Compressing deep networks is essential to expand their range of applications to constrained settings. The need for compression however often arises long after the model was trained, when the original data might no longer be available. On the other hand, unlabeled data, not necessarily related to the target task, is usually plentiful, especially in image classification tasks. In this work, we propose a scheme to leverage such samples to distill the knowledge learned by a large teacher network to a smaller student. The proposed technique relies on (i) preferentially sampling datapoints that appear related, and (ii) taking better advantage of the learning signal. We show that the former speeds up the student's convergence, while the latter boosts its performance, achieving performances closed to what can be expected with the original data.
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…
Distillation with unlabeled examples is a popular and powerful method for training deep neural networks in settings where the amount of labeled data is limited: A large ''teacher'' neural network is trained on the labeled data available, and then it is used to generate labels on an unlabeled dataset (typically much larger in size). These labels are then utilized to train the smaller ''student'' model which will actually be deployed. Naturally, the success of the approach depends on the quality of the teacher's labels, since the student could be confused if trained on inaccurate data. This pape…
Australian Artificial Intelligence Institute (AAII), University of Technology Sydney（悉尼科技大学澳大利亚人工智能研究所）
Minimizing prediction uncertainty on unlabeled data is a key factor to achieve good performance in semi-supervised learning (SSL). The prediction uncertainty is typically expressed as the \emph{entropy} computed by the transformed probabilities in output space. Most existing works distill low-entropy prediction by either accepting the determining class (with the largest probability) as the true label or suppressing subtle predictions (with the smaller probabilities). Unarguably, these distillation strategies are usually heuristic and less informative for model training. From this discernment, …
We present an algorithm based on multi-layer transformers for identifying Adverse Drug Reactions (ADR) in social media data. Our model relies on the properties of the problem and the characteristics of contextual word embeddings to extract two views from documents. Then a classifier is trained on each view to label a set of unlabeled documents to be used as an initializer for a new classifier in the other view. Finally, the initialized classifier in each view is further trained using the initial training examples. We evaluated our model in the largest publicly available ADR dataset. The experi…
Knowledge distillation is a widely used technique for model compression. We posit that the teacher model used in a distillation setup, captures relationships between classes, that extend beyond the original dataset. We empirically show that a teacher model can transfer this knowledge to a student model even on an {\it out-of-distribution} dataset. Using this approach, we show promising results on MNIST, CIFAR-10, and Caltech-256 datasets using unlabeled image data from different sources. Our results are encouraging and help shed further light from the perspective of understanding knowledge dis…
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…
Knowledge distillation is an effective approach for training compact recognizers required in autonomous driving. Recent studies on image classification have shown that matching student and teacher on a wide range of data points is critical for improving performance in distillation. This concept (called function matching) is suitable for driving scene recognition, where generally an almost infinite amount of unlabeled data are available. In this study, we experimentally investigate the impact of using such a large amount of unlabeled data for distillation on the performance of student models in…
Toward Robust Semi-supervised Regression via Dual-stream Knowledge Distillation
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences（重庆绿色智能技术研究所，中国科学院）；Chongqing School, University of Chinese Academy of Sciences（中国科学院大学重庆学院）；Singapore Management University（新加坡管理大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
Relevance has significant impact on user experience and business profit for e-commerce search platform. In this work, we propose a data-driven framework for search relevance prediction, by distilling knowledge from BERT and related multi-layer Transformer teacher models into simple feed-forward networks with large amount of unlabeled data. The distillation process produces a student model that recovers more than 97\% test accuracy of teacher models on new queries, at a serving cost that's several magnitude lower (latency 150x lower than BERT-Base and 15x lower than the most efficient BERT vari…
Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large stream of unlabeled data easily obtainable in the wild. In particular, we design a novel class-incremental learning scheme with (a) a new distillation loss, termed global distillation, (b) a learning strategy to avoid overfitting to the most recent task, and (c) a confidence-based sampling method to effectively leverage unlabeled external data. Our experimental …
Recent advances in pre-training huge models on large amounts of text through self supervision have obtained state-of-the-art results in various natural language processing tasks. However, these huge and expensive models are difficult to use in practise for downstream tasks. Some recent efforts use knowledge distillation to compress these models. However, we see a gap between the performance of the smaller student models as compared to that of the large teacher. In this work, we leverage large amounts of in-domain unlabeled transfer data in addition to a limited amount of labeled training insta…
The growing size of neural language models has led to increased attention in model compression. The two predominant approaches are pruning, which gradually removes weights from a pre-trained model, and distillation, which trains a smaller compact model to match a larger one. Pruning methods can significantly reduce the model size but hardly achieve large speedups as distillation. However, distillation methods require large amounts of unlabeled data and are expensive to train. In this work, we propose a task-specific structured pruning method CoFi (Coarse- and Fine-grained Pruning), which deliv…
MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation
Shanghai Jiao Tong University（上海交通大学）；GAIR；Alibaba Group（阿里巴巴集团）；University of Science and Technology of China（中国科学技术大学）；Shanghai Innovation Institute（上海创新研究院）
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
Tianjin University（天津大学）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Haihe Laboratory of Information Technology Application Innovation（海河信息技术应用创新实验室）
Ensemble Distribution Distillation for Self-Supervised Human Activity Recognition
organization= The University of New South Wales , city= Sydney , country= Australia；organization= The University of New South Wales \& CSIRO , city= Sydney , country= Australia
This paper addresses the problem of decentralized learning to achieve a high-performance global model by asking a group of clients to share local models pre-trained with their own data resources. We are particularly interested in a specific case where both the client model architectures and data distributions are diverse, which makes it nontrivial to adopt conventional approaches such as Federated Learning and network co-distillation. To this end, we propose a new decentralized learning method called Decentralized Learning via Adaptive Distillation (DLAD). Given a collection of client models a…
University of Edinburgh（爱丁堡大学）；University of Amsterdam（阿姆斯特丹大学）
Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts…
Bar Ilan University（巴伊兰大学）；RIKEN（理化学研究所）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Tokyo（东京大学）
We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large collection. Information Retrieval (IR) solutions treat the document set as a query, and look for similar documents in the collection. We propose to extend the IR approach by treating the problem as an instance of positive-unlabeled (PU) learning -- i.e., learning binary classifiers from only positive and unlabeled data, where the positive data corresponds to the query documents, and the unlabeled data is the results retu…
Can Distillation Mitigate Backdoor Attacks in Pre-trained Encoders?
State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；Shenzhen Research Institute of Nanjing University（南京大学深圳研究院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Decentralized learning with private data is a central problem in machine learning. We propose a novel distillation-based decentralized learning technique that allows multiple agents with private non-iid data to learn from each other, without having to share their data, weights or weight updates. Our approach is communication efficient, utilizes an unlabeled public dataset and uses multiple auxiliary heads for each client, greatly improving training efficiency in the case of heterogeneous data. This approach allows individual models to preserve and enhance performance on their private tasks whi…
Shanghai Qi Zhi Institute（上海期智研究院）；UT Austin（德克萨斯大学奥斯汀分校）；South China University of Technology（华南理工大学）；MIT（麻省理工学院）；Tsinghua University（清华大学）
The popularity of multimodal sensors and the accessibility of the Internet have brought us a massive amount of unlabeled multimodal data. Since existing datasets and well-trained models are primarily unimodal, the modality gap between a unimodal network and unlabeled multimodal data poses an interesting problem: how to transfer a pre-trained unimodal network to perform the same task on unlabeled multimodal data? In this work, we propose multimodal knowledge expansion (MKE), a knowledge distillation-based framework to effectively utilize multimodal data without requiring labels. Opposite to tra…
University at Buffalo（布法罗大学）；United Imaging Intelligence（联影智能）
Federated Learning (FL) is a machine learning paradigm where local nodes collaboratively train a central model while the training data remains decentralized. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they suffer from communication bottlenecks. More importantly, they risk privacy leakage. In this work, we develop a privacy preserving and communication efficient method in a FL framework with one-shot offline knowledge distillation using unlabeled, cross-domain public data. We propose a quantized a…
Recent breakthroughs in the field of semi-supervised learning have achieved results that match state-of-the-art traditional supervised learning methods. Most successful semi-supervised learning approaches in computer vision focus on leveraging huge amount of unlabeled data, learning the general representation via data augmentation and transformation, creating pseudo labels, implementing different loss functions, and eventually transferring this knowledge to more task-specific smaller models. In this paper, we aim to conduct our analyses on three different aspects of SimCLR, the current state-o…
Harvard University（哈佛大学）；Mobileye（Mobileye公司）；Hebrew University（希伯来大学）；University of California San Diego（加利福尼亚大学圣迭戈分校）
Large neural networks trained in the overparameterized regime are able to fit noise to zero train error. Recent work \citep{nakkiran2020distributional} has empirically observed that such networks behave as "conditional samplers" from the noisy distribution. That is, they replicate the noise in the train data to unseen examples. We give a theoretical framework for studying this conditional sampling behavior in the context of learning theory. We relate the notion of such samplers to knowledge distillation, where a student network imitates the outputs of a teacher on unlabeled data. We show that …
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）
Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally different communication properties, emerged. FD methods leverage ensemble distillation techniques and exchange model outputs, presented as soft labels on an unlabeled public data set, between the central server and the participating clients. While for conventional Federated Learning algorithms, like Federated Averaging (FA), communication scales with the size of th…
Knowledge distillation is an effective machine learning technique to transfer knowledge from a teacher model to a smaller student model, especially with unlabeled data. In this paper, we focus on knowledge distillation for the RNN-T model, which is widely used in state-of-the-art (SoTA) automatic speech recognition (ASR). Specifically, we compared using soft and hard target distillation to train large-scaleRNN-T models on the LibriSpeech/LibriLight public dataset (60k hours) and our in-house data (600k hours). We found that hard tar-gets are more effective when the teacher and student have dif…
National University of Singapore（新加坡国立大学）；NEC Corporation（NEC公司）
A membership inference attack (MIA) poses privacy risks for the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The state-of-the-art defense against MIAs, distillation for membership privacy (DMP), requires not only private data for protection but a large amount of unlabeled public data. However, in certain privacy-sensitive domains, such as medicine and finance, the availability of public data is not guaranteed. Moreover, a trivial method for generating public data by using generative adversarial networks sig…
Federated Distillation (FD) is a popular novel algorithmic paradigm for Federated Learning, which achieves training performance competitive to prior parameter averaging based methods, while additionally allowing the clients to train different model architectures, by distilling the client predictions on an unlabeled auxiliary set of data into a student model. In this work we propose FedAUX, an extension to FD, which, under the same set of assumptions, drastically improves performance by deriving maximum utility from the unlabeled auxiliary data. FedAUX modifies the FD training procedure in two …
Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. However, directly averaging model parameters is only possible if all models have the same structure and size, which could be a restrictive constraint in many scenarios. In this work we investigate more powerful and more flexible aggregation schemes for FL. Specifical…
University at Buffalo（布法罗大学）；United Imaging Intelligence（联影智能）
Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facilities, leading to the need for FL. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they also require numerous rounds of synchronized communication and, more importantly, suffer from a privacy leakage risk. …
We propose a new semi-supervised learning method on face-related tasks based on Multi-Task Learning (MTL) and data distillation. The proposed method exploits multiple datasets with different labels for different-but-related tasks such as simultaneous age, gender, race, facial expression estimation. Specifically, when there are only a few well-labeled data for a specific task among the multiple related ones, we exploit the labels of other related tasks in different domains. Our approach is composed of (1) a new MTL method which can deal with weakly labeled datasets and perform several tasks sim…
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Peking University（北京大学）；The University of Sydney（悉尼大学）
Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providing compression and acceleration service of deep learning models on the cloud is therefore of significance and is attractive for end users. However, existing network compression and acceleration approaches usually fine-tuning the svelte model by requesting the entire original training data (\eg ImageNet), which could be more cumbersome than the network itself and cannot be easily uploaded to the cloud. In this paper, w…
Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that transfer well to future tasks. However, we observe that standard distillation of task-specific teachers actually *reduces* the transferability of student representations to downstream tasks. We show that a multi-head, multi-task distillation method using an unlabeled proxy dataset and a generalist teacher is sufficient to consolidate representations from task-spe…
Zhejiang University（浙江大学）；Stevens Institute of Technology（史蒂文斯理工学院）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Knowledge distillation has demonstrated encouraging performances in deep model compression. Most existing approaches, however, require massive labeled data to accomplish the knowledge transfer, making the model compression a cumbersome and costly process. In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category. To this end, we introduce a principled dual-stage distillation scheme tailored for few-shot data. In the first step, we graft the student blocks one by one onto the…
Medical University of Vienna（维也纳医科大学）；Intel（英特尔公司）；Lobachevsky State University（罗巴切夫斯基国立大学）
The segmentation of brain tumors in multimodal MRIs is one of the most challenging tasks in medical image analysis. The recent state of the art algorithms solving this task is based on machine learning approaches and deep learning in particular. The amount of data used for training such models and its variability is a keystone for building an algorithm with high representation power. In this paper, we study the relationship between the performance of the model and the amount of data employed during the training process. On the example of brain tumor segmentation challenge, we compare the model…
IST Austria (Institute of Science and Technology Austria)（奥地利科学技术研究所）
In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data is available for all tasks, we consider a new setting, in which for some tasks, potentially most of them, only unlabeled training data is provided. Consequently, to solve all tasks, information must be transferred between tasks with labels and tasks without labels. Focusing on an instance-based transfer method we analyze two variants of this setting: when the set of labeled tasks is fixed, and when it can be active…
Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint of these large LMs makes them difficult to deploy in many scenarios (e.g. on mobile phones). Recent research points to knowledge distillation as a potential solution, showing that when training data for a given task is abundant, it is possible to distill a large (teacher) LM into a small task-specific (student) network with minimal loss of performance. Howeve…
Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院金在哲人工智能研究生院）
As segmentation labels are scarce, extensive researches have been conducted to train segmentation networks with domain adaptation, semi-supervised or self-supervised learning techniques to utilize abundant unlabeled dataset. However, these approaches appear different from each other, so it is not clear how these approaches can be combined for better performance. Inspired by recent multi-domain image translation approaches, here we propose a novel segmentation framework using adaptive instance normalization (AdaIN), so that a single generator is trained to perform both domain adaptation and sem…
Applied Artificial Intelligence Institute (AI), Deakin University（迪肯大学应用人工智能研究所）
Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher (parameters are accessible) to train a good student. However, these resources are not always available in real-world applications. The distillation process often happens at an external party side where we do not have access to much data, and the teacher does not disclose its parameters due to security and privacy concerns. To overcome these challenges, we propose a bl…
Robust Decentralized Federated Distillation via Multi-Modality Knowledge Collaboration
Faculty of Applied Sciences, Macao Polytechnic University（澳门理工大学应用科学学院）；School of Engineering and Technology, Central Queensland University（中央昆士兰大学工程与技术学院）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）
Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation
California State University, Fullerton, CA, USA（加州州立大学弗里蒙特分校）；Microsoft, Redmond, WA, USA（微软公司）；Beijing Normal-Hong Kong Baptist University, China（北京师范大学-香港 Baptist大学）
