paper-with-me

홈 › Papers

Learning Attentional Mixture of LoRAs for Language Model Continual Learning

2024-09-29 · Jialin Liu, Jianhua Wu, Jie Liu, Yutai Duan

Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dealing with multiple tasks sequentially. To this end, we propose Attentional Mixture of LoRAs (AM-LoRA), a continual learning approach tailored for LLMs. Specifically, AM-LoRA learns a sequence of LoRAs for a series of tasks to continually learn knowledge from different tasks. The key of our approach is that we devise an attention mechanism as a knowledge mixture module to adaptively integrate information from each LoRA. With the attention mechanism, AM-LoRA can efficiently leverage the distinctive contributions of each LoRA, while mitigating the risk of mutually negative interactions among them that may lead to catastrophic forgetting. Moreover, we further introduce $L1$ norm in the learning process to make the attention vector more sparse. The sparse constraints can enable the model to lean towards selecting a few highly relevant LoRAs, rather than aggregating and weighting all LoRAs collectively, which can further reduce the impact stemming from mutual interference. Experimental results on continual learning benchmarks indicate the superiority of our proposed method.

📄 PDF Abstract BibTeX arXiv:2409.19611

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

K-Merge: Online Continual Merging of Adapters for On-device Large Language Models

2025-10-15 · Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay 외 arxiv

On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address the limited storage capacity of mobile …

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning

2026-03-10 · Ruizhong Qiu, Hanqing Zeng, Yinglong Xia, Yiwen Meng 외 arxiv

Low-rank adapters (LoRAs) are a parameter-efficient finetuning technique that injects trainable low-rank matrices into pretrained models to adapt them to new tasks. Mixture-of-LoRAs models expand neural networks efficien…

Reinforcement Learning

Merge before Forget: A Single LoRA Continual Learning via Continual Merging

2025-12-28 · Fuli Qiao, Mehrdad Mahdavi arxiv

Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks. Current Low-Rank Adaptation (LoRA) c…

Continual Learning

Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning

2024-06-24 · Ziyu Zhao, Leilei Gan, Guoyin Wang, Yuwei Hu 외

Low-Rank Adaptation (LoRA) offers an efficient way to fine-tune large language models (LLMs). Its modular and plug-and-play nature allows the integration of various domain-specific LoRAs, enhancing LLM capabilities. Open…

Retrieval

Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models

2024-03-06 · Wenfeng Feng, Chuzhan Hao, Yuewei Zhang, Yu Han 외

Instruction Tuning has the potential to stimulate or enhance specific capabilities of large language models (LLMs). However, achieving the right balance of data is crucial to prevent catastrophic forgetting and interfere…

Mixture-of-ExpertsMulti-Task Learning