Proposes RaT to mitigate bias in student-teacher estimation.
problem Systematic bias in teacher's predictions propagates to student model.
method Uses teacher to estimate residuals in student's predictions.
result RaT method reduces teacher bias effect and achieves optimal rate.
Student-teacher learning improves generalization with noisy inputs.
problem Transfer knowledge from clean inputs to noisy inputs.
method Analyzes student-teacher learning using deep linear networks and experiments with nonlinear networks.
result Three factors are vital for success: zero training loss, teacher knowledge, and feature decomposition.
A new teacher-class network method compresses DNNs by distributing knowledge to multiple student networks.
problem Overwhelming size of Deep Neural Networks (DNNs).
method Single teacher with multiple student networks, transferring knowledge to each student.
result The combined knowledge of the class of students achieves better performance and reduces parameters.
Distilled models often fail to match teacher models, despite improving generalization.
problem The discrepancy between teacher and student predictive distributions remains large.
method Investigated the optimization difficulties and dataset details affecting student performance.
result Optimizing for matching the teacher does not always lead to better generalization.
A new distillation method transfers channel information from teacher to student.
problem Transfer knowledge from teacher to student with fewer parameters and calculations.
method Channel Distillation (CD) and Guided Knowledge Distillation (GKD) with loss decay.
result Achieved 27.68% top-1 error on ImageNet with ResNet18, outperforming state-of-the-art methods.
Improved knowledge distillation using a teacher assistant to bridge the gap between student and teacher networks.
problem Large neural networks are hard to deploy on edge devices due to size constraints.
method Introduce multi-step knowledge distillation with an intermediate-sized teacher assistant.
result The proposed multi-step distillation method improves student network performance.
Estimates model performance from compute budget for distillation.
problem Risk mitigation in large-scale distillation.
method Distillation scaling law based on compute budget allocation.
result Maximizes student performance with compute-optimal allocation.
This paper proposes a method to embed teacher knowledge into a student network without increasing parameters.
problem The need for portable neural networks on mobile devices with limited resources.
method Feature embedding approach to distill knowledge from a teacher network to a student network without introducing new parameters.
result The proposed method maintains the performance of the teacher network while significantly reducing computational and storage complexity.
A new method transfers knowledge without data, matching teacher's predictions closely.
problem Lack of access to training data for knowledge transfer.
method Adversarial training to match teacher's predictions without data.
result Zero-shot student performs well on CIFAR10, improving state-of-the-art.
Conditional T/S learning improves student model performance by selectively learning from teacher or ground truth.
problem Teacher's occasional wrong guidance leads to suboptimal student model performance.
method Proposes a conditional T/S learning scheme where the student selectively chooses between teacher and ground truth based on teacher correctness.
result The conditional learning achieves significant performance improvements over traditional T/S learning.
A new KD layer lets student models learn and apply teacher knowledge explicitly.
problem Implicit action of traditional KD on student's feature transform limits its use in intermediate layers.
method Proposes a learnable KD layer that explicitly embeds teacher's knowledge in feature transform.
result Improves KD with two abilities: leveraging teacher's knowledge and feeding forward knowledge deeper.
Two-layer ReLU networks outperform kernel methods in teacher-student settings.
problem Understanding the excess risk of two-layer ReLU neural networks in teacher-student models.
method Investigated a two-phase training process for a student network, comparing it to kernel methods.
result The student network reaches near-global optimality and outperforms kernel methods in minimax optimal rate.
Improved learning to reweight using deep interactions between student and teacher models.
problem Limitation of existing learning to reweight methods in utilizing student model's internal states.
method Proposes an algorithm that uses the student model's internal states to the teacher model, which returns adaptive weights to enhance student model training.
result Significant improvement over previous methods in image classification and neural machine translation experiments.
Self-training with noisy student-teacher boosts keyword spotting accuracy.
problem Robust keyword spotting in challenging conditions.
method Aggressive data augmentation and self-training with noisy student-teacher approach.
result Significant accuracy improvement in difficult conditions, up to 60%.
Subclass distillation improves small models by matching teacher's subclass probabilities.
problem Improving small models trained on limited data.
method Train a small model to match probabilities of subclasses invented by a large teacher model.
result Better small models trained on limited data.
Under-parameterized networks can either copy or average teacher weights, leading to universal optimal solutions.
problem Approximating a teacher network with an under-parameterized student network.
method Analyzing shallow neural networks with erf activation function and unitary teacher weights, proving copy-average configurations are critical points and finding the optimal solution.
result The optimal solution for under-parameterized networks has a universal structure, whether copying or averaging teacher neurons.
KD can lead to student-teacher deviations that improve performance.
problem KD can lead to student-teacher deviations that may outperform the teacher.
method Characterized and explained the nature of student-teacher deviations through experiments and theory.
result KD can lead to improved generalization by exaggerating the implicit bias of gradient descent.
Deep neural networks bring in impressive accuracy in various applications, but the success often relies on the heavy network architecture. Taking well-trained heavy networks as teachers, classical teacher-student learning paradigm aims to learn a student network that is lightweight yet accurate. In this way, a portable…
A new training method improves MLIPs for faster, lighter simulations.
problem High computational and memory costs of complex MLIPs for large-scale MD simulations.
method Teacher-student training framework using latent atomic energy knowledge.
result Lightweight student MLIPs achieve faster MD speeds and comparable accuracy to teachers.
Study shows how task similarity affects forgetting in teacher-student setup.
problem Catastrophic forgetting in continual learning.
method Extended teacher-student setup to multiple teachers, analyzing similarity between tasks.
result Task similarity, whether at readouts or features, influences forgetting and transfer.
Dual Student separates the teacher from the student in SSL, improving performance.
problem Performance bottleneck caused by coupled teacher in consistency-based SSL methods.
method Introduces Dual Student, replacing the teacher with another student and defining a stabilization constraint.
result Significant improvement in classification performance on SSL benchmarks.
This work proposes a student-teacher network for predicting hospital admission locations.
problem Accurate prediction of hospital admission locations to optimize resource allocation.
method Reinforcement learning approach where a teacher network selects data batches for a student network.
result The approach outperforms state-of-the-art methods on tabular data and image recognition.
Knowledge flow transfers knowledge from multiple teachers to a student net.
problem Choosing and initializing deep nets for new tasks is unclear and inefficient.
method Develops a method to move 'knowledge' from multiple deep nets (teachers) to a new net (student) without dependency on teachers.
result The student net outperforms fine-tuning and other methods on various tasks.
Novel framework learns efficient student models from teacher networks.
problem Model capacity gap between teacher and student networks.
method Neural architecture search and oracle knowledge distillation.
result Searched student models often outperform teacher models.
Role-wise data augmentation improves knowledge distillation effectiveness.
problem Existing knowledge distillation methods fail to utilize the full potential of teacher-student data interaction.
method Design and implement data augmentation agents with distinct roles for teacher and student.
result Specially tailored data points enhance the demonstration of teacher's knowledge to the student.
Student network specializes teacher nodes in deep ReLU networks.
problem Training deep ReLU networks with finite width and input dimension.
method Stochastic Gradient Descent (SGD) on over-realized student network trained from teacher network output.
result Each teacher node is specialized by at least one student node at the lowest layer under mild conditions.
ReOPD uses pre-collected teacher trajectories to distill knowledge from multi-turn interactions.
problem The cost of fully online on-policy distillation for multi-turn interactions.
method ReOPD, an off-environment alternative that reuses pre-collected teacher trajectories as replayed prefixes, addressing the prefix trap and distribution shift.
result ReOPD preserves or improves OPD-level accuracy, uses zero tool calls, and is at least 4imes faster per training step. Paper generalizes teacher-student model for realistic data.
problem Capturing learning curves for realistic datasets.
method Introduces a Gaussian covariate generalization of the teacher-student model.
result Generalized model captures learning curves for various realistic data sets.
Paper analyzes how neural networks learn from a teacher in a specific setting.
problem Understanding how two-layer ReLU neural networks learn from a teacher in a regression model.
method Used gradient descent with specific regularization and over-parameterization, combined with measure representation and sparse estimation.
result Student network can identify teacher network parameters with high probability via gradient descent.
The paper reveals three mechanisms for weak-to-strong generalization.
problem Understanding the mechanisms behind weak-to-strong generalization in imperfect labeling scenarios.
method Theoretical analysis of simple models including ridge regression and weighted ridge regression, and a nonlinear multi-index setting.
result A student model can compensate for a teacher's under-regularization and achieve lower test error.
Method teaches students without teachers, estimating true labels from crowdsourcing.
problem Teaching without access to true labels.
method Apply crowdsourcing techniques to estimate true labels and student models for iterative teaching.
result Teaching performance is particularly effective for low-level students.
Proposes KTAN for better training of student networks with both intermediate representations and probability distributions.
problem Reduces large computation and storage cost of deep networks by transferring generalization ability.
method Holistically considers intermediate representations and probability distributions; uses a Teacher-to-Student layer and adversarial learning.
result Significantly improves performance of student networks on image classification and object detection tasks.
The study analyzes multi-class teacher-student perceptron performance and generalization errors.
problem Analyzing multi-class classification with the teacher-student perceptron.
method Deriving asymptotic expressions for Bayes-optimal and empirical risk minimization (ERM) generalization errors.
result Regularised cross-entropy minimization yields close-to-optimal accuracy for multi-class classification.
Meta Pseudo Labels boosts image classification accuracy to 90.2%.
problem Improving semi-supervised learning for image classification.
method Adapts a teacher network to generate better pseudo labels through student feedback.
result Achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet.
Improved machine learning models outperform their simpler counterparts by using imperfect labels.
problem Improving model performance using imperfect labels.
method Random feature ridge regression (RFRR) with a deterministic equivalent for excess test error.
result The student model can outperform the teacher model regardless of the teacher's scaling law, achieving the minimax optimal rate.
A new method for student-initiated action advice using novelty detection.
problem Exploration and sample inefficiency in RL, especially with teacher absence.
method Random Network Distillation (RND) to measure advice novelty, updates only for advised states.
result Significant performance improvement over state-of-the-art methods, especially in challenging scenarios.
A new method identifies a stable subnetwork in overparameterized student models.
problem Identifying a stable subnetwork in overparameterized student models.
method Spectral representation of linear transfer of information, focusing on eigenvalues and eigenvectors.
result A stable student substructure is isolated that mirrors the true complexity of the teacher.
Teaches AI models to learn effectively through dynamic loss functions.
problem Optimizing machine learning models' performance through dynamic loss functions.
method Develops a method for a teacher model to dynamically output loss functions for a student model, enabling gradient-based optimization.
result Significantly improves the performance of various student models in real-world tasks.
Random feature models can outperform a weak teacher with early stopping.
problem Generalization from a weak to a strong model in random feature networks.
method Random feature models, early stopping, proving weak-to-strong generalization.
result Random feature models can outperform a weak teacher with early stopping.
A student classifier learns from feature visualizations of a teacher network to achieve high accuracy.
problem Machine learning-based sleep apnea detection with limited access to training data.
method Interpretation-based indirect knowledge transfer using activation maximization and synthetic datasets.
result The student classifier achieves 97.8% accuracy on MNIST and 86.1-89.5% on Apnea-ECG dataset.
New model shows weak teachers can help strong students learn even with imperfect labels.
problem Improving strong student's performance with weak teacher's imperfect pseudolabels.
method Stylized overparameterized spiked covariance model with Gaussian covariates, proving two phases of generalization.
result Provable successful and random guessing phases of strong student's generalization.
A novel feature selection method using a teacher-student network.
problem Feature selection for high-dimensional data in machine learning.
method Teacher-student network approach for feature selection.
result The proposed TSFS method outperforms existing methods in classification and clustering.
Study reveals how initial weights influence convergence in deep ReLU networks.
problem Understanding the dynamics and generalization of deep ReLU networks.
method Teacher-student setting, gradient analysis, and activation assumptions.
result Initial weights close to teacher nodes lead to faster convergence, and fan-out weights of other nodes converge to zero in over-parameterized cases.
Pea-KD improves BERT student models by 4.4% on average in GLUE tasks.
problem Efficiently compressing BERT while maintaining performance.
method Parameter-efficient and accurate Knowledge Distillation (Pea-KD) with Shuffled Parameter Sharing (SPS) and Pretraining with Teacher's Predictions (PTP).
result Pea-KD improves student model's performance by 4.4% on average in four GLUE tasks.
GAN-TSC improves student model accuracy by augmenting with synthetic data.
problem Suboptimal compression when fresh data is unavailable for TSC.
method Augment compression dataset with synthetic data from a GAN.
result Significant improvement in student accuracy for expensive models.
Knowledge transfer speeds up neural classifier training.
problem Lack of theoretical analysis of knowledge transfer in neural networks.
method Regularization of fit between teacher and student networks using privileged information.
result Wide two-layer networks can interpolate between privileged information and data, improving generalization.
Researchers study how teachers' advising relationships influence their perceptions of satisfaction and students, not policy influence.
problem Understanding the relationship between teachers' advising relationships and their perceptions of satisfaction and students.
method Proposed a novel joint model of network and item responses (JNIRM) with correlated latent variables.
result Teachers' advising relationships contribute more to satisfaction and students than to influence over educational policies.
Enhances model compression with multi-teacher knowledge distillation.
problem Uncertainty evaluation and diverse teacher expertise in model deployment.
method Bayesian inference and teacher-informed prior with entropy-based weighting.
result Improved predictive accuracy and robust uncertainty quantification.