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

• URL: http://arxiv.org/abs/2504.06426v1
• Date: Tue, 08 Apr 2025 20:54:00 GMT
• Title: S'MoRE: Structural Mixture of Residual Experts for LLM Fine-tuning
• Authors: Hanqing Zeng, Yinglong Xia, Zhuokai Zhao, Gilbert Jiang, Qiang Zhang, Jiayi Liu, Lizhu Zhang, Xiangjun Fan, Benyu Zhang,
• Abstract summary: We propose Structural Mixture of Residual Experts (S'MoRE), a novel framework that seamlessly integrates the efficiency of LoRA with the flexibility of MoE.<n>Specifically, S'MoRE employs hierarchical low-rank decomposition of expert weights, yielding residuals of varying orders interconnected in a multi-layer structure.<n>We prove that S'MoRE improves "structural flexibility" of traditional MoE (or Mixture-of-LoRA) by exponential order.
• Score: 17.579948649237497
• License: http://creativecommons.org/licenses/by/4.0/
• 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) architectures 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. Specifically, 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 many 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.

Related papers

• DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism [5.988126768890861]
  DynMoLE is a hybrid routing strategy that dynamically adjusts expert selection based on the Tsallis entropy of the router's probability distribution.<n>Our experiments on commonsense reasoning benchmarks demonstrate that DynMoLE achieves substantial performance improvements.
  arXiv  Detail & Related papers  (2025-04-01T11:14:19Z)
• Beyond Standard MoE: Mixture of Latent Experts for Resource-Efficient Language Models [10.623996218106564]
  We introduce a novel parameterization methodology that facilitates the mapping of specific experts into a shared latent space. All expert operations are systematically decomposed into two principal components: a shared projection into a lower-dimensional latent space, followed by expert-specific transformations. This factorized approach substantially diminishes parameter count and computational requirements.
  arXiv  Detail & Related papers  (2025-03-29T14:35:34Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [70.91804882618243]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• OMoE: Diversifying Mixture of Low-Rank Adaptation by Orthogonal Finetuning [3.8813502422318127]
  Building mixture-of-experts (MoE) architecture for Low-rank adaptation (LoRA) is emerging as a potential direction in parameter-efficient fine-tuning (PEFT)<n>We first conduct qualitative analysis to indicate that experts collapse to similar representations in vanilla MoE, limiting the capacity of modular design and computational efficiency.<n>Motivated by these findings, we propose Orthogonal Mixture-of-Experts (OMoE)<n>Our method is simple and alleviates memory bottlenecks, as it incurs minimal experts compared to vanilla MoE models.
  arXiv  Detail & Related papers  (2025-01-17T09:27:08Z)
• Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging [111.8456671452411]
  Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. We propose a Weight-Ensembling Mixture of Experts (WEMoE) method for multi-task model merging. We show that WEMoE and E-WEMoE outperform state-of-the-art (SOTA) model merging methods in terms of MTL performance, generalization, and robustness.
  arXiv  Detail & Related papers  (2024-10-29T07:16:31Z)
• Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design [59.00758127310582]
  We propose a novel framework Read-ME that transforms pre-trained dense LLMs into smaller MoE models. Our approach employs activation sparsity to extract experts. Read-ME outperforms other popular open-source dense models of similar scales.
  arXiv  Detail & Related papers  (2024-10-24T19:48:51Z)
• Retraining-Free Merging of Sparse MoE via Hierarchical Clustering [14.858134039539697]
  This paper introduces Hierarchical Clustering for Sparsely activated Mixture of Experts (HC-SMoE)<n>HC-SMoE is a task-agnostic expert merging framework for parameter reduction without retraining.<n>We provide theoretical analysis and evaluations across multiple zero-shot language tasks to demonstrate HC-SMoE's effectiveness in state-of-the-art models including Qwen and Mixtral.
  arXiv  Detail & Related papers  (2024-10-11T07:36:14Z)
• Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts [74.40198929049959]
  Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks. generalist LMMs often suffer from performance degradation when tuned over a large collection of tasks. We propose Omni-SMoLA, an architecture that uses the Soft MoE approach to mix many multimodal low rank experts.
  arXiv  Detail & Related papers  (2023-12-01T23:04:27Z)
• Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models [68.9288651177564]
  We present a novel MoE architecture based on matrix product operators (MPO) from quantum many-body physics. With the decomposed MPO structure, we can reduce the parameters of the original MoE architecture. Experiments on the three well-known downstream natural language datasets based on GPT2 show improved performance and efficiency in increasing model capacity.
  arXiv  Detail & Related papers  (2022-03-02T13:44:49Z)
• Training Deep Energy-Based Models with f-Divergence Minimization [113.97274898282343]
  Deep energy-based models (EBMs) are very flexible in distribution parametrization but computationally challenging. We propose a general variational framework termed f-EBM to train EBMs using any desired f-divergence. Experimental results demonstrate the superiority of f-EBM over contrastive divergence, as well as the benefits of training EBMs using f-divergences other than KL.
  arXiv  Detail & Related papers  (2020-03-06T23:11:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.