REP: Resource-Efficient Prompting for On-device Continual Learning

• URL: http://arxiv.org/abs/2406.04772v1
• Date: Fri, 7 Jun 2024 09:17:33 GMT
• Title: REP: Resource-Efficient Prompting for On-device Continual Learning
• Authors: Sungho Jeon, Xinyue Ma, Kwang In Kim, Myeongjae Jeon,
• Abstract summary: On-device continual learning (CL) requires the co-optimization of model accuracy and resource efficiency to be practical. It is commonly believed that CNN-based CL excels in resource efficiency, whereas ViT-based CL is superior in model performance. We introduce REP, which improves resource efficiency specifically targeting prompt-based rehearsal-free methods.
• Score: 23.92661395403251
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: On-device continual learning (CL) requires the co-optimization of model accuracy and resource efficiency to be practical. This is extremely challenging because it must preserve accuracy while learning new tasks with continuously drifting data and maintain both high energy and memory efficiency to be deployable on real-world devices. Typically, a CL method leverages one of two types of backbone networks: CNN or ViT. It is commonly believed that CNN-based CL excels in resource efficiency, whereas ViT-based CL is superior in model performance, making each option attractive only for a single aspect. In this paper, we revisit this comparison while embracing powerful pre-trained ViT models of various sizes, including ViT-Ti (5.8M parameters). Our detailed analysis reveals that many practical options exist today for making ViT-based methods more suitable for on-device CL, even when accuracy, energy, and memory are all considered. To further expand this impact, we introduce REP, which improves resource efficiency specifically targeting prompt-based rehearsal-free methods. Our key focus is on avoiding catastrophic trade-offs with accuracy while trimming computational and memory costs throughout the training process. We achieve this by exploiting swift prompt selection that enhances input data using a carefully provisioned model, and by developing two novel algorithms-adaptive token merging (AToM) and adaptive layer dropping (ALD)-that optimize the prompt updating stage. In particular, AToM and ALD perform selective skipping across the data and model-layer dimensions without compromising task-specific features in vision transformer models. Extensive experiments on three image classification datasets validate REP's superior resource efficiency over current state-of-the-art methods.

Related papers

• Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval [49.669503570350166]
  Generative information retrieval (GenIR) is a promising neural retrieval paradigm that formulates document retrieval as a document identifier (docid) generation task. Existing GenIR models suffer from token-level misalignment, where models trained to predict the next token often fail to capture document-level relevance effectively. We propose direct document relevance optimization (DDRO), which aligns token-level docid generation with document-level relevance estimation through direct optimization via pairwise ranking.
  arXiv  Detail & Related papers  (2025-04-07T15:27:37Z)
• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• Active Prompt Learning with Vision-Language Model Priors [9.173468790066956]
  We introduce a class-guided clustering that leverages the pre-trained image and text encoders of vision-language models. We propose a budget-saving selective querying based on adaptive class-wise thresholds.
  arXiv  Detail & Related papers  (2024-11-23T02:34:33Z)
• SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models [27.522743690956315]
  We propose a SElective attEntion-guided Knowledge Retention method (SEEKR) for data-efficient replay-based continual learning of large language models (LLMs) SEEKR performs attention distillation on the selected attention heads for finer-grained knowledge retention. Experimental results on two continual learning benchmarks for LLMs demonstrate the superiority of SEEKR over the existing methods on both performance and efficiency.
  arXiv  Detail & Related papers  (2024-11-09T13:02:36Z)
• DELIFT: Data Efficient Language model Instruction Fine Tuning [13.538140114667772]
  We introduce DELIFT, a novel algorithm that systematically optimize data selection across the three key stages of fine-tuning. Experiments across various tasks and model scales demonstrate that DELIFT can reduce the fine-tuning data size by up to 70% without compromising performance.
  arXiv  Detail & Related papers  (2024-11-07T04:38:29Z)
• SUDS: A Strategy for Unsupervised Drift Sampling [0.5437605013181142]
  Supervised machine learning encounters concept drift, where the data distribution changes over time, degrading performance. We present the Strategy for Drift Sampling (SUDS), a novel method that selects homogeneous samples for retraining using existing drift detection algorithms. Our results demonstrate the efficacy of SUDS in optimizing labeled data use in dynamic environments.
  arXiv  Detail & Related papers  (2024-11-05T10:55:29Z)
• QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning [58.767866109043055]
  We introduce Query-dependent Prompt Optimization (QPO), which iteratively fine-tune a small pretrained language model to generate optimal prompts tailored to the input queries. We derive insights from offline prompting demonstration data, which already exists in large quantities as a by-product of benchmarking diverse prompts on open-sourced tasks. Experiments on various LLM scales and diverse NLP and math tasks demonstrate the efficacy and cost-efficiency of our method in both zero-shot and few-shot scenarios.
  arXiv  Detail & Related papers  (2024-08-20T03:06:48Z)
• Efficient and Versatile Robust Fine-Tuning of Zero-shot Models [34.27380518351181]
  We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks. Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially. Our experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders.
  arXiv  Detail & Related papers  (2024-08-11T11:37:43Z)
• Adaptive Rentention & Correction for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task. We name our approach Adaptive Retention & Correction (ARC) ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL [62.824464372594576]
  We aim to enhance arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective of query dependency in such optimization. We introduce Prompt-OIRL, which harnesses offline inverse reinforcement learning to draw insights from offline prompting demonstration data.
  arXiv  Detail & Related papers  (2023-09-13T01:12:52Z)
• Knowledge Transfer-Driven Few-Shot Class-Incremental Learning [23.163459923345556]
  Few-shot class-incremental learning (FSCIL) aims to continually learn new classes using a few samples while not forgetting the old classes. Despite the advance of existing FSCIL methods, the proposed knowledge transfer learning schemes are sub-optimal due to the insufficient optimization for the model's plasticity. We propose a Random Episode Sampling and Augmentation (RESA) strategy that relies on diverse pseudo incremental tasks as agents to achieve the knowledge transfer.
  arXiv  Detail & Related papers  (2023-06-19T14:02:45Z)
• The Cost of Learning: Efficiency vs. Efficacy of Learning-Based RRM for 6G [10.28841351455586]
  Deep Reinforcement Learning (DRL) has become a valuable solution to automatically learn efficient resource management strategies in complex networks. In many scenarios, the learning task is performed in the Cloud, while experience samples are generated directly by edge nodes or users. This creates a friction between the need to speed up convergence towards an effective strategy, which requires the allocation of resources to transmit learning samples. We propose a dynamic balancing strategy between the learning and data planes, which allows the centralized learning agent to quickly converge to an efficient resource allocation strategy.
  arXiv  Detail & Related papers  (2022-11-30T11:26:01Z)
• FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification [47.24770508263431]
  We develop FiLM Transfer (FiT) which fulfills requirements in the image classification setting. FiT uses an automatically configured Naive Bayes classifier on top of a fixed backbone that has been pretrained on large image datasets. We show that FiT achieves better classification accuracy than the state-of-the-art Big Transfer (BiT) algorithm at low-shot and on the challenging VTAB-1k benchmark.
  arXiv  Detail & Related papers  (2022-06-17T10:17:20Z)
• RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning [84.75064077323098]
  This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL) RLPrompt is flexibly applicable to different types of LMs, such as masked gibberish (e.g., grammaBERT) and left-to-right models (e.g., GPTs) Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing finetuning or prompting methods.
  arXiv  Detail & Related papers  (2022-05-25T07:50:31Z)
• Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning [81.3514358542452]
  Few-shot in-context learning (ICL) incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made. parameter-efficient fine-tuning offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task. In this paper, we rigorously compare few-shot ICL and parameter-efficient fine-tuning and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs.
  arXiv  Detail & Related papers  (2022-05-11T17:10:41Z)
• Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
  Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples. We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment. We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
  arXiv  Detail & Related papers  (2022-03-23T06:24:31Z)
• Mitigating Sampling Bias and Improving Robustness in Active Learning [13.994967246046008]
  We introduce supervised contrastive active learning by leveraging the contrastive loss for active learning under a supervised setting. We propose an unbiased query strategy that selects informative data samples of diverse feature representations. We empirically demonstrate our proposed methods reduce sampling bias, achieve state-of-the-art accuracy and model calibration in an active learning setup.
  arXiv  Detail & Related papers  (2021-09-13T20:58:40Z)
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective [52.497514255040514]
  This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment. We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes. Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2021-05-03T07:23:39Z)
• Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement [56.40587594647692]
  We propose a novel transfer learning algorithm, introducing the idea of Target-awareness REpresentation Disentanglement (TRED) TRED disentangles the relevant knowledge with respect to the target task from the original source model and used as a regularizer during fine-tuning the target model. Experiments on various real world datasets show that our method stably improves the standard fine-tuning by more than 2% in average.
  arXiv  Detail & Related papers  (2020-10-16T17:45:08Z)

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.