PyTorchKR Papers

최신 논문

총 4,526편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2109.15285

Improving Neural Ranking via Lossless Knowledge Distillation

We explore a novel perspective of knowledge distillation (KD) for learning to rank (LTR), and introduce Self-Distilled neural Rankers (SDR), where student rankers are parameterized identically to their teachers. Unlike the existing ranking distillation work which pursues a good trade-off between performance and efficiency, SDR is able to significantly improve ranking performance of students over the teacher rankers without increasing model capacity. The key success factors of SDR, which differs from common distillation techniques for classification are: (1) an appropriate teacher score transformation function, and (2) a novel listwise distillation framework. Both techniques are specifically designed for ranking problems and are rarely studied in the existing knowledge distillation literature. Building upon the state-of-the-art neural ranking structure, SDR is able to push the limits of neural ranking performance above a recent rigorous benchmark study and significantly outperforms traditionally strong gradient boosted decision tree based models on 7 out of 9 key metrics, the first time in the literature. In addition to the strong empirical results, we give theoretical explanations on why listwise distillation is effective for neural rankers, and provide ablation studies to verify the necessity of the key factors in the SDR framework.

arXiv:2109.15014

Deep Neural Compression Via Concurrent Pruning and Self-Distillation

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the pruned and unpruned versions of the same network is maximized. Unlike previous approaches that treat distillation and pruning separately, we use distillation to inform the pruning criteria, without requiring a separate student network as in knowledge distillation. We show that the proposed {\em cross-correlation objective for self-distilled pruning} implicitly encourages sparse solutions, naturally complementing magnitude-based pruning criteria. Experiments on the GLUE and XGLUE benchmarks show that self-distilled pruning increases mono- and cross-lingual language model performance. Self-distilled pruned models also outperform smaller Transformers with an equal number of parameters and are competitive against (6 times) larger distilled networks. We also observe that self-distillation (1) maximizes class separability, (2) increases the signal-to-noise ratio, and (3) converges faster after pruning steps, providing further insights into why self-distilled pruning improves generalization.

arXiv:2109.14960공식 코드 · Papers with Code

Prune Your Model Before Distill It

Knowledge distillation transfers the knowledge from a cumbersome teacher to a small student. Recent results suggest that the student-friendly teacher is more appropriate to distill since it provides more transferable knowledge. In this work, we propose the novel framework, "prune, then distill," that prunes the model first to make it more transferrable and then distill it to the student. We provide several exploratory examples where the pruned teacher teaches better than the original unpruned networks. We further show theoretically that the pruned teacher plays the role of regularizer in distillation, which reduces the generalization error. Based on this result, we propose a novel neural network compression scheme where the student network is formed based on the pruned teacher and then apply the "prune, then distill" strategy. The code is available at https://github.com/ososos888/prune-then-distill

arXiv:2109.14710

Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition

Modern Convolutional Neural Network (CNN) architectures, despite their superiority in solving various problems, are generally too large to be deployed on resource constrained edge devices. In this paper, we reduce memory usage and floating-point operations required by convolutional layers in CNNs. We compress these layers by generalizing the Kronecker Product Decomposition to apply to multidimensional tensors, leading to the Generalized Kronecker Product Decomposition (GKPD). Our approach yields a plug-and-play module that can be used as a drop-in replacement for any convolutional layer. Experimental results for image classification on CIFAR-10 and ImageNet datasets using ResNet, MobileNetv2 and SeNet architectures substantiate the effectiveness of our proposed approach. We find that GKPD outperforms state-of-the-art decomposition methods including Tensor-Train and Tensor-Ring as well as other relevant compression methods such as pruning and knowledge distillation.

arXiv:2109.15196공식 코드 · Papers with Code

Multilingual AMR Parsing with Noisy Knowledge Distillation

We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parser as its teacher. We constrain our exploration in a strict multilingual setting: there is but one model to parse all different languages including English. We identify that noisy input and precise output are the key to successful distillation. Together with extensive pre-training, we obtain an AMR parser whose performances surpass all previously published results on four different foreign languages, including German, Spanish, Italian, and Chinese, by large margins (up to 18.8 \textsc{Smatch} points on Chinese and on average 11.3 \textsc{Smatch} points). Our parser also achieves comparable performance on English to the latest state-of-the-art English-only parser.

arXiv:2109.12662공식 코드 · Papers with Code

Improving Question Answering Performance Using Knowledge Distillation and Active Learning

Contemporary question answering (QA) systems, including transformer-based architectures, suffer from increasing computational and model complexity which render them inefficient for real-world applications with limited resources. Further, training or even fine-tuning such models requires a vast amount of labeled data which is often not available for the task at hand. In this manuscript, we conduct a comprehensive analysis of the mentioned challenges and introduce suitable countermeasures. We propose a novel knowledge distillation (KD) approach to reduce the parameter and model complexity of a pre-trained BERT system and utilize multiple active learning (AL) strategies for immense reduction in annotation efforts. In particular, we demonstrate that our model achieves the performance of a 6-layer TinyBERT and DistilBERT, whilst using only 2% of their total parameters. Finally, by the integration of our AL approaches into the BERT framework, we show that state-of-the-art results on the SQuAD dataset can be achieved when we only use 20% of the training data.

arXiv:2109.12862공식 코드 · Papers with Code

Deep Structured Instance Graph for Distilling Object Detectors

Effectively structuring deep knowledge plays a pivotal role in transfer from teacher to student, especially in semantic vision tasks. In this paper, we present a simple knowledge structure to exploit and encode information inside the detection system to facilitate detector knowledge distillation. Specifically, aiming at solving the feature imbalance problem while further excavating the missing relation inside semantic instances, we design a graph whose nodes correspond to instance proposal-level features and edges represent the relation between nodes. To further refine this graph, we design an adaptive background loss weight to reduce node noise and background samples mining to prune trivial edges. We transfer the entire graph as encoded knowledge representation from teacher to student, capturing local and global information simultaneously. We achieve new state-of-the-art results on the challenging COCO object detection task with diverse student-teacher pairs on both one- and two-stage detectors. We also experiment with instance segmentation to demonstrate robustness of our method. It is notable that distilled Faster R-CNN with ResNet18-FPN and ResNet50-FPN yields 38.68 and 41.82 Box AP respectively on the COCO benchmark, Faster R-CNN with ResNet101-FPN significantly achieves 43.38 AP, which outperforms ResNet152-FPN teacher about 0.7 AP. Code: https://github.com/dvlab-research/Dsig.

arXiv:2109.12507

Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better

Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher. These existing distillation approaches simply focus on the improvement of \textit{knowledge quality}, but ignore the significant influence of \textit{knowledge quantity} on the distillation procedure. Opposed to the conventional distillation approaches, which extract knowledge from a fixed teacher computation graph, this paper explores a non-negligible research direction from a novel perspective of \textit{knowledge quantity} to further improve the efficacy of knowledge distillation. We introduce a new concept of knowledge decomposition, and further put forward the \textbf{P}artial to \textbf{W}hole \textbf{K}nowledge \textbf{D}istillation~(\textbf{PWKD}) paradigm. Specifically, we reconstruct teacher into weight-sharing sub-networks with same depth but increasing channel width, and train sub-networks jointly to obtain decomposed knowledge~(sub-networks with more channels represent more knowledge). Then, student extract partial to whole knowledge from the pre-trained teacher within multiple training stages where cyclic learning rate is leveraged to accelerate convergence. Generally, \textbf{PWKD} can be regarded as a plugin to be compatible with existing offline knowledge distillation approaches. To verify the effectiveness of \textbf{PWKD}, we conduct experiments on two benchmark datasets:~CIFAR-100 and ImageNet, and comprehensive evaluation results reveal that \textbf{PWKD} consistently improve existing knowledge distillation approaches without bells and whistles.

arXiv:2109.11078공식 코드 · Papers with Code

IE-GAN: An Improved Evolutionary Generative Adversarial Network Using a New Fitness Function and a Generic Crossover Operator

The training of generative adversarial networks (GANs) is usually vulnerable to mode collapse and vanishing gradients. The evolutionary generative adversarial network (E-GAN) attempts to alleviate these issues by optimizing the learning strategy with multiple loss functions. It uses a learning-based evolutionary framework, which develops new mutation operators specifically for general deep neural networks. However, the evaluation mechanism in the fitness function of E-GAN cannot truly reflect the adaptability of individuals to their environment, leading to an inaccurate assessment of the diversity of individuals. Moreover, the evolution step of E-GAN only contains mutation operators without considering the crossover operator jointly, isolating the superior characteristics among individuals. To address these issues, we propose an improved E-GAN framework called IE-GAN, which introduces a new fitness function and a generic crossover operator. In particular, the proposed fitness function, from an objective perspective, can model the evolutionary process of individuals more accurately. The crossover operator, which has been commonly adopted in evolutionary algorithms, can enable offspring to imitate the superior gene expression of their parents through knowledge distillation. Experiments on various datasets demonstrate the effectiveness of our proposed IE-GAN in terms of the quality of the generated samples and time efficiency.

arXiv:2109.11369

Recent Advances of Continual Learning in Computer Vision: An Overview

In contrast to batch learning where all training data is available at once, continual learning represents a family of methods that accumulate knowledge and learn continuously with data available in sequential order. Similar to the human learning process with the ability of learning, fusing, and accumulating new knowledge coming at different time steps, continual learning is considered to have high practical significance. Hence, continual learning has been studied in various artificial intelligence tasks. In this paper, we present a comprehensive review of the recent progress of continual learning in computer vision. In particular, the works are grouped by their representative techniques, including regularization, knowledge distillation, memory, generative replay, parameter isolation, and a combination of the above techniques. For each category of these techniques, both its characteristics and applications in computer vision are presented. At the end of this overview, several subareas, where continuous knowledge accumulation is potentially helpful while continual learning has not been well studied, are discussed.

arXiv:2109.11295공식 코드 · Papers with Code

Dynamic Knowledge Distillation for Pre-trained Language Models

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected teacher model on the pre-defined training dataset. In this paper, we explore whether a dynamic knowledge distillation that empowers the student to adjust the learning procedure according to its competency, regarding the student performance and learning efficiency. We explore the dynamical adjustments on three aspects: teacher model adoption, data selection, and KD objective adaptation. Experimental results show that (1) proper selection of teacher model can boost the performance of student model; (2) conducting KD with 10% informative instances achieves comparable performance while greatly accelerates the training; (3) the student performance can be boosted by adjusting the supervision contribution of different alignment objective. We find dynamic knowledge distillation is promising and provide discussions on potential future directions towards more efficient KD methods. Our code is available at https://github.com/lancopku/DynamicKD.

arXiv:2109.10902공식 코드 · Papers with Code

Segmentation with mixed supervision: Confidence maximization helps knowledge distillation

Despite achieving promising results in a breadth of medical image segmentation tasks, deep neural networks require large training datasets with pixel-wise annotations. Obtaining these curated datasets is a cumbersome process which limits the applicability in scenarios. Mixed supervision is an appealing alternative for mitigating this obstacle. In this work, we propose a dual-branch architecture, where the upper branch (teacher) receives strong annotations, while the bottom one (student) is driven by limited supervision and guided by the upper branch. Combined with a standard cross-entropy loss over the labeled pixels, our novel formulation integrates two important terms: (i) a Shannon entropy loss defined over the less-supervised images, which encourages confident student predictions in the bottom branch; and (ii) a KL divergence term, which transfers the knowledge (i.e., predictions) of the strongly supervised branch to the less-supervised branch and guides the entropy (student-confidence) term to avoid trivial solutions. We show that the synergy between the entropy and KL divergence yields substantial improvements in performance. We also discuss an interesting link between Shannon-entropy minimization and standard pseudo-mask generation, and argue that the former should be preferred over the latter for leveraging information from unlabeled pixels. We evaluate the effectiveness of the proposed formulation through a series of quantitative and qualitative experiments using two publicly available datasets. Results demonstrate that our method significantly outperforms other strategies for semantic segmentation within a mixed-supervision framework, as well as recent semi-supervised approaches. Our code is publicly available: https://github.com/by-liu/ConfKD.

arXiv:2109.10724

Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network

Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language model to take unobserved future context into account without waiting for the subsequent segment. Although this method achieves comparable speech quality to that of a method that waits for the future context, it entails a huge amount of processing for sampling from the language model at each time step. In this paper, we propose an incremental TTS method that directly predicts the unobserved future context with a lightweight model, instead of sampling words from the large-scale language model. We perform knowledge distillation from a GPT2-based context prediction network into a simple recurrent model by minimizing a teacher-student loss defined between the context embedding vectors of those models. Experimental results show that the proposed method requires about ten times less inference time to achieve comparable synthetic speech quality to that of our previous method, and it can perform incremental synthesis much faster than the average speaking speed of human English speakers, demonstrating the availability of our method to real-time applications.

arXiv:2109.10485

The NiuTrans Machine Translation Systems for WMT21

This paper describes NiuTrans neural machine translation systems of the WMT 2021 news translation tasks. We made submissions to 9 language directions, including English$\leftrightarrow$$\{$Chinese, Japanese, Russian, Icelandic$\}$ and English$\rightarrow$Hausa tasks. Our primary systems are built on several effective variants of Transformer, e.g., Transformer-DLCL, ODE-Transformer. We also utilize back-translation, knowledge distillation, post-ensemble, and iterative fine-tuning techniques to enhance the model performance further.

arXiv:2109.10504

KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation

Self-supervised vision-and-language pretraining (VLP) aims to learn transferable multi-modal representations from large-scale image-text data and to achieve strong performances on a broad scope of vision-language tasks after finetuning. Previous mainstream VLP approaches typically adopt a two-step strategy relying on external object detectors to encode images in a multi-modal Transformer framework, which suffer from restrictive object concept space, limited image context and inefficient computation. In this paper, we propose an object-aware end-to-end VLP framework, which directly feeds image grid features from CNNs into the Transformer and learns the multi-modal representations jointly. More importantly, we propose to perform object knowledge distillation to facilitate learning cross-modal alignment at different semantic levels. To achieve that, we design two novel pretext tasks by taking object features and their semantic labels from external detectors as supervision: 1.) Object-guided masked vision modeling task focuses on enforcing object-aware representation learning in the multi-modal Transformer; 2.) Phrase-region alignment task aims to improve cross-modal alignment by utilizing the similarities between noun phrases and object labels in the linguistic space. Extensive experiments on a wide range of vision-language tasks demonstrate the efficacy of our proposed framework, and we achieve competitive or superior performances over the existing pretraining strategies.

arXiv:2109.10547

K-AID: Enhancing Pre-trained Language Models with Domain Knowledge for Question Answering

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic approach that includes a low-cost knowledge acquisition process for acquiring domain knowledge, an effective knowledge infusion module for improving model performance, and a knowledge distillation component for reducing the model size and deploying K-PLMs on resource-restricted devices (e.g., CPU) for real-world application. Importantly, instead of capturing entity knowledge like the majority of existing K-PLMs, our approach captures relational knowledge, which contributes to better-improving sentence-level text classification and text matching tasks that play a key role in question answering (QA). We conducted a set of experiments on five text classification tasks and three text matching tasks from three domains, namely E-commerce, Government, and Film&TV, and performed online A/B tests in E-commerce. Experimental results show that our approach is able to achieve substantial improvement on sentence-level question answering tasks and bring beneficial business value in industrial settings.

arXiv:2109.10164

RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation

Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained language models. However, intermediate layer distillation suffers from excessive computational burdens and engineering efforts required for setting up a proper layer mapping. To address these problems, we propose a RAndom Intermediate Layer Knowledge Distillation (RAIL-KD) approach in which, intermediate layers from the teacher model are selected randomly to be distilled into the intermediate layers of the student model. This randomized selection enforce that: all teacher layers are taken into account in the training process, while reducing the computational cost of intermediate layer distillation. Also, we show that it act as a regularizer for improving the generalizability of the student model. We perform extensive experiments on GLUE tasks as well as on out-of-domain test sets. We show that our proposed RAIL-KD approach outperforms other state-of-the-art intermediate layer KD methods considerably in both performance and training-time.

arXiv:2109.10147

Knowledge Distillation with Noisy Labels for Natural Language Understanding

Knowledge Distillation (KD) is extensively used to compress and deploy large pre-trained language models on edge devices for real-world applications. However, one neglected area of research is the impact of noisy (corrupted) labels on KD. We present, to the best of our knowledge, the first study on KD with noisy labels in Natural Language Understanding (NLU). We document the scope of the problem and present two methods to mitigate the impact of label noise. Experiments on the GLUE benchmark show that our methods are effective even under high noise levels. Nevertheless, our results indicate that more research is necessary to cope with label noise under the KD.

arXiv:2109.08907공식 코드 · Papers with Code

Releasing Graph Neural Networks with Differential Privacy Guarantees

With the increasing popularity of graph neural networks (GNNs) in several sensitive applications like healthcare and medicine, concerns have been raised over the privacy aspects of trained GNNs. More notably, GNNs are vulnerable to privacy attacks, such as membership inference attacks, even if only black-box access to the trained model is granted. We propose PrivGNN, a privacy-preserving framework for releasing GNN models in a centralized setting. Assuming an access to a public unlabeled graph, PrivGNN provides a framework to release GNN models trained explicitly on public data along with knowledge obtained from the private data in a privacy preserving manner. PrivGNN combines the knowledge-distillation framework with the two noise mechanisms, random subsampling, and noisy labeling, to ensure rigorous privacy guarantees. We theoretically analyze our approach in the Renyi differential privacy framework. Besides, we show the solid experimental performance of our method compared to several baselines adapted for graph-structured data. Our code is available at https://github.com/iyempissy/privGnn.

arXiv:2008.00671

TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance improvements, end-to-end models typically require expensive computational cost to show successful performance. To reduce this computational burden, knowledge distillation (KD), which is a popular model compression method, has been used to transfer knowledge from a deep and complex model (teacher) to a shallower and simpler model (student). Previous KD approaches have commonly designed the architecture of the student model by reducing the width per layer or the number of layers of the teacher model. This structural reduction scheme might limit the flexibility of model selection since the student model structure should be similar to that of the given teacher. To cope with this limitation, we propose a new KD method for end-to-end speech recognition, namely TutorNet, that can transfer knowledge across different types of neural networks at the hidden representation-level as well as the output-level. For concrete realizations, we firstly apply representation-level knowledge distillation (RKD) during the initialization step, and then apply the softmax-level knowledge distillation (SKD) combined with the original task learning. When the student is trained with RKD, we make use of frame weighting that points out the frames to which the teacher model pays more attention. Through a number of experiments on LibriSpeech dataset, it is verified that the proposed method not only distills the knowledge between networks with different topologies but also significantly contributes to improving the word error rate (WER) performance of the distilled student. Interestingly, TutorNet allows the student model to surpass its teacher's performance in some particular cases.