Learning Attentional Mixture of LoRAs for Language Model Continual Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningLanguage ModelingLanguage ModellingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models
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
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 LearningMerge before Forget: A Single LoRA Continual Learning via Continual Merging
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 LearningRetrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning
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…
RetrievalMixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models
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