Paper distills word embeddings to reduce dimensionality without sacrificing accuracy.
problem Reducing neural model size for practical deployment.
method Teacher-student model-based embedding distillation with ensemble learning.
result Significant reduction in model size (80x faster and lighter) with minimal accuracy loss.
Survey of knowledge distillation for resource-limited devices.
problem Deploying large deep learning models on resource-limited devices.
method Knowledge distillation using a smaller model trained with information from a larger model.
result A new metric (distillation metric) for comparing different knowledge distillation algorithms.
SARD improves deep learning clinical prediction performance.
problem Deep learning models struggle to match linear models in healthcare predictions.
method Reverse Distillation to initialize deep models, combined with contextual and temporal embeddings.
result SARD outperforms state-of-the-art methods on clinical prediction outcomes.
DSE learns sentence embeddings from cross-attention models to speed up sentence-pair similarity computation.
problem Computing sentence-pair similarity is computationally expensive when candidate sentences are large.
method Distilled Sentence Embedding (DSE) based on knowledge distillation from cross-attentive models.
result DSE significantly outperforms ELMO variants and other sentence embedding methods, accelerating computation by several orders of magnitude.
We propose a novel Wasserstein method with a distillation mechanism, yielding joint learning of word embeddings and topics. The proposed method is based on the fact that the Euclidean distance between word embeddings may be employed as the underlying distance in the Wasserstein topic model. The word distributions of to…
Graph-based RKD improves knowledge distillation for resource-constrained systems.
problem Efficiently distill deep learning knowledge for resource-constrained systems.
method Graph-based relative knowledge distillation (RKD) to capture latent space geometry.
result The proposed method achieves better accuracy with the same resource budget.
Paper proposes G-CRD to improve GNNs by preserving global graph topology.
problem Improving lightweight GNNs for robust performance on large-scale real-world graphs.
method Introduces Graph Contrastive Representation Distillation (G-CRD) using contrastive learning.
result G-CRD consistently boosts GNN performance and robustness, outperforming existing methods.
A new method for training GNNs without a teacher model.
problem Training over-parameterized GNN models is difficult and inefficient.
method GNN Self-Distillation (GNN-SD) with NDR and ADR.
result Improves GNN performance with less training cost and better generalization.
A new KD method distills dataset-based knowledge using MHA.
problem Distilling knowledge from large teacher networks to small student networks.
method Graph-based knowledge distillation by multi-head attention network.
result The method improves SN performance by 7.05% on CIFAR100.
MEDAL converts manifold embeddings into models for rigorous validation.
problem Challenges in validating manifold embeddings without held-out validation.
method Develops MEDAL framework that distills embeddings into autoencoder models.
result Enables rigorous validation of manifold embeddings and hyperparameters.
Survey of knowledge distillation for model compression.
problem Deploying large deep models on resource-limited devices.
method Knowledge distillation from large teacher models to small student models.
result Effective model compression and acceleration.
Self-knowledge distillation improves NLP performance.
problem Efficient knowledge representation in NLP models.
method A new knowledge distillation method using soft target probabilities from the training model itself.
result Improves performance on language model and neural machine translation tasks.
A new GNN model predicts stock trends by learning historical and future correlations.
problem Limited improvement in stock trend prediction models due to ignoring future patterns.
method DishFT-GNN framework that trains a teacher and student model to capture historical and future data correlations.
result State-of-the-art performance on real-world datasets.
Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or embedded sensor nodes. There have been efforts to compress these networks, and a popular method is knowledge distillation, where a large (teac…
Recent variants improve knowledge distillation performance.
problem Improving the performance of knowledge distillation.
method Introducing additional components or changing the learning process.
result These variants have shown promising results.
Proposes a method to compress and sparsify neural networks using KD and VI.
problem Porting deep neural networks to embedded platforms with minimal accuracy loss.
method Combines knowledge distillation and variational inference to create a sparse student network.
result Significant memory footprint reduction and improved sparsity without accuracy loss.
Bayesian neural networks improve knowledge sharing across networks.
problem Improving knowledge sharing between neural networks.
method Application of Bayesian interpretations to neural networks for feature sharing.
result Enhanced feature sharing across networks.
This study improves knowledge distillation for RNN-T models with noisy labels.
problem Challenges in distilling knowledge from RNN-T models with variable quality teachers.
method Full-sum distillation and sequence-level knowledge distillation.
result Full-sum distillation outperforms other methods for RNN-T models, especially for bad teachers.
Improved dataset distillation for images and texts boosts model accuracy.
problem Reducing dataset size for faster and more energy-efficient model training.
method Simultaneous distillation of images and soft labels, extending to text datasets.
result 2-4% increase in accuracy for image classification tasks, 20% reduction in distilled samples.
Labels distilled from images improve model training efficiency and flexibility.
problem Creating synthetic labels for a small set of real images to train models effectively.
method Introduce a more robust and flexible meta-learning algorithm for distillation and an effective first-order strategy based on convex optimization layers.
result Label distillation leads to improved results and greater flexibility in neural architectures.
DLM-One speeds up language generation by 500x with continuous models.
problem Efficiently generating text sequences in natural language processing.
method Score-distillation of continuous diffusion language models.
result Achieves up to 500x speedup in inference time with competitive performance.
New method distills discrete diffusion models, maintaining quality and diversity.
problem Difficult to distill discrete diffusion models.
method Discrete Moment Matching Distillation (D-MMD)
result Maintains high quality and diversity in distilled models.
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.
Real-time policy distillation speeds up and improves reinforcement learning.
problem Slow and inefficient policy distillation in reinforcement learning.
method Simultaneous training and distillation of a teacher and student model.
result Significantly reduced distillation time and improved small model performance.
Distillation affects some classes more than others, impacting fairness and bias.
problem Distillation affects some classes more than others, impacting fairness and bias.
method Examined class-wise accuracy and fairness metrics (DPD, EOD) on models trained with different datasets.
result Increasing the distillation temperature improves the distilled student model's fairness and individual fairness.
This paper improves robustness in small neural networks through distillation.
problem Vulnerability of small neural networks to adversarial attacks.
method Adversarially Robust Distillation (ARD) to transfer robustness from teacher to student networks.
result ARD produces small models with superior robust accuracy compared to adversarially trained networks.
Study on ensemble, distillation, and self-distillation in deep learning models.
problem Improving test accuracy in deep learning models using ensemble and distillation methods.
method Formal study of ensemble and distillation, considering multi-view data structure.
result Proven that ensemble and distillation can improve test accuracy in deep learning models, and the superior performance can be distilled into a single model.
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.
Repeated self-distillation improves model performance significantly.
problem How much gain is possible by applying multiple steps of self-distillation?
method Investigated linear regression tasks, applied multiple steps of self-distillation, analyzed excess risk reduction.
result Multi-step self-distillation reduces excess risk by a factor as large as d, where d is the input dimension. OKDDip uses diverse peers to improve online knowledge distillation.
problem Early saturation in group-based distillation.
method Two-level distillation with multiple auxiliary peers and a group leader, using attention-based aggregation weights.
result OKDDip consistently gives better performance than state-of-the-art approaches.
RID framework quantifies and regularizes task-relevant knowledge in distillation.
problem Distilling irrelevant information can hinder student model performance.
method Partial Information Decomposition to quantify and regularize task-relevant knowledge.
result RID framework leads to more resilient distillation under nuisance teachers.
Distiller simplifies DNN compression research with a Python package.
problem Efficiently compressing deep neural networks.
method Open-source Python package with DNN compression algorithms.
result Facilitates new research and learning tasks in DNN compression.
FasterVoiceGrad speeds up VC by 6-7x with novel distillation.
problem Slow iterative sampling in diffusion-based VC models.
method Adversarial diffusion conversion distillation (ADCD) to create a faster one-step model.
result 6.6-6.9 and 1.8x faster on GPU and CPU, respectively.
This paper improves speech recognition by distilling knowledge from acoustic models.
problem Improving speech recognition accuracy using ensemble models.
method Proposes multi-teacher distillation strategies for joint CTC-attention end-to-end ASR systems, integrating error rate metric for optimization.
result Reports state-of-the-art error rates on various datasets and languages.
A framework preserves uncertainty in ensemble distillation.
problem Preserving uncertainty decomposition in ensemble distillation.
method General framework for distilling both regression and classification ensembles, preserving natural uncertainty decomposition.
result Framework maintains decomposition of predictive uncertainty.
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.
For assistive robots and virtual agents to achieve ubiquity, machines will need to anticipate the needs of their human counterparts. The field of Learning from Demonstration (LfD) has sought to enable machines to infer predictive models of human behavior for autonomous robot control. However, humans exhibit heterogenei…
CAKD framework optimizes knowledge transfer by focusing on influential components of distillation.
problem Balancing and optimizing knowledge transfer in distillation models.
method Decouple KL divergence into BCD, SCD, and WCD; prioritize influential components.
result CAKD framework consistently outperforms baseline across diverse models and datasets.
Consistency distillation reduces memorization in diffusion models without harming sample quality.
problem Understanding how distillation affects memorization in diffusion models.
method Analysis of consistency distillation in diffusion models using a random feature neural network model.
result Consistency distillation reduces memorization in diffusion models without harming sample quality.
Self-distillation improves model performance but can lead to underfitting.
problem Understanding why self-distillation improves model performance and its limitations.
method Theoretical analysis of self-distillation in Hilbert space with ℓ2 regularization. result Self-distillation modifies regularization by limiting the number of basis functions, potentially leading to underfitting.
A new method distills datasets more efficiently and effectively.
problem Achieving competitive performance on test data with a small synthetic dataset.
method Tackles dataset distillation as a bilevel optimization problem, introduces RaT-BPTT to stabilize gradients and speed up optimization.
result Establishes new state-of-the-art performance across various benchmarks.
The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents, leading to stronger performance faster, on harder domains [26, 32, 5, 8]. Despite the…
Improved generalization with iterative self-distillation using weighted ground-truth targets.
problem Improving generalization accuracy in neural networks.
method Iterative kernel regression with weighted ground-truth targets and ℓ2 regularization. result Closed-form solution for optimal weighting parameter and efficient estimation.
The paper explains knowledge distillation by analyzing visual concepts in DNNs.
problem Understanding how knowledge distillation affects the learning of visual concepts in deep neural networks.
method The paper proposes three hypotheses and designs mathematical metrics to evaluate feature representations of DNNs.
result The hypotheses were verified through experiments on various DNNs.
This work proposes splitting deep neural networks into smaller sub-networks for faster and more efficient distillation.
problem Challenges in training deep neural networks, including local optima, gradient issues, and computational demands.
method Proposes a non-end-to-end distillation approach by splitting networks into smaller, independent sub-networks (neighbourhoods).
result Independent training of smaller sub-networks can speed up distillation and improve efficiency in various applications.
SiD distills pretrained diffusion models into a fast one-step generator.
problem Efficiently distilling pretrained diffusion models into a fast generator.
method Reformulates forward diffusion processes as semi-implicit distributions and uses three score-related identities to create a loss mechanism.
result Achieves high FID performance and significantly reduces generation time.
Compressed Federated Distillation reduces communication in federated learning.
problem Communication constraints in Federated Learning.
method Compressed Federated Distillation (CFD) leverages soft labels and quantization techniques.
result Reduces communication by more than 4 orders of magnitude compared to Federated Averaging.
Extracting a curriculum from a teacher network improves distillation efficiency.
problem Efficiently training a small network using a large teacher network's output.
method Random projection of teacher network's hidden representations to progressively train the student network.
result Extracted curriculum significantly outperforms one-shot distillation and achieves similar performance to progressive distillation.