NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating
True Coverage
- URL: http://arxiv.org/abs/2306.04099v1
- Date: Wed, 7 Jun 2023 01:43:47 GMT
- Title: NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating
True Coverage
- Authors: Ziting Wen, Oscar Pizarro, Stefan Williams
- Abstract summary: We propose a novel active learning strategy, neural tangent kernel clustering-pseudo-labels (NTKCPL)
It estimates empirical risk based on pseudo-labels and the model prediction with NTK approximation.
We validate our method on five datasets, empirically demonstrating that it outperforms the baseline methods in most cases.
- Score: 3.4806267677524896
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: High annotation cost for training machine learning classifiers has driven
extensive research in active learning and self-supervised learning. Recent
research has shown that in the context of supervised learning different active
learning strategies need to be applied at various stages of the training
process to ensure improved performance over the random baseline. We refer to
the point where the number of available annotations changes the suitable active
learning strategy as the phase transition point. In this paper, we establish
that when combining active learning with self-supervised models to achieve
improved performance, the phase transition point occurs earlier. It becomes
challenging to determine which strategy should be used for previously unseen
datasets. We argue that existing active learning algorithms are heavily
influenced by the phase transition because the empirical risk over the entire
active learning pool estimated by these algorithms is inaccurate and influenced
by the number of labeled samples. To address this issue, we propose a novel
active learning strategy, neural tangent kernel clustering-pseudo-labels
(NTKCPL). It estimates empirical risk based on pseudo-labels and the model
prediction with NTK approximation. We analyze the factors affecting this
approximation error and design a pseudo-label clustering generation method to
reduce the approximation error. We validate our method on five datasets,
empirically demonstrating that it outperforms the baseline methods in most
cases and is valid over a wider range of training budgets.
Related papers
- Querying Easily Flip-flopped Samples for Deep Active Learning [63.62397322172216]
Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data.
One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is.
This paper proposes the it least disagree metric (LDM) as the smallest probability of disagreement of the predicted label.
arXiv Detail & Related papers (2024-01-18T08:12:23Z) - Learning Objective-Specific Active Learning Strategies with Attentive
Neural Processes [72.75421975804132]
Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting.
We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem.
Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
arXiv Detail & Related papers (2023-09-11T14:16:37Z) - Active Learning Guided by Efficient Surrogate Learners [25.52920030051264]
Re-training a deep learning model each time a single data point receives a new label is impractical.
We introduce a new active learning algorithm that harnesses the power of a Gaussian process surrogate in conjunction with the neural network principal learner.
Our proposed model adeptly updates the surrogate learner for every new data instance, enabling it to emulate and capitalize on the continuous learning dynamics of the neural network.
arXiv Detail & Related papers (2023-01-07T01:35:25Z) - Responsible Active Learning via Human-in-the-loop Peer Study [88.01358655203441]
We propose a responsible active learning method, namely Peer Study Learning (PSL), to simultaneously preserve data privacy and improve model stability.
We first introduce a human-in-the-loop teacher-student architecture to isolate unlabelled data from the task learner (teacher) on the cloud-side.
During training, the task learner instructs the light-weight active learner which then provides feedback on the active sampling criterion.
arXiv Detail & Related papers (2022-11-24T13:18:27Z) - Making Look-Ahead Active Learning Strategies Feasible with Neural
Tangent Kernels [6.372625755672473]
We propose a new method for approximating active learning acquisition strategies that are based on retraining with hypothetically-labeled candidate data points.
Although this is usually infeasible with deep networks, we use the neural tangent kernel to approximate the result of retraining.
arXiv Detail & Related papers (2022-06-25T06:13:27Z) - Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective [67.45111837188685]
Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data.
We experimentally analyze neural network models trained by CIL algorithms using various evaluation protocols in representation learning.
arXiv Detail & Related papers (2022-06-16T11:44:11Z) - MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition.
We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL)
In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
arXiv Detail & Related papers (2021-07-23T06:57:08Z) - Active Learning for Sequence Tagging with Deep Pre-trained Models and
Bayesian Uncertainty Estimates [52.164757178369804]
Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget.
We conduct an empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework.
We also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance.
arXiv Detail & Related papers (2021-01-20T13:59:25Z) - Ask-n-Learn: Active Learning via Reliable Gradient Representations for
Image Classification [29.43017692274488]
Deep predictive models rely on human supervision in the form of labeled training data.
We propose Ask-n-Learn, an active learning approach based on gradient embeddings obtained using the pesudo-labels estimated in each of the algorithm.
arXiv Detail & Related papers (2020-09-30T05:19:56Z) - Active Learning for Gaussian Process Considering Uncertainties with
Application to Shape Control of Composite Fuselage [7.358477502214471]
We propose two new active learning algorithms for the Gaussian process with uncertainties.
We show that the proposed approach can incorporate the impact from uncertainties, and realize better prediction performance.
This approach has been applied to improving the predictive modeling for automatic shape control of composite fuselage.
arXiv Detail & Related papers (2020-04-23T02:04:53Z) - Fase-AL -- Adaptation of Fast Adaptive Stacking of Ensembles for
Supporting Active Learning [0.0]
This work presents the FASE-AL algorithm which induces classification models with non-labeled instances using Active Learning.
The algorithm achieves promising results in terms of the percentage of correctly classified instances.
arXiv Detail & Related papers (2020-01-30T17:25:47Z)
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.