Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is used to train a more compact student model with better inference efficiency. Through distillation, one hopes to benefit from student's compactness, without sacrificing too much on model quality. Despite the large success of knowledge distillation, better understanding of how it benefits student model's training dynamics remains under-explored. In this paper, we categorize teacher's knowledge into three hierarchical levels and study its effects on knowledge distillation: (1) knowledge of the `universe', where KD brings a regularization effect through label smoothing; (2) domain knowledge, where teacher injects class relationships prior to student's logit layer geometry; and (3) instance specific knowledge, where teacher rescales student model's per-instance gradients based on its measurement on the event difficulty. Using systematic analyses and extensive empirical studies on both synthetic and real-world datasets, we confirm that the aforementioned three factors play a major role in knowledge distillation. Furthermore, based on our findings, we diagnose some of the failure cases of applying KD from recent studies.
Adversarial training is the most promising method for learning robust models against adversarial examples. A recent study has shown that knowledge distillation between the same architectures is effective in improving the performance of adversarial training. Exploiting knowledge distillation is a new approach to improve adversarial training and has attracted much attention. However, its performance is still insufficient. Therefore, we propose Adversarial Robust Distillation with Internal Representation~(ARDIR) to utilize knowledge distillation even more effectively. In addition to the output of…
Sun Yat-Sen University（中山大学）；University of Alberta（阿尔伯塔大学）
Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student. However, just like massive classification, large scale knowledge distillation also imposes heavy computational costs on training models of deep neural networks, as the softmax activations at the last layer involve computing probabilities over numerous classes. In this work, we apply the idea of importance sampling which is often used in Neural Machine Translation on large scale knowledge distillation. We present a method called dynamic importance sampling, where ranked cla…
This paper aims to provide a selective survey about knowledge distillation(KD) framework for researchers and practitioners to take advantage of it for developing new optimized models in the deep neural network field. To this end, we give a brief overview of knowledge distillation and some related works including learning using privileged information(LUPI) and generalized distillation(GD). Even though knowledge distillation based on the teacher-student architecture was initially devised as a model compression technique, it has found versatile applications over various frameworks. In this paper,…
King Fahd University of Petroleum and Minerals（法赫德国王石油与矿产大学）
Deep learning based models are relatively large, and it is hard to deploy such models on resource-limited devices such as mobile phones and embedded devices. One possible solution is knowledge distillation whereby a smaller model (student model) is trained by utilizing the information from a larger model (teacher model). In this paper, we present a survey of knowledge distillation techniques applied to deep learning models. To compare the performances of different techniques, we propose a new metric called distillation metric. Distillation metric compares different knowledge distillation algor…
Stanford University（斯坦福大学）；Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
We study the use of knowledge distillation to compress the U-net architecture. We show that, while standard distillation is not sufficient to reliably train a compressed U-net, introducing other regularization methods, such as batch normalization and class re-weighting, in knowledge distillation significantly improves the training process. This allows us to compress a U-net by over 1000x, i.e., to 0.1% of its original number of parameters, at a negligible decrease in performance.
University of Science and Technology of China（中国科学技术大学）；Sun Yat-sen University（中山大学）
Knowledge distillation is to transfer the knowledge from the data learned by the teacher network to the student network, so that the student has the advantage of less parameters and less calculations, and the accuracy is close to the teacher. In this paper, we propose a new distillation method, which contains two transfer distillation strategies and a loss decay strategy. The first transfer strategy is based on channel-wise attention, called Channel Distillation (CD). CD transfers the channel information from the teacher to the student. The second is Guided Knowledge Distillation (GKD). Unlike…
To put a state-of-the-art neural network to practical use, it is necessary to design a model that has a good trade-off between the resource consumption and performance on the test set. Many researchers and engineers are developing methods that enable training or designing a model more efficiently. Developing an efficient model includes several strategies such as network architecture search, pruning, quantization, knowledge distillation, utilizing cheap convolution, regularization, and also includes any craft that leads to a better performance-resource trade-off. When combining these technologi…
Stanford University（斯坦福大学）；Microsoft Research, New England（微软研究院新英格兰分院）
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 higher accuracy than training the student directly on labeled data. To explain and enhance this phenomenon, we cast knowledge distillation as a semiparametric inference problem with the optimal student model as the target, the unknown Bayes class probabilities as nuisance, and the teacher probabilities as a plug-in nuisance estimate. By adapting modern semipa…
In recent years, knowledge distillation has become a cornerstone of efficiently deployed machine learning, with labs and industries using knowledge distillation to train models that are inexpensive and resource-optimized. Trojan attacks have contemporaneously gained significant prominence, revealing fundamental vulnerabilities in deep learning models. Given the widespread use of knowledge distillation, in this work we seek to exploit the unlabelled data knowledge distillation process to embed Trojans in a student model without introducing conspicuous behavior in the teacher. We ultimately devi…
Shanghai Jiao Tong University（上海交通大学）；Huazhong University of Science & Technology（华中科技大学）；Xi’an Jiaotong University（西安交通大学）
This paper presents a method to interpret the success of knowledge distillation by quantifying and analyzing task-relevant and task-irrelevant visual concepts that are encoded in intermediate layers of a deep neural network (DNN). More specifically, three hypotheses are proposed as follows. 1. Knowledge distillation makes the DNN learn more visual concepts than learning from raw data. 2. Knowledge distillation ensures that the DNN is prone to learning various visual concepts simultaneously. Whereas, in the scenario of learning from raw data, the DNN learns visual concepts sequentially. 3. Know…
Ludwig Maximilian Muenchen Unitversitaet（慕尼黑路德维希-马克西米利安大学）
Although deep neural networks have shown well-performance in various tasks, the poor interpretability of the models is always criticized. In the paper, we propose a new interpretable neural network method, by embedding neurons into the semantic space to extract their intrinsic global semantics. In contrast to previous methods that probe latent knowledge inside the model, the proposed semantic vector externalizes the latent knowledge to static knowledge, which is easy to exploit. Specifically, we assume that neurons with similar activation are of similar semantic information. Afterwards, semant…
Knowledge distillation (KD) has become a well established paradigm for compressing deep neural networks. The typical way of conducting knowledge distillation is to train the student network under the supervision of the teacher network to harness the knowledge at one or multiple spots (i.e., layers) in the teacher network. The distillation spots, once specified, will not change for all the training samples, throughout the whole distillation process. In this work, we argue that distillation spots should be adaptive to training samples and distillation epochs. We thus propose a new distillation s…
Compared to traditional learning from scratch, knowledge distillation sometimes makes the DNN achieve superior performance. This paper provides a new perspective to explain the success of knowledge distillation, i.e., quantifying knowledge points encoded in intermediate layers of a DNN for classification, based on the information theory. To this end, we consider the signal processing in a DNN as the layer-wise information discarding. A knowledge point is referred to as an input unit, whose information is much less discarded than other input units. Thus, we propose three hypotheses for knowledg…
Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some recent variants attempt to exploit diverse knowledge sources from multiple teachers. However, existing studies mainly integrate knowledge from diverse sources by averaging over multiple teacher predictions or combining them using other various label-free strategies, which may mislead student in the presence of low-quality teacher predictions. To tackle this problem, we propose Confidence-Aware Multi-teacher Knowledge…
Zhejiang University（浙江大学）；ZJU-LianlianPay Joint Research Center（浙江大学-连连支付联合研究中心）；Zhejiang University of Technology（浙江工业大学）
Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always available. Recently proposed online variants use the aggregated intermediate predictions of multiple student models as targets to train each student model. Although group-derived targets give a good recipe for teacher-free distillation, group members are homogenized quickly with simple aggregation functions, leading to early saturated solutions. In this wor…
Entity alignment aims at integrating heterogeneous knowledge from different knowledge graphs. Recent studies employ embedding-based methods by first learning the representation of Knowledge Graphs and then performing entity alignment via measuring the similarity between entity embeddings. However, they failed to make good use of the relation semantic information due to the trade-off problem caused by the different objectives of learning knowledge embedding and neighborhood consensus. To address this problem, we propose Relational Knowledge Distillation for Entity Alignment (RKDEA), a Graph Con…
The University of Sydney（悉尼大学）；Birkbeck College, University of London（伦敦大学伯贝克学院）；UBTECH（优必选）
In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. …
Illinois Institute of Technology（伊利诺伊理工学院）；Texas State University（德克萨斯州立大学）；Shandong University（山东大学）
Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although great success has been achieved by prior distillation methods via delicately designing various types of knowledge, they overlook the functional properties of neural networks, which makes the process of applying those techniques to new tasks unreliable and non-trivial. To alleviate such problem, in this paper, we initially leverage Lipschitz continuity to better represent the functional characteristic of neural networks a…
Knowledge distillation (KD) has been widely used for model compression and knowledge transfer. Typically, a big teacher model trained on sufficient data transfers knowledge to a small student model. However, despite the success of KD, little effort has been made to study whether KD leaks the training data of the teacher model. In this paper, we experimentally reveal that KD suffers from the risk of privacy leakage. To alleviate this issue, we propose a novel knowledge distillation method, swing distillation, which can effectively protect the private information of the teacher model from flowin…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Zhejiang University（浙江大学）；China University of Geosciences (Beijing)（中国地质大学（北京））
Graph, such as citation networks, social networks, and transportation networks, are prevalent in the real world. Graph Neural Networks (GNNs) have gained widespread attention for their robust expressiveness and exceptional performance in various graph applications. However, the efficacy of GNNs is heavily reliant on sufficient data labels and complex network models, with the former obtaining hardly and the latter computing costly. To address the labeled data scarcity and high complexity of GNNs, Knowledge Distillation (KD) has been introduced to enhance existing GNNs. This technique involves t…
Samsung Research America（三星美国研究院）；Georgia Institute of Technology（佐治亚理工学院）
Knowledge distillation (KD) is a substantial strategy for transferring learned knowledge from one neural network model to another. A vast number of methods have been developed for this strategy. While most method designs a more efficient way to facilitate knowledge transfer, less attention has been put on comparing the effect of knowledge sources such as features, logits, and gradients. This work provides a new perspective to motivate a set of knowledge distillation strategies by approximating the classical KL-divergence criteria with different knowledge sources, making a systematic comparison…
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of 'mismatched' unlabeled stimulus to perform KD for image classification networks. For illustration, we consider scenarios where this is a complete absence of training data, or mismatched stimulus has to be used for augmenting a small amount of training data. We demonstrate that stimulus complexity is a key factor for distillation's good performance. Our examples include use of various datasets for stimulating MNIST and…
Seoul National University（首尔国立大学）；Hanyang University（汉阳大学）；NAVER Corp（NAVER公司）；Clova AI Research（Clova人工智能研究院）
Many recent works on knowledge distillation have provided ways to transfer the knowledge of a trained network for improving the learning process of a new one, but finding a good technique for knowledge distillation is still an open problem. In this paper, we provide a new perspective based on a decision boundary, which is one of the most important component of a classifier. The generalization performance of a classifier is closely related to the adequacy of its decision boundary, so a good classifier bears a good decision boundary. Therefore, transferring information closely related to the dec…
Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our modular method can be straightforwardly applied with any neural topic model to improve topic quality, which we demonstrate using two models having disparate architectures, obtaining state-of-the-art topic coherence. We show that our adaptable framework not only improves performance in the aggregate over all estimated topics, as is commonly reported, but als…
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high performance can be explained by efficient knowledge representation of deep learning models. While many methods have been proposed to learn more efficient representation, knowledge distillation from pretrained deep networks suggest that we can use more information from the soft target probability to train other neural networks. In this paper, we propose a new k…
It is challenging to perform lifelong language learning (LLL) on a stream of different tasks without any performance degradation comparing to the multi-task counterparts. To address this issue, we present Lifelong Language Knowledge Distillation (L2KD), a simple but efficient method that can be easily applied to existing LLL architectures in order to mitigate the degradation. Specifically, when the LLL model is trained on a new task, we assign a teacher model to first learn the new task, and pass the knowledge to the LLL model via knowledge distillation. Therefore, the LLL model can better ada…
Meta FAIR Labs（Meta FAIR 实验室）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）
We formally study how ensemble of deep learning models can improve test accuracy, and how the superior performance of ensemble can be distilled into a single model using knowledge distillation. We consider the challenging case where the ensemble is simply an average of the outputs of a few independently trained neural networks with the SAME architecture, trained using the SAME algorithm on the SAME data set, and they only differ by the random seeds used in the initialization. We show that ensemble/knowledge distillation in Deep Learning works very differently from traditional learning theory (…
We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets, and consistent training schedules indicate that many of these distillation results are hard to reproduce. This is especially apparent with methods using some form of feature distillation. Further examination reveals a lack of generalizability where these techniques may only succeed for specific architectures and training settings. We observe that appropriate…
Knowledge Distillation is becoming one of the primary trends among neural network compression algorithms to improve the generalization performance of a smaller student model with guidance from a larger teacher model. This momentous rise in applications of knowledge distillation is accompanied by the introduction of numerous algorithms for distilling the knowledge such as soft targets and hint layers. Despite this advancement in different techniques for distilling the knowledge, the aggregation of different paths for distillation has not been studied comprehensively. This is of particular signi…
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 to the cumbersome computation and storage of extra feature transformation, the training overhead of feature-based methods is much higher than that of logit-based distillation. In this work, we revisit the logit-based knowledge distillation, and observe that the existing logit-based distillation methods treat the prediction logits only in the instance level,…
DIT Center, Samsung Electronics（三星电子DIT中心）；ECE & ASRI, Seoul National University（首尔大学电子与计算机工程系及自动化与系统研究所）
We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained teachers, we aim to learn the teacher models that are friendly to students and, consequently, more appropriate for knowledge transfer. In other words, at the time of optimizing a teacher model, the proposed algorithm learns the student branches jointly to obtain student-friendly representations. Since the main goal of our approach lies in training teacher models an…
George Mason University（乔治梅森大学）；University of California, Davis（加州大学戴维斯分校）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
This paper proposes an ensemble learning model that is resistant to adversarial attacks. To build resilience, we introduced a training process where each member learns a radically distinct latent space. Member models are added one at a time to the ensemble. Simultaneously, the loss function is regulated by a reverse knowledge distillation, forcing the new member to learn different features and map to a latent space safely distanced from those of existing members. We assessed the security and performance of the proposed solution on image classification tasks using CIFAR10 and MNIST datasets and…
Traditional knowledge distillation transfers "dark knowledge" of a pre-trained teacher network to a student network, and ignores the knowledge in the training process of the teacher, which we call teacher's experience. However, in realistic educational scenarios, learning experience is often more important than learning results. In this work, we propose a novel knowledge distillation method by integrating the teacher's experience for knowledge transfer, named experience ensemble knowledge distillation (EEKD). We save a moderate number of intermediate models from the training process of the tea…
CLOVA AI Research, NAVER Corp.（NAVER公司CLOVA人工智能研究院）
Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge through pre-defined links. However, manual selection often constructs ineffective links that limit the improvement from the distillation. There has been an attempt to address the problem, but it is still challenging to identify effective links under practical scenarios. In this paper, we introduce an effective and efficient feature distillation method utilizing a…
Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model. Existing efforts guide the distillation by matching their prediction logits, feature embedding, etc., while leaving how to efficiently utilize them in junction less explored. In this paper, we propose Hint-dynamic Knowledge Distillation, dubbed HKD, which excavates the knowledge from the teacher' s hints in a dynamic scheme. The guidance effect from the knowledge hints usually varies in different instances and learning stages, which motivates us to customize a specific hin…
Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning instance-wise outputs between the teacher and student, while neglecting an important knowledge source, i.e., the gradient of the teacher. The gradient characterizes how the teacher responds to changes in inputs, which we assume is beneficial for the student to better approximate the underlying mapping function of the teacher. Therefore, we propose Gradient Know…
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；JD Explore Academy（京东探索研究院）；Peng Cheng Laboratory（鹏城实验室）
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 this mode may cause difficulties in knowledge transfer due to the mismatched model capacities. To alleviate the mismatch problem, teacher-student joint training methods, e.g., online distillation, have been proposed, but it always requires expensive computational cost. In this paper, we present a parameter-efficient and student-friendly knowledge distillation…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are usually learned on the same labeled data, and their predictions have high correlations with groudtruth labels. Thus, they cannot provide sufficient knowledge complementary to task labels for student teaching. Distilling on unseen unlabeled data has the potential to enhance the knowledge transfer from the teachers to the student. In this paper, we propose a uni…
In this paper, we present a thorough evaluation of the efficacy of knowledge distillation and its dependence on student and teacher architectures. Starting with the observation that more accurate teachers often don't make good teachers, we attempt to tease apart the factors that affect knowledge distillation performance. We find crucially that larger models do not often make better teachers. We show that this is a consequence of mismatched capacity, and that small students are unable to mimic large teachers. We find typical ways of circumventing this (such as performing a sequence of knowledge…
Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output activations of individual data examples represented by the teacher. We introduce a novel approach, dubbed relational knowledge distillation (RKD), that transfers mutual relations of data examples instead. For concrete realizations of RKD, we propose distance-wise and angle-wise distillation losses that penalize structural differences in relations. Experiments conduct…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Department of Communication Engineering, Shanghai University（上海大学通信工程学院）
Knowledge distillation provides an effective way to transfer knowledge via teacher-student learning, where most existing distillation approaches apply a fixed pre-trained model as teacher to supervise the learning of student network. This manner usually brings in a big capability gap between teacher and student networks during learning. Recent researches have observed that a small teacher-student capability gap can facilitate knowledge transfer. Inspired by that, we propose an evolutionary knowledge distillation approach to improve the transfer effectiveness of teacher knowledge. Instead of a …
To circumvent the non-parallelizability of recurrent neural network-based equalizers, we propose knowledge distillation to recast the RNN into a parallelizable feedforward structure. The latter shows 38\% latency decrease, while impacting the Q-factor by only 0.5dB.
Deep neural networks (DNNs) have been extremely successful in solving many challenging AI tasks in natural language processing, speech recognition, and computer vision nowadays. However, DNNs are typically computation intensive, memory demanding, and power hungry, which significantly limits their usage on platforms with constrained resources. Therefore, a variety of compression techniques (e.g. quantization, pruning, and knowledge distillation) have been proposed to reduce the size and power consumption of DNNs. Blockwise knowledge distillation is one of the compression techniques that can eff…
