AUKT: Adaptive Uncertainty-Guided Knowledge Transfer with Conformal Prediction
- URL: http://arxiv.org/abs/2502.16736v2
- Date: Tue, 25 Feb 2025 04:07:57 GMT
- Title: AUKT: Adaptive Uncertainty-Guided Knowledge Transfer with Conformal Prediction
- Authors: Rui Liu, Peng Gao, Yu Shen, Ming Lin, Pratap Tokekar,
- Abstract summary: We propose a novel framework to dynamically adjust the student's reliance on the teacher's guidance based on the teacher's prediction uncertainty.<n>We validate the proposed framework across diverse applications, including image classification, imitation-guided reinforcement learning, and autonomous driving.
- Score: 38.20651868834144
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Knowledge transfer between teacher and student models has proven effective across various machine learning applications. However, challenges arise when the teacher's predictions are noisy, or the data domain during student training shifts from the teacher's pretraining data. In such scenarios, blindly relying on the teacher's predictions can lead to suboptimal knowledge transfer. To address these challenges, we propose a novel and universal framework, Adaptive Uncertainty-guided Knowledge Transfer ($\textbf{AUKT}$), which leverages Conformal Prediction (CP) to dynamically adjust the student's reliance on the teacher's guidance based on the teacher's prediction uncertainty. CP is a distribution-free, model-agnostic approach that provides reliable prediction sets with statistical coverage guarantees and minimal computational overhead. This adaptive mechanism mitigates the risk of learning undesirable or incorrect knowledge. We validate the proposed framework across diverse applications, including image classification, imitation-guided reinforcement learning, and autonomous driving. Experimental results consistently demonstrate that our approach improves performance, robustness and transferability, offering a promising direction for enhanced knowledge transfer in real-world applications.
Related papers
- Global Variational Inference Enhanced Robust Domain Adaptation [7.414646586981638]
We propose a framework that learns continuous, class-conditional global priors via variational inference to enable structure-aware cross-domain alignment.<n>GVI-DA minimizes domain gaps through latent feature reconstruction, and mitigates posterior collapse using global codebook learning with randomized sampling.<n>It further improves robustness by discarding low-confidence pseudo-labels and generating reliable target-domain samples.
arXiv Detail & Related papers (2025-07-04T04:43:23Z) - Variational Supervised Contrastive Learning [50.79938854370321]
We propose Variational Supervised Contrastive Learning (VarCon), which reformulates supervised contrastive learning as variational inference over latent class variables.<n>VarCon achieves state-of-the-art performance for contrastive learning frameworks, reaching 79.36% Top-1 accuracy on ImageNet-1K and 78.29% on CIFAR-100 with a ResNet-50 encoder.
arXiv Detail & Related papers (2025-06-09T04:19:12Z) - Learning to Reason without External Rewards [100.27210579418562]
Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision.<n>We explore Reinforcement Learning from Internal Feedback (RLIF), a framework that enables LLMs to learn from intrinsic signals without external rewards or labeled data.<n>We propose Intuitor, an RLIF method that uses a model's own confidence, termed self-certainty, as its sole reward signal.
arXiv Detail & Related papers (2025-05-26T07:01:06Z) - Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation [5.122518070721238]
Co-STAR integrates curriculum learning with collaborative self-training between a source-trained teacher and a contrastive vision-language model (CLIP)
Our curriculum learning approach employs a reliability-based weight function that measures bidirectional prediction alignment between the teacher and CLIP, balancing between confident and uncertain predictions.
To further improve adaptation, we propose Adaptive Curriculum Regularization, which modifies the learning priority of samples in a probabilistic, adaptive manner based on their confidence scores and prediction stability.
arXiv Detail & Related papers (2025-04-15T23:47:35Z) - Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization [2.733505168507872]
Drone-view Geo-Localization (DVGL) aims to achieve accurate localization of drones by retrieving the most relevant GPS-tagged satellite images.<n>Existing methods heavily rely on strictly pre-paired drone-satellite images for supervised learning.<n>We propose an end-to-end self-supervised learning method with a shallow backbone network.
arXiv Detail & Related papers (2025-02-17T02:53:08Z) - CGLearn: Consistent Gradient-Based Learning for Out-of-Distribution Generalization [0.7366405857677226]
In this work, we introduce a simple yet powerful approach, CGLearn, which relies on the agreement of gradients across various environments.
Our proposed method demonstrates superior performance compared to state-of-the-art methods in both linear and nonlinear settings.
Comprehensive experiments on both synthetic and real-world datasets highlight its effectiveness in diverse scenarios.
arXiv Detail & Related papers (2024-11-09T02:36:39Z) - Disentangling Masked Autoencoders for Unsupervised Domain Generalization [57.56744870106124]
Unsupervised domain generalization is fast gaining attention but is still far from well-studied.
Disentangled Masked Auto (DisMAE) aims to discover the disentangled representations that faithfully reveal intrinsic features.
DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders.
arXiv Detail & Related papers (2024-07-10T11:11:36Z) - Improve Knowledge Distillation via Label Revision and Data Selection [37.74822443555646]
This paper proposes to rectify the teacher's inaccurate predictions using the ground truth.
In the latter, we introduce a data selection technique to choose suitable training samples to be supervised by the teacher.
Experiment results demonstrate the effectiveness of our proposed method, and show that our method can be combined with other distillation approaches.
arXiv Detail & Related papers (2024-04-03T02:41:16Z) - Selective Knowledge Sharing for Privacy-Preserving Federated
Distillation without A Good Teacher [52.2926020848095]
Federated learning is vulnerable to white-box attacks and struggles to adapt to heterogeneous clients.
This paper proposes a selective knowledge sharing mechanism for FD, termed Selective-FD.
arXiv Detail & Related papers (2023-04-04T12:04:19Z) - Improving Adaptive Conformal Prediction Using Self-Supervised Learning [72.2614468437919]
We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores.
We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.
arXiv Detail & Related papers (2023-02-23T18:57:14Z) - Differentiating Student Feedbacks for Knowledge Tracing [28.669001606806525]
We propose a framework to reweight the contribution of different responses based on their discrimination in training.<n>We also introduce an adaptive predictive score fusion technique to maintain accuracy on less discriminative responses.
arXiv Detail & Related papers (2022-12-16T13:55:07Z) - Distantly-Supervised Named Entity Recognition with Adaptive Teacher
Learning and Fine-grained Student Ensemble [56.705249154629264]
Self-training teacher-student frameworks are proposed to improve the robustness of NER models.
In this paper, we propose an adaptive teacher learning comprised of two teacher-student networks.
Fine-grained student ensemble updates each fragment of the teacher model with a temporal moving average of the corresponding fragment of the student, which enhances consistent predictions on each model fragment against noise.
arXiv Detail & Related papers (2022-12-13T12:14:09Z) - Learning Domain Adaptive Object Detection with Probabilistic Teacher [93.76128726257946]
We present a simple yet effective framework, termed as Probabilistic Teacher (PT)
PT aims to capture the uncertainty of unlabeled target data from a gradually evolving teacher and guides the learning of a student in a mutually beneficial manner.
We also present a novel Entropy Focal Loss (EFL) to further facilitate the uncertainty-guided self-training.
arXiv Detail & Related papers (2022-06-13T16:24:22Z) - Agree to Disagree: Diversity through Disagreement for Better
Transferability [54.308327969778155]
We propose D-BAT (Diversity-By-disAgreement Training), which enforces agreement among the models on the training data.
We show how D-BAT naturally emerges from the notion of generalized discrepancy.
arXiv Detail & Related papers (2022-02-09T12:03:02Z) - Shuffle Augmentation of Features from Unlabeled Data for Unsupervised
Domain Adaptation [21.497019000131917]
Unsupervised Domain Adaptation (UDA) is a branch of transfer learning where labels for target samples are unavailable.
In this paper, we propose Shuffle Augmentation of Features (SAF) as a novel UDA framework.
SAF learns from the target samples, adaptively distills class-aware target features, and implicitly guides the classifier to find comprehensive class borders.
arXiv Detail & Related papers (2022-01-28T07:11:05Z) - Grasping Detection Network with Uncertainty Estimation for
Confidence-Driven Semi-Supervised Domain Adaptation [17.16216430459064]
This paper presents an approach enabling the easy domain adaptation through a novel grasping detection network with confidence-driven semi-supervised learning.
The proposed grasping detection network specially provides a prediction uncertainty estimation mechanism by leveraging on Feature Pyramid Network (FPN), and the mean-teacher semi-supervised learning utilizes such uncertainty information to emphasizing the consistency loss only for those unlabelled data with high confidence.
Our results show that the proposed network can achieve high success rate on the Cornell grasping dataset, and for domain adaptation with very limited data, the confidence-driven mean teacher outperforms the original mean teacher and direct training by more than 10% in evaluation
arXiv Detail & Related papers (2020-08-20T07:42:45Z) - Foreseeing the Benefits of Incidental Supervision [83.08441990812636]
This paper studies whether we can, in a single framework, quantify the benefits of various types of incidental signals for a given target task without going through experiments.
We propose a unified PAC-Bayesian motivated informativeness measure, PABI, that characterizes the uncertainty reduction provided by incidental supervision signals.
arXiv Detail & Related papers (2020-06-09T20:59:42Z) - Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic
Segmentation [63.75774438196315]
Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data.
Most existing methods suffer from noticeable negative transfer resulting from either the error-prone discriminator network or the unreasonable teacher model.
We propose an uncertainty-aware consistency regularization method for cross-domain semantic segmentation.
arXiv Detail & Related papers (2020-04-19T15:30:26Z)
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.