Related papers: Knowledge Distillation with Refined Logits
Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distillation. However, due…
Knowledge distillation (KD) is an established paradigm for transferring privileged knowledge from a cumbersome model to a lightweight and efficient one. In recent years, logit-based KD methods are quickly catching up in performance with…
Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto…
Knowledge distillation (KD) aims to distill the knowledge from the teacher (larger) to the student (smaller) model via soft-label for the efficient neural network. In general, the performance of a model is determined by accuracy, which is…
Knowledge distillation (KD) compresses the network capacity by transferring knowledge from a large (teacher) network to a smaller one (student). It has been mainstream that the teacher directly transfers knowledge to the student with its…
Knowledge Distillation (KD), aiming to train a better student model by mimicking the teacher model, plays an important role in model compression. One typical way is to align the output logits. However, we find a common issue named…
Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…
In knowledge distillation (KD), logit distillation (LD) aims to transfer class-level knowledge from a more powerful teacher network to a small student model via accurate teacher-student alignment at the logits level. Since high-confidence…
In the knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based approaches, which aim to distill "dark knowledge" from teachers,…
Continual learning (CL) aims to learn new tasks without erasing previous knowledge. However, current CL methods primarily emphasize improving accuracy while often neglecting training efficiency, which consequently restricts their practical…
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…
Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…
Knowledge Distillation (KD) has emerged as a promising approach for transferring knowledge from a larger, more complex teacher model to a smaller student model. Traditionally, KD involves training the student to mimic the teacher's output…
Knowledge Distillation (KD) uses the teacher's prediction logits as soft labels to guide the student, while self-KD does not need a real teacher to require the soft labels. This work unifies the formulations of the two tasks by decomposing…
This study proposes a method for knowledge distillation (KD) of fine-tuned Large Language Models (LLMs) into smaller, more efficient, and accurate neural networks. We specifically target the challenge of deploying these models on…
Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationship across samples with same class is often neglected. In…
In recent years, large language models (LLMs) have shown exceptional capabilities across various natural language processing (NLP) tasks. However, such impressive performance often comes with the trade-off of an increased parameter size,…
Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student by aligning their predictive distributions. However, conventional KD formulations - typically based on Kullback-Leibler divergence - assume that…
As a promising solution for model compression, knowledge distillation (KD) has been applied in recommender systems (RS) to reduce inference latency. Traditional solutions first train a full teacher model from the training data, and then…
Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning.…