Active Few-Shot Fine-Tuning

• URL: http://arxiv.org/abs/2402.15441v4
• Date: Fri, 21 Jun 2024 08:48:18 GMT
• Title: Active Few-Shot Fine-Tuning
• Authors: Jonas Hübotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause,
• Abstract summary: We study the question: How can we select the right data for fine-tuning to a specific task? We call this data selection problem active fine-tuning and show that it is an instance of transductive active learning. We propose ITL, short for information-based transductive learning, an approach which samples adaptively to maximize information gained about the specified task.
• Score: 35.49225932333298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the question: How can we select the right data for fine-tuning to a specific task? We call this data selection problem active fine-tuning and show that it is an instance of transductive active learning, a novel generalization of classical active learning. We propose ITL, short for information-based transductive learning, an approach which samples adaptively to maximize information gained about the specified task. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We apply ITL to the few-shot fine-tuning of large neural networks and show that fine-tuning with ITL learns the task with significantly fewer examples than the state-of-the-art.

Related papers

• Transductive Model Selection under Prior Probability Shift [49.56191463229252]
  Transductive learning is a supervised machine learning task in which the unlabelled data that require labelling are a finite set and are available at training time.<n>We propose a method, tailored to transductive classification contexts, for performing model selection when the data exhibit prior probability shift.
  arXiv  Detail & Related papers  (2025-07-30T13:03:24Z)
• 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)
• DeepONet as a Multi-Operator Extrapolation Model: Distributed Pretraining with Physics-Informed Fine-Tuning [6.635683993472882]
  We propose a novel fine-tuning method to achieve multi-operator learning. Our approach combines distributed learning to integrate data from various operators in pre-training, while physics-informed methods enable zero-shot fine-tuning.
  arXiv  Detail & Related papers  (2024-11-11T18:58:46Z)
• Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence [60.37934652213881]
  Domain Adaptation (DA) facilitates knowledge transfer from a source domain to a related target domain. This paper investigates a practical DA paradigm, namely Source data-Free Active Domain Adaptation (SFADA), where source data becomes inaccessible during adaptation. We present learn from the learnt (LFTL), a novel paradigm for SFADA to leverage the learnt knowledge from the source pretrained model and actively iterated models without extra overhead.
  arXiv  Detail & Related papers  (2024-07-26T17:51:58Z)
• Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning [85.66907881270785]
  We propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training. In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk. In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training.
  arXiv  Detail & Related papers  (2024-01-07T18:12:20Z)
• FUNCK: Information Funnels and Bottlenecks for Invariant Representation Learning [7.804994311050265]
  We investigate a set of related information funnels and bottleneck problems that claim to learn invariant representations from the data. We propose a new element to this family of information-theoretic objectives: The Conditional Privacy Funnel with Side Information. Given the generally intractable objectives, we derive tractable approximations using amortized variational inference parameterized by neural networks.
  arXiv  Detail & Related papers  (2022-11-02T19:37:55Z)
• CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning [55.733193075728096]
  Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
  arXiv  Detail & Related papers  (2022-02-11T13:49:51Z)
• Continual Learning via Bit-Level Information Preserving [88.32450740325005]
  We study the continual learning process through the lens of information theory. We propose Bit-Level Information Preserving (BLIP) that preserves the information gain on model parameters. BLIP achieves close to zero forgetting while only requiring constant memory overheads throughout continual learning.
  arXiv  Detail & Related papers  (2021-05-10T15:09:01Z)
• Active Learning: Problem Settings and Recent Developments [2.1574781022415364]
  This paper explains the basic problem settings of active learning and recent research trends. In particular, research on learning acquisition functions to select samples from the data for labeling, theoretical work on active learning algorithms, and stopping criteria for sequential data acquisition are highlighted.
  arXiv  Detail & Related papers  (2020-12-08T05:24:06Z)
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning [79.32403825036792]
  We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials. We show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent's ability to try out novel behaviors.
  arXiv  Detail & Related papers  (2020-11-19T18:47:40Z)
• Sequential Transfer in Reinforcement Learning with a Generative Model [48.40219742217783]
  We show how to reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. We derive PAC bounds on its sample complexity which clearly demonstrate the benefits of using this kind of prior knowledge. We empirically verify our theoretical findings in simple simulated domains.
  arXiv  Detail & Related papers  (2020-07-01T19:53:35Z)
• Exploring and Predicting Transferability across NLP Tasks [115.6278033699853]
  We study the transferability between 33 NLP tasks across three broad classes of problems. Our results show that transfer learning is more beneficial than previously thought. We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task.
  arXiv  Detail & Related papers  (2020-05-02T09:39:36Z)

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.