Related papers: Faithful Knowledge Distillation
Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a…
We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully…
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…
Adversarial training attains strong empirical robustness to specific adversarial attacks by training on concrete adversarial perturbations, but it produces neural networks that are not amenable to strong robustness certificates through…
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student. Existing methods focus on excavating the knowledge hints and transferring the whole knowledge to the student. However,…
Knowledge distillation (KD) has been extensively employed to transfer the knowledge from a large teacher model to the smaller students, where the parameters of the teacher are fixed (or partially) during training. Recent studies show that…
Knowledge distillation (KD) is a popular method to train efficient networks ("student") with the help of high-capacity networks ("teacher"). Traditional methods use the teacher's soft logits as extra supervision to train the student…
Knowledge Distillation (KD) is a common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions. In its regular manifestations, KD requires access to the…
This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). Contemporary findings addressing this thesis statement take dichotomous standpoints: Muller et al. (2019) and Shen et al. (2021b).…
Knowledge distillation (KD) provides an effective way to improve the performance of a student network under the guidance of pre-trained teachers. However, this approach usually brings in a large capacity gap between teacher and student…
Knowledge distillation (KD) is a popular method of transferring knowledge from a large "teacher" model to a small "student" model. Previous work has explored various layer-selection strategies (e.g., forward matching and in-order random…
This work studies knowledge distillation (KD) for large language models (LLMs) through preference optimization. We propose a reward-guided imitation learning framework for sequential KD, formulating a min-max optimization problem between…
Knowledge Distillation (KD) could transfer the ``dark knowledge" of a well-performed yet large neural network to a weaker but lightweight one. From the view of output logits and softened probabilities, this paper goes deeper into the dark…
Knowledge distillation (KD) is essentially a process of transferring a teacher model's behavior, e.g., network response, to a student model. The network response serves as additional supervision to formulate the machine domain, which uses…
Knowledge distillation (KD) is a widely used technique to transfer knowledge from a large teacher network to a smaller student model. Traditional KD uses a fixed balancing factor alpha as a hyperparameter to combine the hard-label…
Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel…
Originally proposed as a method for knowledge transfer from one model to another, some recent studies have suggested that knowledge distillation (KD) is in fact a form of regularization. Perhaps the strongest argument of all for this new…
Knowledge distillation (KD) is one of the most potent ways for model compression. The key idea is to transfer the knowledge from a deep teacher model (T) to a shallower student (S). However, existing methods suffer from performance…
Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented -- enabling smaller student models to…
Deep neural networks have achieved remarkable performance for artificial intelligence tasks. The success behind intelligent systems often relies on large-scale models with high computational complexity and storage costs. The…