S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning

Hanqing Zeng, Yinglong Xia, Zhuokai Zhao, Chuan Jiang, Qiang Zhang, Jiayi Liu, Qunshu Zhang, Lizhu Zhang, Xiangjun Fan, Benyu Zhang

Keywords: Mixture-of-experts, low-rank adaptation, language models, graph neural networks

TL;DR: We propose a PEFT architecture that performs structural mixture of LoRA experts, boosting the expressive power of traditional MoE with negligible parameter and computation overhead.

Abstract: Fine-tuning pre-trained large language models (LLMs) presents a dual challenge of balancing parameter efficiency and model capacity. Existing methods like low-rank adaptations (LoRA) are efficient but lack flexibility, while Mixture-of-Experts (MoE) enhance model capacity at the cost of more & under-utilized parameters. To address these limitations, we propose Structural Mixture of Residual Experts (S’MoRE), a novel framework that seamlessly integrates the efficiency of LoRA with the flexibility of MoE. Conceptually, S’MoRE employs hierarchical low-rank decomposition of expert weights, yielding residuals of varying orders interconnected in a multi-layer structure. By routing input tokens through sub-trees of residuals, S’MoRE emulates the capacity of numerous experts by instantiating and assembling just a few low-rank matrices. We craft the inter-layer propagation of S’MoRE’s residuals as a special type of Graph Neural Network (GNN), and prove that under similar parameter budget, S’MoRE improves structural flexibility of traditional MoE (or Mixture-of-LoRA) by exponential order. Comprehensive theoretical analysis and empirical results demonstrate that S’MoRE achieves superior fine-tuning performance, offering a transformative approach for efficient LLM adaptation. Our implementation is available at: https://github.com/ZimpleX/SMoRE-LLM.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 6835