MoxE: Mixture of xLSTM Experts with Entropy-Aware Routing for Efficient Language Modeling

• URL: http://arxiv.org/abs/2505.01459v1
• Date: Thu, 01 May 2025 12:06:39 GMT
• Title: MoxE: Mixture of xLSTM Experts with Entropy-Aware Routing for Efficient Language Modeling
• Authors: Abdoul Majid O. Thiombiano, Brahim Hnich, Ali Ben Mrad, Mohamed Wiem Mkaouer,
• Abstract summary: MoxE is a novel architecture that combines the Extended Long Short-Term Memory (xLSTM) with the Mixture of Experts (MoE) framework.<n>At the heart of our approach is a novel entropy-based routing mechanism, designed to dynamically route tokens to specialized experts.<n>MoxE achieves significant efficiency gains and enhanced effectiveness compared to existing approaches.
• Score: 6.553328746906528
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces MoxE, a novel architecture that synergistically combines the Extended Long Short-Term Memory (xLSTM) with the Mixture of Experts (MoE) framework to address critical scalability and efficiency challenges in large language models (LLMs). The proposed method effectively leverages xLSTM's innovative memory structures while strategically introducing sparsity through MoE to substantially reduce computational overhead. At the heart of our approach is a novel entropy-based routing mechanism, designed to dynamically route tokens to specialized experts, thereby ensuring efficient and balanced resource utilization. This entropy awareness enables the architecture to effectively manage both rare and common tokens, with mLSTM blocks being favored to handle rare tokens. To further enhance generalization, we introduce a suite of auxiliary losses, including entropy-based and group-wise balancing losses, ensuring robust performance and efficient training. Theoretical analysis and empirical evaluations rigorously demonstrate that MoxE achieves significant efficiency gains and enhanced effectiveness compared to existing approaches, marking a notable advancement in scalable LLM architectures.

Related papers

• MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models [61.89384981175277]
  We propose a emphheterogeneous textbfMixture-of-Adapters (MoA) approach to integrate Low-Rank Adaptation (LoRA) and Mixture-of-Experts (MoE)<n> Experimental results demonstrate that heterogeneous MoA outperforms homogeneous MoE-LoRA methods in both performance and parameter efficiency.
  arXiv  Detail & Related papers  (2025-06-06T09:54:19Z)
• S'MoRE: Structural Mixture of Residual Experts for LLM Fine-tuning [17.579948649237497]
  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.
  arXiv  Detail & Related papers  (2025-04-08T20:54:00Z)
• 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.<n>All expert operations are systematically decomposed into two principal components: a shared projection into a lower-dimensional latent space, followed by expert-specific transformations.<n>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)
• 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)
• Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity [89.81738321188391]
  This study investigates the relationship between task complexity and optimal sparsity in SMoE models.<n>We show that the optimal sparsity lies between minimal activation (1-2 experts) and full activation, with the exact number scaling proportionally to task complexity.
  arXiv  Detail & Related papers  (2024-10-17T18:40:48Z)
• 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)
• Balancing LoRA Performance and Efficiency with Simple Shard Sharing [8.827921242078883]
  textbfOptimal textbfShard textbfSharing textbfIntegration in textbfLoRA, a novel PEFT approach that addresses this trade-off through a simple shard-sharing mechanism.<n>Fossils significantly outperforms standard LoRA and its prominent variants in both model performance metrics and computational efficiency.
  arXiv  Detail & Related papers  (2024-09-19T10:26:42Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment [103.05005690990271]
  We propose a novel framework that combines reasoning chains and expert mixtures to improve self-alignments.<n>MoTE employs a structured reasoning chain comprising four key stages: Question Analysis, Answer Guidance, Safe Answer, and Safety Checking.<n>MoTE significantly improves model safety, jailbreak resistance, and over-refusal capabilities, achieving performance comparable to OpenAI's state-of-the-art o1 model.
  arXiv  Detail & Related papers  (2024-05-01T15:06:05Z)
• Optimization-driven Machine Learning for Intelligent Reflecting Surfaces Assisted Wireless Networks [82.33619654835348]
  Intelligent surface (IRS) has been employed to reshape the wireless channels by controlling individual scattering elements' phase shifts. Due to the large size of scattering elements, the passive beamforming is typically challenged by the high computational complexity. In this article, we focus on machine learning (ML) approaches for performance in IRS-assisted wireless networks.
  arXiv  Detail & Related papers  (2020-08-29T08:39:43Z)

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.