Pre-trained language models (LM) such as BERT, DistilBERT, and RoBERTa can be tuned for different domains (domain-tuning) by continuing the pre-training phase on a new target domain corpus. This simple domain tuning (SDT) technique has been widely used to create domain-tuned models such as BioBERT, SciBERT and ClinicalBERT. However, during the pretraining phase on the target domain, the LM models may catastrophically forget the patterns learned from their source domain. In this work, we study the effects of catastrophic forgetting on domain-tuned LM models and investigate methods that mitigate its negative effects. We propose continual learning (CL) based alternatives for SDT, that aim to reduce catastrophic forgetting. We show that these methods may increase the performance of LM models on downstream target domain tasks. Additionally, we also show that constraining the LM model from forgetting the source domain leads to downstream task models that are more robust to domain shifts. We analyze the computational cost of using our proposed CL methods and provide recommendations for computationally lightweight and effective CL domain-tuning procedures.
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；University of Moratuwa（莫拉图瓦大学）；Toyota Motor Europe（丰田汽车欧洲公司）
With the success of pretraining techniques in representation learning, a number of continual learning methods based on pretrained models have been proposed. Some of these methods design continual learning mechanisms on the pre-trained representations and only allow minimum updates or even no updates of the backbone models during the training of continual learning. In this paper, we question whether the complexity of these models is needed to achieve good performance by comparing them to a simple baseline that we designed. We argue that the pretrained feature extractor itself can be strong enou…
Center for Artificial Intelligence Research (CAiRE)（人工智能研究中心（CAiRE））；Department of Electronic and Computer Engineering（电子与计算机工程系）；The Hong Kong University of Science and Technology（香港科技大学）
Recently, fine-tuning pre-trained language models (e.g., multilingual BERT) to downstream cross-lingual tasks has shown promising results. However, the fine-tuning process inevitably changes the parameters of the pre-trained model and weakens its cross-lingual ability, which leads to sub-optimal performance. To alleviate this problem, we leverage continual learning to preserve the original cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. The experimental result shows that our fine-tuning methods can better preserve the cross-lingual ability of the pre-tr…
The massive scale and growth of textual biomedical data have made its indexing and classification increasingly important. However, existing research on this topic mainly utilized convolutional and recurrent neural networks, which generally achieve inferior performance than the novel transformers. On the other hand, systems that apply transformers only focus on the target documents, overlooking the rich semantic information that label descriptions contain. To address this gap, we develop a transformer-based biomedical text classifier that considers label information. The system achieves this wi…
HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model
School of Advanced Interdisciplinary Sciences, UCAS（UCAS先进交叉科学学院）；MAIS, CASIA（CASIA人工智能研究所）；School of Artificial Intelligence, UCAS（UCAS人工智能学院）；Centre for Artificial Intelligence and Robotics, HKISI-CAS（HKISI-CAS人工智能与机器人中心）；FKLPRIU, School of Computer and Information Engineering, Xiamen University of Technology（厦门理工学院计算机与信息工程学院）
Continual Instruction Tuning for Large Multimodal Models
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；The Peng Cheng Laboratory（鹏城实验室）；Wuhan AI Research（武汉人工智能研究院）
Learn it or Leave it: Module Composition and Pruning for Continual Learning
Bosch Center for Artificial Intelligence（博世人工智能中心）；LMU Munich（慕尼黑大学）；Hochschule der Medien（慕尼黑应用科技大学）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用科技大学）
SwitchCIT: Switching for Continual Instruction Tuning
Coordinated Science Laboratory（协调科学实验室）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Department of Mathematics（数学系）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
Pattern Recognition Center, WeChat AI, Tencent Inc（腾讯公司微信AI模式识别中心）；School of Engineering, Westlake University（西湖大学工程学院）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院先进技术研究所）
East China Normal University（东华大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Xiamen University（厦门大学）；Tencent YouTu Lab（腾讯YouTu实验室）
TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；College of Software, Jilin University（吉林大学软件学院）；Fudan University（复旦大学）；School of Mathematical and Computer Sciences, Heriot-Watt University（赫瑞-瓦特大学数学与计算机科学学院）；Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系）
Korea Advanced Institute of Science and Technology（韩国科学技术院）；LG AI Research（LG人工智能研究院）
Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore an alternative framework to incremental learning where we continually fine-tune the model from a pre-trained representation. Our method takes advantage of linearization technique of a pre-trained neural network for simple and effective continual learning. We show that this allows us to design a linear model where quadratic parameter regularization method is…
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
Khoury College of Computer Sciences, Northeastern University（东北大学克劳尔计算机科学学院）；New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别新实验室）
Arizona State University（亚利桑那州立大学）；Mayo Clinic（梅奥诊所）
The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create such large annotated datasets, as annotating medical images is not only tedious, laborious, and time consuming, but it also demands costly, specialty-oriented skills, which are not easily accessible. To dramatically reduce annotation cost, this paper presents a novel method to naturally integrate active learning and transfer learning (fine-tuning) into a si…
Continual Gradient Low-Rank Projection Fine-Tuning for LLMs
Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通大数据挖掘与具身智能重点实验室）；School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；State Key Laboratory of Advanced Rail Autonomous Operation（先进轨道交通自主运行国家重点实验室）
Previous studies have shown the efficacy of knowledge augmentation methods in pretrained language models. However, these methods behave differently across domains and downstream tasks. In this work, we investigate the augmentation of pretrained language models with commonsense knowledge in the cause-effect relation classification and commonsense causal reasoning tasks. After automatically verbalizing ATOMIC2020, a wide coverage commonsense reasoning knowledge graph, and GLUCOSE, a dataset of implicit commonsense causal knowledge, we continually pretrain BERT and RoBERTa with the verbalized dat…
Pretrained language models have demonstrated outstanding performance in many NLP tasks recently. However, their social intelligence, which requires commonsense reasoning about the current situation and mental states of others, is still developing. Towards improving language models' social intelligence, we focus on the Social IQA dataset, a task requiring social and emotional commonsense reasoning. Building on top of the pretrained RoBERTa and GPT2 models, we propose several architecture variations and extensions, as well as leveraging external commonsense corpora, to optimize the model for Soc…
Gradient Projection For Continual Parameter-Efficient Tuning
School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；School of Information Science and Technology, Xiamen University（厦门大学信息科学与技术学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）
Prompt tuning recently becomes a hot-spot in the applications of large pretrained language models on specific downstream tasks. Regarding the Language Model as a Service (LMaaS), black-box tuning using derivative-free optimization (DFO) provides a novel approach to expand the practical scenarios of pretrained models and enrich the researches of few-shot learning. In this report, we present our solution in this competition that is based on the LMaaS scenario. Our solution consists of several modifications to BBTv2, including multiple label words, selection of P0, rolling update strategy, multi-…
