MoKA: Mixture of Kronecker Adapters

• URL: http://arxiv.org/abs/2508.03527v1
• Date: Tue, 05 Aug 2025 14:58:14 GMT
• Title: MoKA: Mixture of Kronecker Adapters
• Authors: Mohammadreza Sadeghi, Mahsa Ghazvini Nejad, MirHamed Jafarzadeh Asl, Yu Gu, Yuanhao Yu, Masoud Asgharian, Vahid Partovi Nia,
• Abstract summary: Low-rank family adapters are commonly used to control the parameter size efficiently while maintaining the generative power of large language models.<n>We propose a new generation of Kronecker adapters that addresses this limitation by modeling weight updates as a mixture of Kronecker products.<n>We conduct extensive experiments on instruction-tuning and commonsense reasoning tasks using low-bit quantized versions of LLaMA2-7B and LLaMA3-8B models.
• Score: 10.972403518731639
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Parameter-efficient fine-tuning (PEFT) is essential for reducing the computational overhead of large language models (LLMs). Low-rank family adapters are commonly used to control the parameter size efficiently while maintaining the generative power of LLMs. However, their limited expressiveness due to the rank constraint often restricts their performance on complex tasks. We propose Mixture of Kronecker Adapters (MoKA), a new generation of Kronecker adapters that addresses this limitation by modeling weight updates as a mixture of Kronecker products. Our proposed adapter leverages a gating mechanism that measures the importance of each Kronecker factor, enabling more expressive adaptation. Moreover, MoKA enables a rank flexibility that provides a better trade-off between parameter efficiency and accuracy. To ensure hardware efficiency, we reformulate Kronecker computations using standard matrix operations, allowing seamless deployment on GPU-optimized hardware. We conduct extensive experiments on instruction-tuning and commonsense reasoning tasks using low-bit quantized versions of LLaMA2-7B and LLaMA3-8B models. MoKA not only outperforms PEFT baselines, but also reduces the number of trainable parameters up to 27x, achieving state-of-the-art trade-offs between performance and parameter efficiency.

Related papers

• Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product [44.54075854327492]
  We present a comparison amongst full-rank and low-rank PEFT methods.<n> KRAdapter is a novel PEFT algorithm that produces matrix product with a high effective rank.<n>We demonstrate performance gains with KRAdapter on vision-language models up to 1B parameters and on large language models up to 8B parameters.
  arXiv  Detail & Related papers  (2025-08-01T00:29:13Z)
• Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts [72.22148263683037]
  We study the properties of sparse adapters, which train only a subset of weights in the base neural network, as potential building blocks of modular architectures.<n>First, we propose a simple method for training highly effective sparse adapters, which is conceptually simpler than existing methods in the literature.<n>Next, we investigate the merging properties of these sparse adapters by merging adapters for up to 20 natural language processing tasks.
  arXiv  Detail & Related papers  (2025-07-09T03:25:45Z)
• Singular Value Decomposition on Kronecker Adaptation for Large Language Model [0.8747606955991707]
  Large pre-trained Transformer models achieve state-of-the-art results across diverse language and reasoning tasks.<n>Full fine-tuning incurs substantial storage, memory, and computational overhead.<n>We propose SoKA, a novel PEFT strategy that combines Kronecker-product tensor factorization with SVD-driven initialization and dynamic rank selection.
  arXiv  Detail & Related papers  (2025-06-18T08:28:53Z)
• Hyper Compressed Fine-Tuning of Large Foundation Models with Quantum Inspired Adapters [0.0]
  emphQuantum-Inspired Adapters, a PEFT approach inspired by Hamming-weight quantum circuits from quantum machine learning literature.<n>We test our proposed adapters by adapting large language models and large vision transformers on benchmark datasets.
  arXiv  Detail & Related papers  (2025-02-10T13:06:56Z)
• FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing [59.12511498024836]
  We present a method to prune large language models (LLMs) that selectively prunes model blocks based on an importance score.<n>We propose a principled metric to replace each pruned block using a weight-sharing mechanism.<n> Empirical evaluations demonstrate substantial performance gains over existing methods.
  arXiv  Detail & Related papers  (2025-01-24T18:46:37Z)
• OP-LoRA: The Blessing of Dimensionality [93.08208871549557]
  Low-rank adapters enable fine-tuning of large models with only a small number of parameters.<n>They often pose optimization challenges, with poor convergence.<n>We introduce an over- parameterized approach that accelerates training without increasing inference costs.<n>We achieve improvements in vision-language tasks and especially notable increases in image generation.
  arXiv  Detail & Related papers  (2024-12-13T18:55:19Z)
• LoRTA: Low Rank Tensor Adaptation of Large Language Models [70.32218116940393]
  Low Rank Adaptation (LoRA) is a popular Efficient Fine Tuning (PEFT) method.<n>We propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation.<n>Our method can achieve a reduction in the number of parameters while maintaining comparable performance.
  arXiv  Detail & Related papers  (2024-10-05T06:59:50Z)
• Hadamard Adapter: An Extreme Parameter-Efficient Adapter Tuning Method for Pre-trained Language Models [108.08773541490191]
  Pre-trained Language models (PLMs) have a huge amount of parameters, fine-tuning them is often expensive and time consuming. It is necessary to adopt a parameter-efficient approach to reduce parameters of PLMs in fine-tuning without compromising their performance in downstream tasks. In this paper, we design a novel adapter which only acts on self-attention outputs in PLMs.
  arXiv  Detail & Related papers  (2024-07-04T18:21:28Z)
• Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning [38.80020737321214]
  We propose a framework for efficient parameter fine-tuning (PEFT) based on structured unrestricted-rank matrices (SURM)<n>SURMs achieve 5-7% accuracy gains on various image classification tasks while replacing low-rank matrices in LoRA.<n>It also results in up to 12x reduction of the number of parameters in adapters (with virtually no loss in quality) on the GLUE benchmark.
  arXiv  Detail & Related papers  (2024-06-25T17:26:05Z)
• MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning [71.50432879573614]
  Low-rank adaptation (LoRA) is based on the idea that the adaptation process is intrinsically low-dimensional.<n>We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank.<n>Our experimental results show that, compared to LoRA, MELoRA achieves better performance with 8 times fewer trainable parameters on natural language understanding tasks and 36 times fewer trainable parameters on instruction following tasks.
  arXiv  Detail & Related papers  (2024-02-27T07:14:12Z)

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.