TaSL: Task Skill Localization and Consolidation for Language Model Continual Learning
- URL: http://arxiv.org/abs/2408.05200v2
- Date: Fri, 30 Aug 2024 11:14:17 GMT
- Title: TaSL: Task Skill Localization and Consolidation for Language Model Continual Learning
- Authors: Yujie Feng, Xu Chu, Yongxin Xu, Zexin Lu, Bo Liu, Philip S. Yu, Xiao-Ming Wu,
- Abstract summary: 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.
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.
We introduce a novel CL framework for language models, named Task Skill Localization and Consolidation (TaSL), which boosts knowledge transfer without depending on memory replay.
- Score: 41.28933724210434
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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 Task Skill Localization and Consolidation (TaSL), which boosts knowledge transfer without depending on memory replay. TaSL initially segregates the model into 'skill units' based on parameter dependencies, allowing for more precise control. Subsequently, it employs a novel group-wise skill localization 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 skill consolidation strategy that retains task-specific knowledge, thereby preventing forgetting, and updates task-shared knowledge, which facilitates bi-directional knowledge transfer. As a result, TaSL achieves an optimal balance between retaining prior knowledge and excelling in new tasks. TaSL 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 TaSL and its variants across different settings.
Related papers
- Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning [79.46570165281084]
We propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods.
MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections.
Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks.
arXiv Detail & Related papers (2024-11-11T07:36:19Z) - TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation [14.533890076297393]
We present TaSL, a novel framework for task skill localization and consolidation.
TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas.
As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks.
arXiv Detail & Related papers (2024-08-19T10:01:28Z) - Scalable Language Model with Generalized Continual Learning [58.700439919096155]
The Joint Adaptive Re-ization (JARe) is integrated with Dynamic Task-related Knowledge Retrieval (DTKR) to enable adaptive adjustment of language models based on specific downstream tasks.
Our method demonstrates state-of-the-art performance on diverse backbones and benchmarks, achieving effective continual learning in both full-set and few-shot scenarios with minimal forgetting.
arXiv Detail & Related papers (2024-04-11T04:22:15Z) - SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models [71.78800549517298]
Continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world.
Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input.
We propose a novel Shared Attention Framework (SAPT) to align the PET learning and selection via the Shared Attentive Learning & Selection module.
arXiv Detail & Related papers (2024-01-16T11:45:03Z) - LLM Augmented LLMs: Expanding Capabilities through Composition [56.40953749310957]
CALM -- Composition to Augment Language Models -- introduces cross-attention between models to compose their representations and enable new capabilities.
We illustrate that augmenting PaLM2-S with a smaller model trained on low-resource languages results in an absolute improvement of up to 13% on tasks like translation into English.
When PaLM2-S is augmented with a code-specific model, we see a relative improvement of 40% over the base model for code generation and explanation tasks.
arXiv Detail & Related papers (2024-01-04T18:53:01Z) - Concept-aware Training Improves In-context Learning Ability of Language
Models [0.0]
Many recent language models (LMs) of Transformers family exhibit so-called in-context learning (ICL) ability.
We propose a method to create LMs able to better utilize the in-context information.
We measure that data sampling of Concept-aware Training consistently improves models' reasoning ability.
arXiv Detail & Related papers (2023-05-23T07:44:52Z) - A Framework of Meta Functional Learning for Regularising Knowledge
Transfer [89.74127682599898]
This work proposes a novel framework of Meta Functional Learning (MFL) by meta-learning a generalisable functional model from data-rich tasks.
The MFL computes meta-knowledge on functional regularisation generalisable to different learning tasks by which functional training on limited labelled data promotes more discriminative functions to be learned.
arXiv Detail & Related papers (2022-03-28T15:24:09Z)
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.