Related papers: Bayes Conditional Distribution Estimation for Know…

Recently, it was shown that the role of the teacher in knowledge distillation (KD) is to provide the student with an estimate of the true Bayes conditional probability density (BCPD). Notably, the new findings propose that the student's…

The concepts of conditional mutual information (CMI) and normalized conditional mutual information (NCMI) are introduced to measure the concentration and separation performance of a classification deep neural network (DNN) in the output…

In this paper, a novel confidence conditioned knowledge distillation (CCKD) scheme for transferring the knowledge from a teacher model to a student model is proposed. Existing state-of-the-art methods employ fixed loss functions for this…

Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear,…

Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset.…

The rapid increase in multimodal data availability has sparked significant interest in cross-modal knowledge distillation (KD) techniques, where richer "teacher" modalities transfer information to weaker "student" modalities during model…

Meta-learning optimizes an inductive bias---typically in the form of the hyperparameters of a base-learning algorithm---by observing data from a finite number of related tasks. This paper presents an information-theoretic bound on the…

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…

This paper explores the tasks of leveraging auxiliary modalities which are only available at training to enhance multimodal representation learning through cross-modal Knowledge Distillation (KD). The widely adopted mutual information…

Conditional Mutual Information (CMI) is a measure of conditional dependence between random variables X and Y, given another random variable Z. It can be used to quantify conditional dependence among variables in many data-driven inference…

Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in…

Although large language models (LLMs) have demonstrated remarkable capabilities in recent years, the potential of information theory (IT) to enhance LLM development remains underexplored. This paper introduces the information theoretic…

A deep neural network (DNN) is said to be undistillable if, when used as a black-box input-output teacher, it cannot be distilled through knowledge distillation (KD). In this case, the distilled student (referred to as the knockoff student)…

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature…

A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model. Surprisingly, this two-step knowledge distillation process often leads to…

Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely…

The widespread deployment of Large Language Models (LLMs) is hindered by the high computational demands, making knowledge distillation (KD) crucial for developing compact smaller ones. However, the conventional KD methods endure the…

Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is challenging, as some…

Conventional knowledge distillation (KD) methods require access to the internal information of teachers, e.g., logits. However, such information may not always be accessible for large pre-trained language models (PLMs). In this work, we…