PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.12982

From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search

We introduce deep learning models to the two most important stages in product search at JD.com, one of the largest e-commerce platforms in the world. Specifically, we outline the design of a deep learning system that retrieves semantically relevant items to a query within milliseconds, and a pairwise deep re-ranking system, which learns subtle user preferences. Compared to traditional search systems, the proposed approaches are better at semantic retrieval and personalized ranking, achieving significant improvements.

arXiv:2103.13314공식 코드 · Papers with Code

MONAIfbs: MONAI-based fetal brain MRI deep learning segmentation

In fetal Magnetic Resonance Imaging, Super Resolution Reconstruction (SRR) algorithms are becoming popular tools to obtain high-resolution 3D volume reconstructions from low-resolution stacks of 2D slices, acquired at different orientations. To be effective, these algorithms often require accurate segmentation of the region of interest, such as the fetal brain in suspected pathological cases. In the case of Spina Bifida, Ebner, Wang et al. (NeuroImage, 2020) combined their SRR algorithm with a 2-step segmentation pipeline (2D localisation followed by a 2D segmentation network). However, if the localisation step fails, the second network is not able to recover a correct brain mask, thus requiring manual corrections for an effective SRR. In this work, we aim at improving the fetal brain segmentation for SRR in Spina Bifida. We hypothesise that a well-trained single-step UNet can achieve accurate performance, avoiding the need of a 2-step approach. We propose a new tool for fetal brain segmentation called MONAIfbs, which takes advantage of the Medical Open Network for Artificial Intelligence (MONAI) framework. Our network is based on the dynamic UNet (dynUNet), an adaptation of the nnU-Net framework. When compared to the original 2-step approach proposed in Ebner-Wang, and the same Ebner-Wang approach retrained with the expanded dataset available for this work, the dynUNet showed to achieve higher performance using a single step only. It also showed to reduce the number of outliers, as only 28 stacks obtained Dice score less than 0.9, compared to 68 for Ebner-Wang and 53 Ebner-Wang expanded. The proposed dynUNet model thus provides an improvement of the state-of-the-art fetal brain segmentation techniques, reducing the need for manual correction in automated SRR pipelines. Our code and our trained model are made publicly available at https://github.com/gift-surg/MONAIfbs.

arXiv:2103.12551

Deep Learning for Exotic Option Valuation

A common approach to valuing exotic options involves choosing a model and then determining its parameters to fit the volatility surface as closely as possible. We refer to this as the model calibration approach (MCA). A disadvantage of MCA is that some information in the volatility surface is lost during the calibration process and the prices of exotic options will not in general be consistent with those of plain vanilla options. We consider an alternative approach where the structure of the user's preferred model is preserved but points on the volatility are features input to a neural network. We refer to this as the volatility feature approach (VFA) model. We conduct experiments showing that VFA can be expected to outperform MCA for the volatility surfaces encountered in practice. Once the upfront computational time has been invested in developing the neural network, the valuation of exotic options using VFA is very fast.

arXiv:2103.12102공식 코드 · Papers with Code

A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients

There is a shortage of multi-wavelength and spectroscopic followup capabilities given the number of transient and variable astrophysical events discovered through wide-field, optical surveys such as the upcoming Vera C. Rubin Observatory. From the haystack of potential science targets, astronomers must allocate scarce resources to study a selection of needles in real time. Here we present a variational recurrent autoencoder neural network to encode simulated Rubin Observatory extragalactic transient events using 1% of the PLAsTiCC dataset to train the autoencoder. Our unsupervised method uniquely works with unlabeled, real time, multivariate and aperiodic data. We rank 1,129,184 events based on an anomaly score estimated using an isolation forest. We find that our pipeline successfully ranks rarer classes of transients as more anomalous. Using simple cuts in anomaly score and uncertainty, we identify a pure (~95% pure) sample of rare transients (i.e., transients other than Type Ia, Type II and Type Ibc supernovae) including superluminous and pair-instability supernovae. Finally, our algorithm is able to identify these transients as anomalous well before peak, enabling real-time follow up studies in the era of the Rubin Observatory.

arXiv:2103.12608공식 코드 · Papers with Code

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning. In the research community, implementing and benchmarking various advanced tasks are still painful and time-consuming with existing libraries. To facilitate graph deep learning research, we introduce DIG: Dive into Graphs, a turnkey library that provides a unified testbed for higher level, research-oriented graph deep learning tasks. Currently, we consider graph generation, self-supervised learning on graphs, explainability of graph neural networks, and deep learning on 3D graphs. For each direction, we provide unified implementations of data interfaces, common algorithms, and evaluation metrics. Altogether, DIG is an extensible, open-source, and turnkey library for researchers to develop new methods and effortlessly compare with common baselines using widely used datasets and evaluation metrics. Source code is available at https://github.com/divelab/DIG.

arXiv:2103.11072

Local Interpretations for Explainable Natural Language Processing: A Survey

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models. This work investigates various methods to improve the interpretability of deep neural networks for Natural Language Processing (NLP) tasks, including machine translation and sentiment analysis. We provide a comprehensive discussion on the definition of the term interpretability and its various aspects at the beginning of this work. The methods collected and summarised in this survey are only associated with local interpretation and are specifically divided into three categories: 1) interpreting the model's predictions through related input features; 2) interpreting through natural language explanation; 3) probing the hidden states of models and word representations.

arXiv:2103.10975

Accelerating GMRES with Deep Learning in Real-Time

GMRES is a powerful numerical solver used to find solutions to extremely large systems of linear equations. These systems of equations appear in many applications in science and engineering. Here we demonstrate a real-time machine learning algorithm that can be used to accelerate the time-to-solution for GMRES. Our framework is novel in that is integrates the deep learning algorithm in an in situ fashion: the AI-accelerator gradually learns how to optimizes the time to solution without requiring user input (such as a pre-trained data set). We describe how our algorithm collects data and optimizes GMRES. We demonstrate our algorithm by implementing an accelerated (MLGMRES) solver in Python. We then use MLGMRES to accelerate a solver for the Poisson equation -- a class of linear problems that appears in may applications. Informed by the properties of formal solutions to the Poisson equation, we test the performance of different neural networks. Our key takeaway is that networks which are capable of learning non-local relationships perform well, without needing to be scaled with the input problem size, making them good candidates for the extremely large problems encountered in high-performance computing. For the inputs studied, our method provides a roughly 2$\times$ acceleration.

arXiv:2103.11598

Adaptive Degradation Process with Deep Learning-Driven Trajectory

Remaining useful life (RUL) estimation is a crucial component in the implementation of intelligent predictive maintenance and health management. Deep neural network (DNN) approaches have been proven effective in RUL estimation due to their capacity in handling high-dimensional non-linear degradation features. However, the applications of DNN in practice face two challenges: (a) online update of lifetime information is often unavailable, and (b) uncertainties in predicted values may not be analytically quantified. This paper addresses these issues by developing a hybrid DNN-based prognostic approach, where a Wiener-based-degradation model is enhanced with adaptive drift to characterize the system degradation. An LSTM-CNN encoder-decoder is developed to predict future degradation trajectories by jointly learning noise coefficients as well as drift coefficients, and adaptive drift is updated via Bayesian inference. A computationally efficient algorithm is proposed for the calculation of RUL distributions. Numerical experiments are presented using turbofan engines degradation data to demonstrate the superior accuracy of RUL prediction of our proposed approach.

arXiv:2103.11509

Scatter Correction in X-ray CT by Physics-Inspired Deep Learning

Scatter due to interaction of photons with the imaged object is a fundamental problem in X-ray Computed Tomography (CT). It manifests as various artifacts in the reconstruction, making its abatement or correction critical for image quality. Despite success in specific settings, hardware-based methods require modification in the hardware, or increase in the scan time or dose. This accounts for the great interest in software-based methods, including Monte-Carlo based scatter estimation, analytical-numerical, and kernel-based methods, with data-driven learning-based approaches demonstrated recently. In this work, two novel physics-inspired deep-learning-based methods, PhILSCAT and OV-PhILSCAT, are proposed. The methods estimate and correct for the scatter in the acquired projection measurements. Different from previous works, they incorporate both an initial reconstruction of the object of interest and the scatter-corrupted measurements related to it, and use a deep neural network architecture and cost function, both specifically tailored to the problem. Numerical experiments with data generated by Monte-Carlo simulations of the imaging of phantoms reveal consistent improvement over a recent purely projection-domain deep neural network scatter correction method.

arXiv:2103.11834

Generation and Simulation of Yeast Microscopy Imagery with Deep Learning

Time-lapse fluorescence microscopy (TLFM) is an important and powerful tool in synthetic biological research. Modeling TLFM experiments based on real data may enable researchers to repeat certain experiments with minor effort. This thesis is a study towards deep learning-based modeling of TLFM experiments on the image level. The modeling of TLFM experiments, by way of the example of trapped yeast cells, is split into two tasks. The first task is to generate synthetic image data based on real image data. To approach this problem, a novel generative adversarial network, for conditionalized and unconditionalized image generation, is proposed. The second task is the simulation of brightfield microscopy images over multiple discrete time-steps. To tackle this simulation task an advanced future frame prediction model is introduced. The proposed models are trained and tested on a novel dataset that is presented in this thesis. The obtained results showed that the modeling of TLFM experiments, with deep learning, is a proper approach, but requires future research to effectively model real-world experiments.

arXiv:2103.11806

Tackling Racial Bias in Automated Online Hate Detection: Towards Fair and Accurate Classification of Hateful Online Users Using Geometric Deep Learning

Online hate is a growing concern on many social media platforms and other sites. To combat it, technology companies are increasingly identifying and sanctioning `hateful users' rather than simply moderating hateful content. Yet, most research in online hate detection to date has focused on hateful content. This paper examines how fairer and more accurate hateful user detection systems can be developed by incorporating social network information through geometric deep learning. Geometric deep learning dynamically learns information-rich network representations and can generalise to unseen nodes. This is essential for moving beyond manually engineered network features, which lack scalability and produce information-sparse network representations. This paper compares the accuracy of geometric deep learning with other techniques which either exclude network information or incorporate it through manual feature engineering (e.g., node2vec). It also evaluates the fairness of these techniques using the `predictive equality' criteria, comparing the false positive rates on a subset of 136 African-American users with 4836 other users. Geometric deep learning produces the most accurate and fairest classifier, with an AUC score of 90.8\% on the entire dataset and a false positive rate of zero among the African-American subset for the best performing model. This highlights the benefits of more effectively incorporating social network features in automated hateful user detection. Such an approach is also easily operationalized for real-world content moderation as it has an efficient and scalable design.

arXiv:2103.12057공식 코드 · Papers with Code

An Experimental Review on Deep Learning Architectures for Time Series Forecasting

In recent years, deep learning techniques have outperformed traditional models in many machine learning tasks. Deep neural networks have successfully been applied to address time series forecasting problems, which is a very important topic in data mining. They have proved to be an effective solution given their capacity to automatically learn the temporal dependencies present in time series. However, selecting the most convenient type of deep neural network and its parametrization is a complex task that requires considerable expertise. Therefore, there is a need for deeper studies on the suitability of all existing architectures for different forecasting tasks. In this work, we face two main challenges: a comprehensive review of the latest works using deep learning for time series forecasting; and an experimental study comparing the performance of the most popular architectures. The comparison involves a thorough analysis of seven types of deep learning models in terms of accuracy and efficiency. We evaluate the rankings and distribution of results obtained with the proposed models under many different architecture configurations and training hyperparameters. The datasets used comprise more than 50000 time series divided into 12 different forecasting problems. By training more than 38000 models on these data, we provide the most extensive deep learning study for time series forecasting. Among all studied models, the results show that long short-term memory (LSTM) and convolutional networks (CNN) are the best alternatives, with LSTMs obtaining the most accurate forecasts. CNNs achieve comparable performance with less variability of results under different parameter configurations, while also being more efficient.

arXiv:2103.11895

Deep learning on fundus images detects glaucoma beyond the optic disc

Although unprecedented sensitivity and specificity values are reported, recent glaucoma detection deep learning models lack in decision transparency. Here, we propose a methodology that advances explainable deep learning in the field of glaucoma detection and vertical cup-disc ratio (VCDR), an important risk factor. We trained and evaluated deep learning models using fundus images that underwent a certain cropping policy. We defined the crop radius as a percentage of image size, centered on the optic nerve head (ONH), with an equidistant spaced range from 10%-60% (ONH crop policy). The inverse of the cropping mask was also applied (periphery crop policy). Trained models using original images resulted in an area under the curve (AUC) of 0.94 [95% CI: 0.92-0.96] for glaucoma detection, and a coefficient of determination (R^2) equal to 77% [95% CI: 0.77-0.79] for VCDR estimation. Models that were trained on images with absence of the ONH are still able to obtain significant performance (0.88 [95% CI: 0.85-0.90] AUC for glaucoma detection and 37% [95% CI: 0.35-0.40] R^2 score for VCDR estimation in the most extreme setup of 60% ONH crop). Our findings provide the first irrefutable evidence that deep learning can detect glaucoma from fundus image regions outside the ONH.

arXiv:2103.10492

Recent Advances in Deep Learning Techniques for Face Recognition

In recent years, researchers have proposed many deep learning (DL) methods for various tasks, and particularly face recognition (FR) made an enormous leap using these techniques. Deep FR systems benefit from the hierarchical architecture of the DL methods to learn discriminative face representation. Therefore, DL techniques significantly improve state-of-the-art performance on FR systems and encourage diverse and efficient real-world applications. In this paper, we present a comprehensive analysis of various FR systems that leverage the different types of DL techniques, and for the study, we summarize 168 recent contributions from this area. We discuss the papers related to different algorithms, architectures, loss functions, activation functions, datasets, challenges, improvement ideas, current and future trends of DL-based FR systems. We provide a detailed discussion of various DL methods to understand the current state-of-the-art, and then we discuss various activation and loss functions for the methods. Additionally, we summarize different datasets used widely for FR tasks and discuss challenges related to illumination, expression, pose variations, and occlusion. Finally, we discuss improvement ideas, current and future trends of FR tasks.

논문 ID: 2020.00244

Brain Morphometry Estimation: From Hours to Seconds Using Deep Learning

Motivation: Brain morphometry from magnetic resonance imaging (MRI) is a promising neuroimaging biomarker for the non-invasive diagnosis and monitoring of neurodegenerative and neurological disorders. Current tools for brain morphometry often come with a high computational burden, making them hard to use in clinical routine, where time is often an issue. We propose a deep learning-based approach to predict the volumes of anatomically delineated subcortical regions of interest (ROI), and mean thicknesses and curvatures of cortical parcellations directly from T1-weighted MRI. Advantages are the timely availability of results while maintaining a clinically relevant accuracy. Materials and Methods: An anonymized dataset of 574 subjects (443 healthy controls and 131 patients with epilepsy) was used for the supervised training of a convolutional neural network (CNN). A silver-standard ground truth was generated with FreeSurfer 6.0. Results: The CNN predicts a total of 165 morphometric measures directly from raw MR images. Analysis of the results using intraclass correlation coefficients showed, in general, good correlation with FreeSurfer generated ground truth data, with some of the regions nearly reaching human inter-rater performance (ICC > 0.75). Cortical thicknesses predicted by the CNN showed cross-sectional annual age-related gray matter atrophy rates both globally (thickness change of −0.004 mm/year) and regionally in agreement with the literature. A statistical test to dichotomize patients with epilepsy from healthy controls revealed similar effect sizes for structures affecting all subtypes as reported in a large-scale epilepsy study. Conclusions: We demonstrate the general feasibility of using deep learning to estimate human brain morphometry directly from T1-weighted MRI within seconds. A comparison of the results to other publications shows accuracies of comparable magnitudes for the subcortical volumes and cortical thicknesses.

arXiv:2103.10689공식 코드 · Papers with Code

Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction results of deep models. In recent years, many interpretation tools have been proposed to explain or reveal how deep models make decisions. In this paper, we review this line of research and try to make a comprehensive survey. Specifically, we first introduce and clarify two basic concepts -- interpretations and interpretability -- that people usually get confused about. To address the research efforts in interpretations, we elaborate the designs of a number of interpretation algorithms, from different perspectives, by proposing a new taxonomy. Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms. Further, we summarize the current works in evaluating models' interpretability using "trustworthy" interpretation algorithms. Finally, we review and discuss the connections between deep models' interpretations and other factors, such as adversarial robustness and learning from interpretations, and we introduce several open-source libraries for interpretation algorithms and evaluation approaches.

arXiv:2103.10928

BERTSurv: BERT-Based Survival Models for Predicting Outcomes of Trauma Patients

Survival analysis is a technique to predict the times of specific outcomes, and is widely used in predicting the outcomes for intensive care unit (ICU) trauma patients. Recently, deep learning models have drawn increasing attention in healthcare. However, there is a lack of deep learning methods that can model the relationship between measurements, clinical notes and mortality outcomes. In this paper we introduce BERTSurv, a deep learning survival framework which applies Bidirectional Encoder Representations from Transformers (BERT) as a language representation model on unstructured clinical notes, for mortality prediction and survival analysis. We also incorporate clinical measurements in BERTSurv. With binary cross-entropy (BCE) loss, BERTSurv can predict mortality as a binary outcome (mortality prediction). With partial log-likelihood (PLL) loss, BERTSurv predicts the probability of mortality as a time-to-event outcome (survival analysis). We apply BERTSurv on Medical Information Mart for Intensive Care III (MIMIC III) trauma patient data. For mortality prediction, BERTSurv obtained an area under the curve of receiver operating characteristic curve (AUC-ROC) of 0.86, which is an improvement of 3.6% over baseline of multilayer perceptron (MLP) without notes. For survival analysis, BERTSurv achieved a concordance index (C-index) of 0.7. In addition, visualizations of BERT's attention heads help to extract patterns in clinical notes and improve model interpretability by showing how the model assigns weights to different inputs.

arXiv:2103.10911

Performance Analysis of Deep Learning Workloads on a Composable System

A composable infrastructure is defined as resources, such as compute, storage, accelerators and networking, that are shared in a pool and that can be grouped in various configurations to meet application requirements. This freedom to 'mix and match' resources dynamically allows for experimentation early in the design cycle, prior to the final architectural design or hardware implementation of a system. This design provides flexibility to serve a variety of workloads and provides a dynamic co-design platform that allows experiments and measurements in a controlled manner. For instance, key performance bottlenecks can be revealed early on in the experimentation phase thus avoiding costly and time consuming mistakes. Additionally, various system-level topologies can be evaluated when experimenting with new System on Chip (SoCs) and new accelerator types. This paper details the design of an enterprise composable infrastructure that we have implemented and made available to our partners in the IBM Research AI Hardware Center (AIHC). Our experimental evaluations on the composable system give insights into how the system works and evaluates the impact of various resource aggregations and reconfigurations on representative deep learning benchmarks.

arXiv:2103.09985

A deep learning theory for neural networks grounded in physics

In the last decade, deep learning has become a major component of artificial intelligence. The workhorse of deep learning is the optimization of loss functions by stochastic gradient descent (SGD). Traditionally in deep learning, neural networks are differentiable mathematical functions, and the loss gradients required for SGD are computed with the backpropagation algorithm. However, the computer architectures on which these neural networks are implemented and trained suffer from speed and energy inefficiency issues, due to the separation of memory and processing in these architectures. To solve these problems, the field of neuromorphic computing aims at implementing neural networks on hardware architectures that merge memory and processing, just like brains do. In this thesis, we argue that building large, fast and efficient neural networks on neuromorphic architectures also requires rethinking the algorithms to implement and train them. We present an alternative mathematical framework, also compatible with SGD, which offers the possibility to design neural networks in substrates that directly exploit the laws of physics. Our framework applies to a very broad class of models, namely those whose state or dynamics are described by variational equations. This includes physical systems whose equilibrium state minimizes an energy function, and physical systems whose trajectory minimizes an action functional. We present a simple procedure to compute the loss gradients in such systems, called equilibrium propagation (EqProp), which requires solely locally available information for each trainable parameter. Since many models in physics and engineering can be described by variational principles, our framework has the potential to be applied to a broad variety of physical systems whose applications extend to various fields of engineering, beyond neuromorphic computing.

arXiv:2103.10142

Reduced Precision Strategies for Deep Learning: A High Energy Physics Generative Adversarial Network Use Case

Deep learning is finding its way into high energy physics by replacing traditional Monte Carlo simulations. However, deep learning still requires an excessive amount of computational resources. A promising approach to make deep learning more efficient is to quantize the parameters of the neural networks to reduced precision. Reduced precision computing is extensively used in modern deep learning and results to lower execution inference time, smaller memory footprint and less memory bandwidth. In this paper we analyse the effects of low precision inference on a complex deep generative adversarial network model. The use case which we are addressing is calorimeter detector simulations of subatomic particle interactions in accelerator based high energy physics. We employ the novel Intel low precision optimization tool (iLoT) for quantization and compare the results to the quantized model from TensorFlow Lite. In the performance benchmark we gain a speed-up of 1.73x on Intel hardware for the quantized iLoT model compared to the initial, not quantized, model. With different physics-inspired self-developed metrics, we validate that the quantized iLoT model shows a lower loss of physical accuracy in comparison to the TensorFlow Lite model.