MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards

• URL: http://arxiv.org/abs/2410.00938v2
• Date: Sat, 15 Feb 2025 10:36:03 GMT
• Title: MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards
• Authors: Sheng Wang, Liheng Chen, Pengan Chen, Jingwei Dong, Boyang Xue, Jiyue Jiang, Lingpeng Kong, Chuan Wu,
• Abstract summary: The rapid scaling of large language models requires more lightweight finetuning methods to reduce the explosive GPU memory overhead. Our research highlights the indispensable role of differentiation in reversing the detrimental effects of pure sharing. We propose Mixture of Shards (MoS), incorporating both inter-layer and intra-layer sharing schemes, and integrating four nearly cost-free differentiation strategies.
• Score: 35.163843138935455
• License:
• Abstract: The rapid scaling of large language models necessitates more lightweight finetuning methods to reduce the explosive GPU memory overhead when numerous customized models are served simultaneously. Targeting more parameter-efficient low-rank adaptation (LoRA), parameter sharing presents a promising solution. Empirically, our research into high-level sharing principles highlights the indispensable role of differentiation in reversing the detrimental effects of pure sharing. Guided by this finding, we propose Mixture of Shards (MoS), incorporating both inter-layer and intra-layer sharing schemes, and integrating four nearly cost-free differentiation strategies, namely subset selection, pair dissociation, vector sharding, and shard privatization. Briefly, it selects a designated number of shards from global pools with a Mixture-of-Experts (MoE)-like routing mechanism before sequentially concatenating them to low-rank matrices. Hence, it retains all the advantages of LoRA while offering enhanced parameter efficiency, and effectively circumvents the drawbacks of peer parameter-sharing methods. Our empirical experiments demonstrate approximately 8x parameter savings in a standard LoRA setting. The ablation study confirms the significance of each component. Our insights into parameter sharing and MoS method may illuminate future developments of more parameter-efficient finetuning methods. The code is officially available at https://github.com/Forence1999/MoS.

Related papers

• ASLoRA: Adaptive Sharing Low-Rank Adaptation Across Layers [37.77593687901923]
  ASLoRA is a cross-layer parameter-sharing strategy combining global sharing with partial adaptive sharing. We conduct experiments on various NLP tasks, showing that ASLoRA outperforms LoRA while using less than 25% of the parameters.
  arXiv  Detail & Related papers  (2024-12-13T13:32:13Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts. Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• LoRTA: Low Rank Tensor Adaptation of Large Language Models [70.32218116940393]
  Low Rank Adaptation (LoRA) is a popular Efficient Fine Tuning (PEFT) method. We propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation. Our method can achieve a reduction in the number of parameters while maintaining comparable performance.
  arXiv  Detail & Related papers  (2024-10-05T06:59:50Z)
• LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation [57.49045064294086]
  Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity. We introduce LLMEmb, a novel method leveraging LLM to generate item embeddings that enhance Sequential Recommender Systems (SRS) performance.
  arXiv  Detail & Related papers  (2024-09-30T03:59:06Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks [10.266224162377371]
  Low-rank adaptation (LoRA) and its variants incur substantial storage and transmission costs. We introduce a "divide-and-share" paradigm that breaks the barriers of low-rank decomposition across matrix dimensions, modules, and layers. VB-LoRA achieves extreme parameter efficiency while maintaining comparable or better performance compared to state-of-the-art PEFT methods.
  arXiv  Detail & Related papers  (2024-05-24T03:24:34Z)
• 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. We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank. 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)
• LoRA Meets Dropout under a Unified Framework [38.5176197615878]
  Large language models (LLMs) have emerged as essential elements in numerous NLP applications. Various dropout methods, initially designed for full finetuning with all the parameters updated, alleviates overfitting associated with excessive parameter redundancy. We introduce a unified framework for a comprehensive investigation, which instantiates these methods based on dropping position, structural pattern and compensation measure.
  arXiv  Detail & Related papers  (2024-02-25T07:09:10Z)
• PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA [45.38491644250814]
  Partially Rotation-enhanced Low-Rank Adaptation (PRoLoRA) is an intra-layer sharing mechanism. PRoLoRA retains its advantages, and effectively circumvents the drawbacks of peer parameter-sharing methods. Empirical experiments demonstrate the remarkably higher parameter efficiency of PRoLoRA.
  arXiv  Detail & Related papers  (2024-02-24T13:39:05Z)
• Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model [81.55141188169621]
  We equip PEFT with a cross-block orchestration mechanism to enable the adaptation of the Segment Anything Model (SAM) to various downstream scenarios. We propose an intra-block enhancement module, which introduces a linear projection head whose weights are generated from a hyper-complex layer. Our proposed approach consistently improves the segmentation performance significantly on novel scenarios with only around 1K additional parameters.
  arXiv  Detail & Related papers  (2023-11-28T11:23:34Z)
• IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuning [15.964205804768163]
  IncreLoRA is an incremental parameter allocation method that adaptively adds trainable parameters during training. We conduct extensive experiments on GLUE to demonstrate the effectiveness of IncreLoRA.
  arXiv  Detail & Related papers  (2023-08-23T10:08:10Z)

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.