Related papers: Sampling to Distill: Knowledge Transfer from Open-…
Knowledge distillation (KD) is a simple and successful method to transfer knowledge from a teacher to a student model solely based on functional activity. However, current KD has a few shortcomings: it has recently been shown that this…
Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-regressive sequence models suffer from…
Knowledge distillation is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep. These teacher networks are…
Many recent breakthroughs in machine learning have been enabled by the pre-trained foundation models. By scaling up model parameters, training data, and computation resources, foundation models have significantly advanced the…
Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data…
Knowledge distillation (KD) is a technique used to transfer knowledge from an overparameterized teacher network to a less-parameterized student network, thereby minimizing the incurred performance loss. KD methods can be categorized into…
Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged information on similarities/consistency between the class…
Transformers are successfully applied to computer vision due to their powerful modeling capacity with self-attention. However, the excellent performance of transformers heavily depends on enormous training images. Thus, a data-efficient…
Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…
Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn…
Compact models can be effectively trained through Knowledge Distillation (KD), a technique that transfers knowledge from larger, high-performing teacher models. Two key challenges in Knowledge Distillation (KD) are: 1) balancing learning…
We present a systematic study of domain generalization (DG) for tiny neural networks. This problem is critical to on-device machine learning applications but has been overlooked in the literature where research has been merely focused on…
Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the…
Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under…
Knowledge distillation, a widely used model compression technique, works on the basis of transferring knowledge from a cumbersome teacher model to a lightweight student model. The technique involves jointly optimizing the task specific and…
In the history of knowledge distillation, the focus has once shifted over time from logit-based to feature-based approaches. However, this transition has been revisited with the advent of Decoupled Knowledge Distillation (DKD), which…
Recent recommender systems have shown remarkable performance by using an ensemble of heterogeneous models. However, it is exceedingly costly because it requires resources and inference latency proportional to the number of models, which…
Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use…
Spatiotemporal forecasting tasks, such as traffic flow, combustion dynamics, and weather forecasting, often require complex models that suffer from low training efficiency and high memory consumption. This paper proposes a lightweight…
Knowledge distillation (KD) is a widely adopted approach for compressing large neural networks by transferring knowledge from a large teacher model to a smaller student model. In the context of large language models, token level KD,…