameter efficiency. Our project is available at
https://github.com/DCDmllm/MoA.
