KIF: Knowledge Identification and Fusion for Language Model Continual Learning
Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. A major challenge in this domain is catastrophic forgetting, where models lose previously acquired knowledge upon learning new tasks. Existing approaches commonly utilize multiple parameter-efficient fine-tuning (PEFT) blocks to acquire task-specific knowledge, yet these methods are inefficient and fail to leverage potential knowledge transfer across tasks. In this paper, we introduce a novel CL framework for language models, named Knowledge Identification and Fusion (KIF), which boosts knowledge transfer without depending on memory replay. KIF initially segregates the model into 'skill units' based on parameter dependencies, allowing for more precise control. Subsequently, it employs a novel group-wise knowledge identification technique to ascertain the importance distribution of skill units for a new task. By comparing this importance distribution with those from previous tasks, we implement a fine-grained knowledge fusion strategy that retains task-specific knowledge, thereby preventing forgetting, and updates task-shared knowledge, which facilitates bi-directional knowledge transfer. As a result, KIF achieves an optimal balance between retaining prior knowledge and excelling in new tasks. KIF also demonstrates strong generalizability, making it suitable for various base models and adaptable to PEFT methods like LoRA. Furthermore, it offers notable extensibility, supporting enhancements through integration with memory replay techniques. Comprehensive experiments conducted on two CL benchmarks, involving models ranging from 220M to 7B parameters, affirm the effectiveness of KIF and its variants across different settings.
Code (1)
Tasks
Continual LearningLanguage ModelingLanguage Modellingparameter-efficient fine-tuningTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning
Continual learning (CL) is crucial for deploying large language models (LLMs) in dynamic real-world environments without costly retraining. While recent model ensemble and model merging methods guided by parameter import…
Continual LearningLanguage ModelingLanguage ModellingTransfer LearningLamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting
Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose La…
Language IdentificationSpeech RecognitionKnowledge Grafting of Large Language Models
Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent works like FuseLLM and FuseChat have dem…
Continual LearningKnowledge DistillationLarge Language ModelModel Compression+1Synthetic Data is an Elegant GIFT for Continual Vision-Language Models
Pre-trained Vision-Language Models (VLMs) require Continual Learning (CL) to efficiently update their knowledge and adapt to various downstream tasks without retraining from scratch. However, for VLMs, in addition to the…
Continual LearningImage GenerationFederated Continual Learning via Knowledge Fusion: A Survey
Data privacy and silos are nontrivial and greatly challenging in many real-world applications. Federated learning is a decentralized approach to training models across multiple local clients without the exchange of raw d…
Continual LearningFederated LearningSurvey