PyTorchKR Papers

최신 논문

총 2,847편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2009.10835

Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networks

We study different aspects of active learning with deep neural networks in a consistent and unified way. i) We investigate incremental and cumulative training modes which specify how the newly labeled data are used for training. ii) We study active learning w.r.t. the model configurations such as the number of epochs and neurons as well as the choice of batch size. iii) We consider in detail the behavior of query strategies and their corresponding informativeness measures and accordingly propose more efficient querying procedures. iv) We perform statistical analyses, e.g., on actively learned classes and test error estimation, that reveal several insights about active learning. v) We investigate how active learning with neural networks can benefit from pseudo-labels as proxies for actual labels.

arXiv:2009.10214

DISPATCH: Design Space Exploration of Cyber-Physical Systems

Design of cyber-physical systems (CPSs) is a challenging task that involves searching over a large search space of various CPS configurations and possible values of components composing the system. Hence, there is a need for sample-efficient CPS design space exploration to select the system architecture and component values that meet the target system requirements. We address this challenge by formulating CPS design as a multi-objective optimization problem and propose DISPATCH, a two-step methodology for sample-efficient search over the design space. First, we use a genetic algorithm to search over discrete choices of system component values for architecture search and component selection or only component selection and terminate the algorithm even before meeting the system requirements, thus yielding a coarse design. In the second step, we use an inverse design to search over a continuous space to fine-tune the component values and meet the diverse set of system requirements. We use a neural network as a surrogate function for the inverse design of the system. The neural network, converted into a mixed-integer linear program, is used for active learning to sample component values efficiently in a continuous search space. We illustrate the efficacy of DISPATCH on electrical circuit benchmarks: two-stage and three-stage transimpedence amplifiers. Simulation results show that the proposed methodology improves sample efficiency by 5-14x compared to a prior synthesis method that relies on reinforcement learning. It also synthesizes circuits with the best performance (highest bandwidth/lowest area) compared to designs synthesized using reinforcement learning, Bayesian optimization, or humans.

arXiv:2009.10259

ALICE: Active Learning with Contrastive Natural Language Explanations

Training a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process uses a low-bandwidth human-machine communication interface: classification labels, each of which only provides several bits of information. We propose Active Learning with Contrastive Explanations (ALICE), an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning. ALICE learns to first use active learning to select the most informative pairs of label classes to elicit contrastive natural language explanations from experts. Then it extracts knowledge from these explanations using a semantic parser. Finally, it incorporates the extracted knowledge through dynamically changing the learning model's structure. We applied ALICE in two visual recognition tasks, bird species classification and social relationship classification. We found by incorporating contrastive explanations, our models outperform baseline models that are trained with 40-100% more training data. We found that adding 1 explanation leads to similar performance gain as adding 13-30 labeled training data points.

arXiv:2009.09143

Active Learning for Product Type Ontology Enhancement in E-commerce

Entity-based semantic search has been widely adopted in modern search engines to improve search accuracy by understanding users' intent. In e-commerce, an accurate and complete product type (PT) ontology is essential for recognizing product entities in queries and retrieving relevant products from catalog. However, finding product types (PTs) to construct such an ontology is usually expensive due to the considerable amount of human efforts it may involve. In this work, we propose an active learning framework that efficiently utilizes domain experts' knowledge for PT discovery. We also show the quality and coverage of the resulting PTs in the experiment results.

arXiv:2009.08166

Mean-Variance Analysis in Bayesian Optimization under Uncertainty

We consider active learning (AL) in an uncertain environment in which trade-off between multiple risk measures need to be considered. As an AL problem in such an uncertain environment, we study Mean-Variance Analysis in Bayesian Optimization (MVA-BO) setting. Mean-variance analysis was developed in the field of financial engineering and has been used to make decisions that take into account the trade-off between the average and variance of investment uncertainty. In this paper, we specifically focus on BO setting with an uncertain component and consider multi-task, multi-objective, and constrained optimization scenarios for the mean-variance trade-off of the uncertain component. When the target blackbox function is modeled by Gaussian Process (GP), we derive the bounds of the two risk measures and propose AL algorithm for each of the above three problems based on the risk measure bounds. We show the effectiveness of the proposed AL algorithms through theoretical analysis and numerical experiments.

arXiv:2009.06398

On Computability, Learnability and Extractability of Finite State Machines from Recurrent Neural Networks

This work aims at shedding some light on connections between finite state machines (FSMs), and recurrent neural networks (RNNs). Examined connections in this master's thesis is threefold: the extractability of finite state machines from recurrent neural networks, learnability aspects and computationnal links. With respect to the former, the long-standing clustering hypothesis of RNN hidden state space when trained to recognize regular languages was explored, and new insights into this hypothesis through the lens of recent advances of the generalization theory of Deep Learning are provided. As for learnability, an extension of the active learning framework better suited to the problem of approximating RNNs with FSMs is proposed, with the aim of better formalizing the problem of RNN approximation by FSMs. Theoretical analysis of two possible scenarions in this framework were performed. With regard to computability, new computational results on the distance and the equivalence problem between RNNs trained as language models and different types of weighted finite state machines were given.

arXiv:2009.06492

Beyond Accuracy: ROI-driven Data Analytics of Empirical Data

This vision paper demonstrates that it is crucial to consider Return-on-Investment (ROI) when performing Data Analytics. Decisions on "How much analytics is needed"? are hard to answer. ROI could guide for decision support on the What?, How?, and How Much? analytics for a given problem. Method: The proposed conceptual framework is validated through two empirical studies that focus on requirements dependencies extraction in the Mozilla Firefox project. The two case studies are (i) Evaluation of fine-tuned BERT against Naive Bayes and Random Forest machine learners for binary dependency classification and (ii) Active Learning against passive Learning (random sampling) for REQUIRES dependency extraction. For both the cases, their analysis investment (cost) is estimated, and the achievable benefit from DA is predicted, to determine a break-even point of the investigation. Results: For the first study, fine-tuned BERT performed superior to the Random Forest, provided that more than 40% of training data is available. For the second, Active Learning achieved higher F1 accuracy within fewer iterations and higher ROI compared to Baseline (Random sampling based RF classifier). In both the studies, estimate on, How much analysis likely would pay off for the invested efforts?, was indicated by the break-even point. Conclusions: Decisions for the depth and breadth of DA of empirical data should not be made solely based on the accuracy measures. Since ROI-driven Data Analytics provides a simple yet effective direction to discover when to stop further investigation while considering the cost and value of the various types of analysis, it helps to avoid over-analyzing empirical data.

arXiv:2009.06415공식 코드 · Papers with Code

Synbols: Probing Learning Algorithms with Synthetic Datasets

Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing algorithms. Enabling the design of datasets to test specific properties and failure modes of learning algorithms is thus a problem of high interest, as it has a direct impact on innovation in the field. In this sense, we introduce Synbols -- Synthetic Symbols -- a tool for rapidly generating new datasets with a rich composition of latent features rendered in low resolution images. Synbols leverages the large amount of symbols available in the Unicode standard and the wide range of artistic font provided by the open font community. Our tool's high-level interface provides a language for rapidly generating new distributions on the latent features, including various types of textures and occlusions. To showcase the versatility of Synbols, we use it to dissect the limitations and flaws in standard learning algorithms in various learning setups including supervised learning, active learning, out of distribution generalization, unsupervised representation learning, and object counting.

arXiv:2009.05436

Semi-Supervised Active Learning for COVID-19 Lung Ultrasound Multi-symptom Classification

Ultrasound (US) is a non-invasive yet effective medical diagnostic imaging technique for the COVID-19 global pandemic. However, due to complex feature behaviors and expensive annotations of US images, it is difficult to apply Artificial Intelligence (AI) assisting approaches for lung's multi-symptom (multi-label) classification. To overcome these difficulties, we propose a novel semi-supervised Two-Stream Active Learning (TSAL) method to model complicated features and reduce labeling costs in an iterative procedure. The core component of TSAL is the multi-label learning mechanism, in which label correlations information is used to design multi-label margin (MLM) strategy and confidence validation for automatically selecting informative samples and confident labels. On this basis, a multi-symptom multi-label (MSML) classification network is proposed to learn discriminative features of lung symptoms, and a human-machine interaction is exploited to confirm the final annotations that are used to fine-tune MSML with progressively labeled data. Moreover, a novel lung US dataset named COVID19-LUSMS is built, currently containing 71 clinical patients with 6,836 images sampled from 678 videos. Experimental evaluations show that TSAL using only 20% data can achieve superior performance to the baseline and the state-of-the-art. Qualitatively, visualization of both attention map and sample distribution confirms the good consistency with the clinic knowledge.

arXiv:2009.05105

What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper

Social norms support coordination and cooperation in society. With social robots becoming increasingly involved in our society, they also need to follow the social norms of the society. This paper presents a computational framework for learning contexts and the social norms present in a context in an online manner on a robot. The paper utilizes a recent state-of-the-art approach for incremental learning and adapts it for online learning of scenes (contexts). The paper further utilizes Dempster-Schafer theory to model context-specific norms. After learning the scenes (contexts), we use active learning to learn related norms. We test our approach on the Pepper robot by taking it through different scene locations. Our results show that Pepper can learn different scenes and related norms simply by communicating with a human partner in an online manner.

arXiv:2009.04568

Active Learning++: Incorporating Annotator's Rationale using Local Model Explanation

We propose a new active learning (AL) framework, Active Learning++, which can utilize an annotator's labels as well as its rationale. Annotators can provide their rationale for choosing a label by ranking input features based on their importance for a given query. To incorporate this additional input, we modified the disagreement measure for a bagging-based Query by Committee (QBC) sampling strategy. Instead of weighing all committee models equally to select the next instance, we assign higher weight to the committee model with higher agreement with the annotator's ranking. Specifically, we generated a feature importance-based local explanation for each committee model. The similarity score between feature rankings provided by the annotator and the local model explanation is used to assign a weight to each corresponding committee model. This approach is applicable to any kind of ML model using model-agnostic techniques to generate local explanation such as LIME. With a simulation study, we show that our framework significantly outperforms a QBC based vanilla AL framework.

arXiv:2009.03009

Active Learning of Causal Structures with Deep Reinforcement Learning

We study the problem of experiment design to learn causal structures from interventional data. We consider an active learning setting in which the experimenter decides to intervene on one of the variables in the system in each step and uses the results of the intervention to recover further causal relationships among the variables. The goal is to fully identify the causal structures with minimum number of interventions. We present the first deep reinforcement learning based solution for the problem of experiment design. In the proposed method, we embed input graphs to vectors using a graph neural network and feed them to another neural network which outputs a variable for performing intervention in each step. Both networks are trained jointly via a Q-iteration algorithm. Experimental results show that the proposed method achieves competitive performance in recovering causal structures with respect to previous works, while significantly reducing execution time in dense graphs.

arXiv:2009.03219

Active deep learning method for the discovery of objects of interest in large spectroscopic surveys

Current archives of the LAMOST telescope contain millions of pipeline-processed spectra that have probably never been seen by human eyes. Most of the rare objects with interesting physical properties, however, can only be identified by visual analysis of their characteristic spectral features. A proper combination of interactive visualisation with modern machine learning techniques opens new ways to discover such objects. We apply active learning classification supported by deep convolutional networks to automatically identify complex emission-line shapes in multi-million spectra archives. We used the pool-based uncertainty sampling active learning driven by a custom-designed deep convolutional neural network with 12 layers inspired by VGGNet, AlexNet, and ZFNet, but adapted for one-dimensional feature vectors. The unlabelled pool set is represented by 4.1 million spectra from the LAMOST DR2 survey. The initial training of the network was performed on a labelled set of about 13000 spectra obtained in the region around H$\alpha$ by the 2m Perek telescope of the Ond\v{r}ejov observatory, which mostly contains spectra of Be and related early-type stars. The differences between the Ond\v{r}ejov intermediate-resolution and the LAMOST low-resolution spectrographs were compensated for by Gaussian blurring. After several iterations, the network was able to successfully identify emission-line stars with an error smaller than 6.5%. Using the technology of the Virtual Observatory to visualise the results, we discovered 1013 spectra of 948 new candidates of emission-line objects in addition to 664 spectra of 549 objects that are listed in SIMBAD and 2644 spectra of 2291 objects identified in an earlier paper of a Chinese group led by Wen Hou. The most interesting objects with unusual spectral properties are discussed in detail.

arXiv:2009.01420

Accelerating engineering design by automatic selection of simulation cases through Pool-Based Active Learning

A common workflow for many engineering design problems requires the evaluation of the design system to be investigated under a range of conditions. These conditions usually involve a combination of several parameters. To perform a complete evaluation of a single candidate configuration, it may be necessary to perform hundreds to thousands of simulations. This can be computationally very expensive, particularly if several configurations need to be evaluated, as in the case of the mathematical optimization of a design problem. Although the simulations are extremely complex, generally, there is a high degree of redundancy in them, as many of the cases vary only slightly from one another. This redundancy can be exploited by omitting some simulations that are uninformative, thereby reducing the number of simulations required to obtain a reasonable approximation of the complete system. The decision of which simulations are useful is made through the use of machine learning techniques, which allow us to estimate the results of "yet-to-be-performed" simulations from the ones that are already performed. In this study, we present the results of one such technique, namely active learning, to provide an approximate result of an entire offshore riser design simulation portfolio from a subset that is 80% smaller than the original one. These results are expected to facilitate a significant speed-up in the offshore riser design.

arXiv:2009.01797

A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning

Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is investigated. The core challenge is framed as protecting previously acquired representations from being catastrophically forgotten. However, comparison of individual methods is nevertheless performed in isolation from the real world by monitoring accumulated benchmark test set performance. The closed world assumption remains predominant, i.e. models are evaluated on data that is guaranteed to originate from the same distribution as used for training. This poses a massive challenge as neural networks are well known to provide overconfident false predictions on unknown and corrupted instances. In this work we critically survey the literature and argue that notable lessons from open set recognition, identifying unknown examples outside of the observed set, and the adjacent field of active learning, querying data to maximize the expected performance gain, are frequently overlooked in the deep learning era. Hence, we propose a consolidated view to bridge continual learning, active learning and open set recognition in deep neural networks. Finally, the established synergies are supported empirically, showing joint improvement in alleviating catastrophic forgetting, querying data, selecting task orders, while exhibiting robust open world application.

arXiv:2009.00320

Active Deep Densely Connected Convolutional Network for Hyperspectral Image Classification

Deep learning based methods have seen a massive rise in popularity for hyperspectral image classification over the past few years. However, the success of deep learning is attributed greatly to numerous labeled samples. It is still very challenging to use only a few labeled samples to train deep learning models to reach a high classification accuracy. An active deep-learning framework trained by an end-to-end manner is, therefore, proposed by this paper in order to minimize the hyperspectral image classification costs. First, a deep densely connected convolutional network is considered for hyperspectral image classification. Different from the traditional active learning methods, an additional network is added to the designed deep densely connected convolutional network to predict the loss of input samples. Then, the additional network could be used to suggest unlabeled samples that the deep densely connected convolutional network is more likely to produce a wrong label. Note that the additional network uses the intermediate features of the deep densely connected convolutional network as input. Therefore, the proposed method is an end-to-end framework. Subsequently, a few of the selected samples are labelled manually and added to the training samples. The deep densely connected convolutional network is therefore trained using the new training set. Finally, the steps above are repeated to train the whole framework iteratively. Extensive experiments illustrates that the method proposed could reach a high accuracy in classification after selecting just a few samples.

arXiv:2009.00236

A Survey of Deep Active Learning

Active learning (AL) attempts to maximize the performance gain of the model by marking the fewest samples. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model learns how to extract high-quality features. In recent years, due to the rapid development of internet technology, we are in an era of information torrents and we have massive amounts of data. In this way, DL has aroused strong interest of researchers and has been rapidly developed. Compared with DL, researchers have relatively low interest in AL. This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples. Therefore, early AL is difficult to reflect the value it deserves. Although DL has made breakthroughs in various fields, most of this success is due to the publicity of the large number of existing annotation datasets. However, the acquisition of a large number of high-quality annotated datasets consumes a lot of manpower, which is not allowed in some fields that require high expertise, especially in the fields of speech recognition, information extraction, medical images, etc. Therefore, AL has gradually received due attention. A natural idea is whether AL can be used to reduce the cost of sample annotations, while retaining the powerful learning capabilities of DL. Therefore, deep active learning (DAL) has emerged. Although the related research has been quite abundant, it lacks a comprehensive survey of DAL. This article is to fill this gap, we provide a formal classification method for the existing work, and a comprehensive and systematic overview. In addition, we also analyzed and summarized the development of DAL from the perspective of application. Finally, we discussed the confusion and problems in DAL, and gave some possible development directions for DAL.

arXiv:2009.00859

ALEX: Active Learning based Enhancement of a Model's Explainability

An active learning (AL) algorithm seeks to construct an effective classifier with a minimal number of labeled examples in a bootstrapping manner. While standard AL heuristics, such as selecting those points for annotation for which a classification model yields least confident predictions, there has been no empirical investigation to see if these heuristics lead to models that are more interpretable to humans. In the era of data-driven learning, this is an important research direction to pursue. This paper describes our work-in-progress towards developing an AL selection function that in addition to model effectiveness also seeks to improve on the interpretability of a model during the bootstrapping steps. Concretely speaking, our proposed selection function trains an `explainer' model in addition to the classifier model, and favours those instances where a different part of the data is used, on an average, to explain the predicted class. Initial experiments exhibited encouraging trends in showing that such a heuristic can lead to developing more effective and more explainable end-to-end data-driven classifiers.

arXiv:2008.13492

Wireless for Machine Learning

As data generation increasingly takes place on devices without a wired connection, machine learning (ML) related traffic will be ubiquitous in wireless networks. Many studies have shown that traditional wireless protocols are highly inefficient or unsustainable to support ML, which creates the need for new wireless communication methods. In this survey, we give an exhaustive review of the state-of-the-art wireless methods that are specifically designed to support ML services over distributed datasets. Currently, there are two clear themes within the literature, analog over-the-air computation and digital radio resource management optimized for ML. This survey gives a comprehensive introduction to these methods, reviews the most important works, highlights open problems, and discusses application scenarios.

arXiv:2008.12649

Active learning of deep surrogates for PDEs: Application to metasurface design

Surrogate models for partial-differential equations are widely used in the design of meta-materials to rapidly evaluate the behavior of composable components. However, the training cost of accurate surrogates by machine learning can rapidly increase with the number of variables. For photonic-device models, we find that this training becomes especially challenging as design regions grow larger than the optical wavelength. We present an active learning algorithm that reduces the number of training points by more than an order of magnitude for a neural-network surrogate model of optical-surface components compared to random samples. Results show that the surrogate evaluation is over two orders of magnitude faster than a direct solve, and we demonstrate how this can be exploited to accelerate large-scale engineering optimization.