University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）；Microsoft Research（微软研究院）；University of Maryland, College Park（马里兰大学帕克分校）
Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, Hal Daumé, John Langford
Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the reference policy is suboptimal and the goal of learning is to improve upon it. Can learning to search work even when the reference is poor?
We provide a new learning to search algorithm, LOLS, which does well relative to the reference policy, but additionally guarantees low regret compared to deviations from the learned policy: a local-optimality guarantee. Consequently, LOLS can improve upon the reference policy, unlike previous algorithms. This enables us to develop structured contextual bandits, a partial information structured prediction setting with many potential applications.
The Curious AI Company（好奇人工智能公司）；Aalto University（阿尔托大学）
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change only once per epoch, Temporal Ensembling becomes unwieldy when learning large datasets. To overcome this problem, we propose Mean Teacher, a method that averages model weights instead of label predictions. As an additional benefit, Mean Teacher improves test accuracy and enables …
We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student's performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student. Our code w…
University of Oxford（牛津大学）；Oxford University Hospitals Trust（牛津大学医院信托）
Accurate and reliable prediction of hospital admission location is important due to resource-constraints and space availability in a clinical setting, particularly when dealing with patients who come from the emergency department. In this work we propose a student-teacher network via reinforcement learning to deal with this specific problem. A representation of the weights of the student network is treated as the state and is fed as an input to the teacher network. The teacher network's action is to select the most appropriate batch of data to train the student network on from a training set s…
We present a novel framework of knowledge distillation that is capable of learning powerful and efficient student models from ensemble teacher networks. Our approach addresses the inherent model capacity issue between teacher and student and aims to maximize benefit from teacher models during distillation by reducing their capacity gap. Specifically, we employ a neural architecture search technique to augment useful structures and operations, where the searched network is appropriate for knowledge distillation towards student models and free from sacrificing its performance by fixing the netwo…
Peking University（北京大学）；Megvii (Face++) Technology Inc（旷视科技（Face++））；National Engineering Laboratory for Big Data Analysis and Applications（大数据分析与应用技术国家工程实验室）；DiDi AI Labs（滴滴人工智能实验室）
Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher network. Some recent works introduce multi-teacher distillation to provide more supervision to the student network. However, the effectiveness of multi-teacher distillation methods are accompanied by costly computation resources. To tackle with both the efficiency and the effectiveness of knowledge distillation, we introduce the feature aggregation to imitate the m…
In human learning, an effective skill in improving learning outcomes is learning by teaching: a learner deepens his/her understanding of a topic by teaching this topic to others. In this paper, we aim to borrow this teaching-driven learning methodology from humans and leverage it to train more performant machine learning models, by proposing a novel ML framework referred to as learning by teaching (LBT). In the LBT framework, a teacher model improves itself by teaching a student model to learn well. Specifically, the teacher creates a pseudo-labeled dataset and uses it to train a student model…
Google AI（谷歌人工智能）；Google Brain（谷歌大脑）；Multimedia Laboratory, The Chinese University of Hong Kong（香港中文大学多媒体实验室）
Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture. However, the knowledge of a neural network, which is represented by the network's output distribution conditioned on its input, depends not only on its parameters but also on its architecture. Hence, a more generalized approach for KD is to distill the teacher's knowledge into both the parameters and architecture of the student. To achieve this, we present a new Architecture-aware Knowledge Distillation (AKD) approach that f…
National University of Defense Technology（国防科技大学）；Chinese Academy of Sciences（中国科学院）
Knowledge distillation (KD) is an effective training strategy to improve the lightweight student models under the guidance of cumbersome teachers. However, the large architecture difference across the teacher-student pairs limits the distillation gains. In contrast to previous adaptive distillation methods to reduce the teacher-student gap, we explore a novel training-free framework to search for the best student architectures for a given teacher. Our work first empirically show that the optimal model under vanilla training cannot be the winner in distillation. Secondly, we find that the simil…
The University of Munich（慕尼黑大学）；Siemens AG, Corporate Technology（西门子股份公司企业技术部）
Knowledge Distillation, as a model compression technique, has received great attention. The knowledge of a well-performed teacher is distilled to a student with a small architecture. The architecture of the small student is often chosen to be similar to their teacher's, with fewer layers or fewer channels, or both. However, even with the same number of FLOPs or parameters, the students with different architecture can achieve different generalization ability. The configuration of a student architecture requires intensive network architecture engineering. In this work, instead of designing a goo…
State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data. Human transcription is expensive and time consuming. Factors such as the quality and consistency of the transcription can greatly affect the performance of the ASR models trained with these data. In this paper, we show that we can train a strong teacher model to produce high quality pseudo labels by utilizing recent self-supervised and semi-supervised learning techniques. Specifically, we use JUST (Joint Unsupervised/Supervised Training) and iterative noisy student te…
High-dimensional data in many machine learning applications leads to computational and analytical complexities. Feature selection provides an effective way for solving these problems by removing irrelevant and redundant features, thus reducing model complexity and improving accuracy and generalization capability of the model. In this paper, we present a novel teacher-student feature selection (TSFS) method in which a 'teacher' (a deep neural network or a complicated dimension reduction method) is first employed to learn the best representation of data in low dimension. Then a 'student' network…
DeSyR: A Decoupled Symbolic Recovery Framework with PINN-Guided Structure Search and Physics-Informed Coefficient Refinement
Chengdu University of Information Technology（成都信息工程大学）；Sichuan University（四川大学）；Hong Kong Polytechnic University（香港理工大学）；Southwest Petroleum University（西南石油大学）
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…
State University of New York at Binghamton（纽约州立大学宾汉姆顿分校）
Knowledge distillation (KD) is an effective technique to transfer knowledge from one neural network (teacher) to another (student), thus improving the performance of the student. To make the student better mimic the behavior of the teacher, the existing work focuses on designing different criteria to align their logits or representations. Different from these efforts, we address knowledge distillation from a novel data perspective. We argue that transferring knowledge at sparse training data points cannot enable the student to well capture the local shape of the teacher function. To address th…
We propose a method to incrementally learn an embedding space over the domain of network architectures, to enable the careful selection of architectures for evaluation during compressed architecture search. Given a teacher network, we search for a compressed network architecture by using Bayesian Optimization (BO) with a kernel function defined over our proposed embedding space to select architectures for evaluation. We demonstrate that our search algorithm can significantly outperform various baseline methods, such as random search and reinforcement learning (Ashok et al., 2018). The compress…
Istanbul Technical University（伊斯坦布尔理工大学）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Arcelik Research and Development（阿奇立克研发中心）
One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can drastically alter the compression performance, conventional distillation approaches overlook this fact and use the same hint points as in the early studies. Therefore, we propose a clustering based hint selection methodology, where the layers of teacher model are clustered with respect to several metrics and the cluster centers are used as the hint points. Our meth…
Carnegie Mellon University（卡内基梅隆大学）；University of California Berkeley（加州大学伯克利分校）
While numerous 3D detection works leverage the complementary relationship between RGB images and point clouds, developments in the broader framework of semi-supervised object recognition remain uninfluenced by multi-modal fusion. Current methods develop independent pipelines for 2D and 3D semi-supervised learning despite the availability of paired image and point cloud frames. Observing that the distinct characteristics of each sensor cause them to be biased towards detecting different objects, we propose DetMatch, a flexible framework for joint semi-supervised learning on 2D and 3D modalities…
Anomaly detection is a well-established research area that seeks to identify samples outside of a predetermined distribution. An anomaly detection pipeline is comprised of two main stages: (1) feature extraction and (2) normality score assignment. Recent papers used pre-trained networks for feature extraction achieving state-of-the-art results. However, the use of pre-trained networks does not fully-utilize the normal samples that are available at train time. This paper suggests taking advantage of this information by using teacher-student training. In our setting, a pretrained teacher network…
MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and Confidence-Gated Recovery
Department of Physics, Indian Institute of Technology (BHU)（印度理工学院（BHU）物理系）；eBRAIN Lab, Division of Engineering, New York University Abu Dhabi (NYUAD)（纽约大学阿布扎克分校（NYUAD）工程学院eBRAIN实验室）；Center for Quantum and Topological Systems (CQTS), NYUAD Research Institute, NYUAD（纽约大学阿布扎克分校（NYUAD）量子与拓扑系统中心（CQTS））
Knowledge distillation (KD) is a new method for transferring knowledge of a structure under training to another one. The typical application of KD is in the form of learning a small model (named as a student) by soft labels produced by a complex model (named as a teacher). Due to the novel idea introduced in KD, recently, its notion is used in different methods such as compression and processes that are going to enhance the model accuracy. Although different techniques are proposed in the area of KD, there is a lack of a model to generalize KD techniques. In this paper, various studies in the …
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…
Recent recommender systems have started to employ knowledge distillation, which is a model compression technique distilling knowledge from a cumbersome model (teacher) to a compact model (student), to reduce inference latency while maintaining performance. The state-of-the-art methods have only focused on making the student model accurately imitate the predictions of the teacher model. They have a limitation in that the prediction results incompletely reveal the teacher's knowledge. In this paper, we propose a novel knowledge distillation framework for recommender system, called DE-RRD, which …
SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）；University of Science and Technology of China（中国科学技术大学）
Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to distill better from a stronger teacher. We empirically find that the discrepancy of predictions between the student and a stronger teacher may tend to be fairly severer. As a result, the exact match of predictions in KL divergence would disturb the training and make existing methods perform poorly. In this paper, we show that simply preserving the relations be…
Knowledge distillation (KD) is a general neural network training approach that uses a teacher model to guide the student model. Existing works mainly study KD from the network output side (e.g., trying to design a better KD loss function), while few have attempted to understand it from the input side. Especially, its interplay with data augmentation (DA) has not been well understood. In this paper, we ask: Why do some DA schemes (e.g., CutMix) inherently perform much better than others in KD? What makes a "good" DA in KD? Our investigation from a statistical perspective suggests that a good DA…
