PyTorchKR Papers

최신 논문

총 8,922편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2207.08023

Distance-Geometric Graph Attention Network (DG-GAT) for 3D Molecular Geometry

Deep learning for molecular science has so far mainly focused on 2D molecular graphs. Recently, however, there has been work to extend it to 3D molecular geometry, due to its scientific significance and critical importance in real-world applications. The 3D distance-geometric graph representation (DG-GR) adopts a unified scheme (distance) for representing the geometry of 3D graphs. It is invariant to rotation and translation of the graph, and it reflects pair-wise node interactions and their generally local nature, particularly relevant for 3D molecular geometry. To facilitate the incorporation of 3D molecular geometry in deep learning for molecular science, we adopt the new graph attention network with dynamic attention (GATv2) for use with DG-GR and propose the 3D distance-geometric graph attention network (DG-GAT). GATv2 is a great fit for DG-GR since the attention can vary by node and by distance between nodes. Experimental results of DG-GAT for the ESOL and FreeSolv datasets show major improvement (31% and 38%, respectively) over those of the standard graph convolution network based on 2D molecular graphs. The same is true for the QM9 dataset. Our work demonstrates the utility and value of DG-GAT for deep learning based on 3D molecular geometry.

arXiv:2207.08137

Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game

Adversarial deep learning is to train robust DNNs against adversarial attacks, which is one of the major research focuses of deep learning. Game theory has been used to answer some of the basic questions about adversarial deep learning such as the existence of a classifier with optimal robustness and the existence of optimal adversarial samples for a given class of classifiers. In most previous work, adversarial deep learning was formulated as a simultaneous game and the strategy spaces are assumed to be certain probability distributions in order for the Nash equilibrium to exist. But, this assumption is not applicable to the practical situation. In this paper, we give answers to these basic questions for the practical case where the classifiers are DNNs with a given structure, by formulating the adversarial deep learning as sequential games. The existence of Stackelberg equilibria for these games are proved. Furthermore, it is shown that the equilibrium DNN has the largest adversarial accuracy among all DNNs with the same structure, when Carlini-Wagner's margin loss is used. Trade-off between robustness and accuracy in adversarial deep learning is also studied from game theoretical aspect.

arXiv:2207.07859공식 코드 · Papers with Code

SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing

WiFi sensing has been evolving rapidly in recent years. Empowered by propagation models and deep learning methods, many challenging applications are realized such as WiFi-based human activity recognition and gesture recognition. However, in contrast to deep learning for visual recognition and natural language processing, no sufficiently comprehensive public benchmark exists. In this paper, we review the recent progress on deep learning enabled WiFi sensing, and then propose a benchmark, SenseFi, to study the effectiveness of various deep learning models for WiFi sensing. These advanced models are compared in terms of distinct sensing tasks, WiFi platforms, recognition accuracy, model size, computational complexity, feature transferability, and adaptability of unsupervised learning. It is also regarded as a tutorial for deep learning based WiFi sensing, starting from CSI hardware platform to sensing algorithms. The extensive experiments provide us with experiences in deep model design, learning strategy skills and training techniques for real-world applications. To the best of our knowledge, this is the first benchmark with an open-source library for deep learning in WiFi sensing research. The benchmark codes are available at https://github.com/xyanchen/WiFi-CSI-Sensing-Benchmark.

arXiv:2207.07753공식 코드 · Papers with Code

Do Not Sleep on Traditional Machine Learning: Simple and Interpretable Techniques Are Competitive to Deep Learning for Sleep Scoring

Over the last few years, research in automatic sleep scoring has mainly focused on developing increasingly complex deep learning architectures. However, recently these approaches achieved only marginal improvements, often at the expense of requiring more data and more expensive training procedures. Despite all these efforts and their satisfactory performance, automatic sleep staging solutions are not widely adopted in a clinical context yet. We argue that most deep learning solutions for sleep scoring are limited in their real-world applicability as they are hard to train, deploy, and reproduce. Moreover, these solutions lack interpretability and transparency, which are often key to increase adoption rates. In this work, we revisit the problem of sleep stage classification using classical machine learning. Results show that competitive performance can be achieved with a conventional machine learning pipeline consisting of preprocessing, feature extraction, and a simple machine learning model. In particular, we analyze the performance of a linear model and a non-linear (gradient boosting) model. Our approach surpasses state-of-the-art (that uses the same data) on two public datasets: Sleep-EDF SC-20 (MF1 0.810) and Sleep-EDF ST (MF1 0.795), while achieving competitive results on Sleep-EDF SC-78 (MF1 0.775) and MASS SS3 (MF1 0.817). We show that, for the sleep stage scoring task, the expressiveness of an engineered feature vector is on par with the internally learned representations of deep learning models. This observation opens the door to clinical adoption, as a representative feature vector allows to leverage both the interpretability and successful track record of traditional machine learning models.

arXiv:2207.07243

LineCap: Line Charts for Data Visualization Captioning Models

Data visualization captions help readers understand the purpose of a visualization and are crucial for individuals with visual impairments. The prevalence of poor figure captions and the successful application of deep learning approaches to image captioning motivate the use of similar techniques for automated figure captioning. However, research in this field has been stunted by the lack of suitable datasets. We introduce LineCap, a novel figure captioning dataset of 3,528 figures, and we provide insights from curating this dataset and using end-to-end deep learning models for automated figure captioning.

arXiv:2207.07241공식 코드 · Papers with Code

Classification of Bark Beetle-Induced Forest Tree Mortality using Deep Learning

Bark beetle outbreaks can dramatically impact forest ecosystems and services around the world. For the development of effective forest policies and management plans, the early detection of infested trees is essential. Despite the visual symptoms of bark beetle infestation, this task remains challenging, considering overlapping tree crowns and non-homogeneity in crown foliage discolouration. In this work, a deep learning based method is proposed to effectively classify different stages of bark beetle attacks at the individual tree level. The proposed method uses RetinaNet architecture (exploiting a robust feature extraction backbone pre-trained for tree crown detection) to train a shallow subnetwork for classifying the different attack stages of images captured by unmanned aerial vehicles (UAVs). Moreover, various data augmentation strategies are examined to address the class imbalance problem, and consequently, the affine transformation is selected to be the most effective one for this purpose. Experimental evaluations demonstrate the effectiveness of the proposed method by achieving an average accuracy of 98.95%, considerably outperforming the baseline method by approximately 10%.

arXiv:2207.06904

Attention mechanisms for physiological signal deep learning: which attention should we take?

Attention mechanisms are widely used to dramatically improve deep learning model performance in various fields. However, their general ability to improve the performance of physiological signal deep learning model is immature. In this study, we experimentally analyze four attention mechanisms (e.g., squeeze-and-excitation, non-local, convolutional block attention module, and multi-head self-attention) and three convolutional neural network (CNN) architectures (e.g., VGG, ResNet, and Inception) for two representative physiological signal prediction tasks: the classification for predicting hypotension and the regression for predicting cardiac output (CO). We evaluated multiple combinations for performance and convergence of physiological signal deep learning model. Accordingly, the CNN models with the spatial attention mechanism showed the best performance in the classification problem, whereas the channel attention mechanism achieved the lowest error in the regression problem. Moreover, the performance and convergence of the CNN models with attention mechanisms were better than stand-alone self-attention models in both problems. Hence, we verified that convolutional operation and attention mechanisms are complementary and provide faster convergence time, despite the stand-alone self-attention models requiring fewer parameters.

arXiv:2207.07012

AutoML-Based Drought Forecast with Meteorological Variables

A precise forecast for droughts is of considerable value to scientific research, agriculture, and water resource management. With emerging developments of data-driven approaches for hydro-climate modeling, this paper investigates an AutoML-based framework to forecast droughts in the U.S. Compared with commonly-used temporal deep learning models, the AutoML model can achieve comparable performance with less training data and time. As deep learning models are becoming popular for Earth system modeling, this paper aims to bring more efforts to AutoML-based methods, and the use of them as benchmark baselines for more complex deep learning models.

arXiv:2207.06678

Deep Learning Methods for Protein Family Classification on PDB Sequencing Data

Composed of amino acid chains that influence how they fold and thus dictating their function and features, proteins are a class of macromolecules that play a central role in major biological processes and are required for the structure, function, and regulation of the body's tissues. Understanding protein functions is vital to the development of therapeutics and precision medicine, and hence the ability to classify proteins and their functions based on measurable features is crucial; indeed, the automatic inference of a protein's properties from its sequence of amino acids, known as its primary structure, remains an important open problem within the field of bioinformatics, especially given the recent advancements in sequencing technologies and the extensive number of known but uncategorized proteins with unknown properties. In this work, we demonstrate and compare the performance of several deep learning frameworks, including novel bi-directional LSTM and convolutional models, on widely available sequencing data from the Protein Data Bank (PDB) of the Research Collaboratory for Structural Bioinformatics (RCSB), as well as benchmark this performance against classical machine learning approaches, including k-nearest neighbors and multinomial regression classifiers, trained on experimental data. Our results show that our deep learning models deliver superior performance to classical machine learning methods, with the convolutional architecture providing the most impressive inference performance.

arXiv:2207.06630

Identifying Orientation-specific Lipid-protein Fingerprints using Deep Learning

Improved understanding of the relation between the behavior of RAS and RAF proteins and the local lipid environment in the cell membrane is critical for getting insights into the mechanisms underlying cancer formation. In this work, we employ deep learning (DL) to learn this relationship by predicting protein orientational states of RAS and RAS-RAF protein complexes with respect to the lipid membrane based on the lipid densities around the protein domains from coarse-grained (CG) molecular dynamics (MD) simulations. Our DL model can predict six protein states with an overall accuracy of over 80%. The findings of this work offer new insights into how the proteins modulate the lipid environment, which in turn may assist designing novel therapies to regulate such interactions in the mechanisms associated with cancer development.

arXiv:2207.06746

Single-Pixel Image Reconstruction Based on Block Compressive Sensing and Deep Learning

Single-pixel imaging (SPI) is a novel imaging technique whose working principle is based on the compressive sensing (CS) theory. In SPI, data is obtained through a series of compressive measurements and the corresponding image is reconstructed. Typically, the reconstruction algorithm such as basis pursuit relies on the sparsity assumption in images. However, recent advances in deep learning have found its uses in reconstructing CS images. Despite showing a promising result in simulations, it is often unclear how such an algorithm can be implemented in an actual SPI setup. In this paper, we demonstrate the use of deep learning on the reconstruction of SPI images in conjunction with block compressive sensing (BCS). We also proposed a novel reconstruction model based on convolutional neural networks that outperforms other competitive CS reconstruction algorithms. Besides, by incorporating BCS in our deep learning model, we were able to reconstruct images of any size above a certain smallest image size. In addition, we show that our model is capable of reconstructing images obtained from an SPI setup while being priorly trained on natural images, which can be vastly different from the SPI images. This opens up opportunity for the feasibility of pretrained deep learning models for CS reconstructions of images from various domain areas.

arXiv:2207.06440

Graph CNN for Moving Object Detection in Complex Environments from Unseen Videos

Moving Object Detection (MOD) is a fundamental step for many computer vision applications. MOD becomes very challenging when a video sequence captured from a static or moving camera suffers from the challenges: camouflage, shadow, dynamic backgrounds, and lighting variations, to name a few. Deep learning methods have been successfully applied to address MOD with competitive performance. However, in order to handle the overfitting problem, deep learning methods require a large amount of labeled data which is a laborious task as exhaustive annotations are always not available. Moreover, some MOD deep learning methods show performance degradation in the presence of unseen video sequences because the testing and training splits of the same sequences are involved during the network learning process. In this work, we pose the problem of MOD as a node classification problem using Graph Convolutional Neural Networks (GCNNs). Our algorithm, dubbed as GraphMOD-Net, encompasses instance segmentation, background initialization, feature extraction, and graph construction. GraphMOD-Net is tested on unseen videos and outperforms state-of-the-art methods in unsupervised, semi-supervised, and supervised learning in several challenges of the Change Detection 2014 (CDNet2014) and UCSD background subtraction datasets.

arXiv:2207.06421

Deep Learning Discovery of Demographic Biomarkers in Echocardiography

Deep learning has been shown to accurately assess 'hidden' phenotypes and predict biomarkers from medical imaging beyond traditional clinician interpretation of medical imaging. Given the black box nature of artificial intelligence (AI) models, caution should be exercised in applying models to healthcare as prediction tasks might be short-cut by differences in demographics across disease and patient populations. Using large echocardiography datasets from two healthcare systems, we test whether it is possible to predict age, race, and sex from cardiac ultrasound images using deep learning algorithms and assess the impact of varying confounding variables. We trained video-based convolutional neural networks to predict age, sex, and race. We found that deep learning models were able to identify age and sex, while unable to reliably predict race. Without considering confounding differences between categories, the AI model predicted sex with an AUC of 0.85 (95% CI 0.84 - 0.86), age with a mean absolute error of 9.12 years (95% CI 9.00 - 9.25), and race with AUCs ranging from 0.63 - 0.71. When predicting race, we show that tuning the proportion of a confounding variable (sex) in the training data significantly impacts model AUC (ranging from 0.57 to 0.84), while in training a sex prediction model, tuning a confounder (race) did not substantially change AUC (0.81 - 0.83). This suggests a significant proportion of the model's performance on predicting race could come from confounding features being detected by AI. Further work remains to identify the particular imaging features that associate with demographic information and to better understand the risks of demographic identification in medical AI as it pertains to potentially perpetuating bias and disparities.

arXiv:2207.06415

The Free Energy Principle for Perception and Action: A Deep Learning Perspective

The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states of the world, i.e., they minimize their free energy. Under this principle, biological agents learn a generative model of the world and plan actions in the future that will maintain the agent in an homeostatic state that satisfies its preferences. This framework lends itself to being realized in silico, as it comprehends important aspects that make it computationally affordable, such as variational inference and amortized planning. In this work, we investigate the tool of deep learning to design and realize artificial agents based on active inference, presenting a deep-learning oriented presentation of the free energy principle, surveying works that are relevant in both machine learning and active inference areas, and discussing the design choices that are involved in the implementation process. This manuscript probes newer perspectives for the active inference framework, grounding its theoretical aspects into more pragmatic affairs, offering a practical guide to active inference newcomers and a starting point for deep learning practitioners that would like to investigate implementations of the free energy principle.

arXiv:2207.06873공식 코드 · Papers with Code

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

High-quality calibrated uncertainty estimates are crucial for numerous real-world applications, especially for deep learning-based deployed ML systems. While Bayesian deep learning techniques allow uncertainty estimation, training them with large-scale datasets is an expensive process that does not always yield models competitive with non-Bayesian counterparts. Moreover, many of the high-performing deep learning models that are already trained and deployed are non-Bayesian in nature and do not provide uncertainty estimates. To address these issues, we propose BayesCap that learns a Bayesian identity mapping for the frozen model, allowing uncertainty estimation. BayesCap is a memory-efficient method that can be trained on a small fraction of the original dataset, enhancing pretrained non-Bayesian computer vision models by providing calibrated uncertainty estimates for the predictions without (i) hampering the performance of the model and (ii) the need for expensive retraining the model from scratch. The proposed method is agnostic to various architectures and tasks. We show the efficacy of our method on a wide variety of tasks with a diverse set of architectures, including image super-resolution, deblurring, inpainting, and crucial application such as medical image translation. Moreover, we apply the derived uncertainty estimates to detect out-of-distribution samples in critical scenarios like depth estimation in autonomous driving. Code is available at https://github.com/ExplainableML/BayesCap.

arXiv:2207.06883

RF-Photonic Deep Learning Processor with Shannon-Limited Data Movement

Edholm's Law predicts exponential growth in data rate and spectrum bandwidth for communications and is forecasted to remain true for the upcoming deployment of 6G. Compounding this issue is the exponentially increasing demand for deep neural network (DNN) compute, including DNNs for signal processing. However, the slowing of Moore's Law due to the limitations of transistor-based electronics means that completely new paradigms for computing will be required to meet these increasing demands for advanced communications. Optical neural networks (ONNs) are promising DNN accelerators with ultra-low latency and energy consumption. Yet state-of-the-art ONNs struggle with scalability and implementing linear with in-line nonlinear operations. Here we introduce our multiplicative analog frequency transform ONN (MAFT-ONN) that encodes the data in the frequency domain, achieves matrix-vector products in a single shot using photoelectric multiplication, and uses a single electro-optic modulator for the nonlinear activation of all neurons in each layer. We experimentally demonstrate the first hardware accelerator that computes fully-analog deep learning on raw RF signals, performing single-shot modulation classification with 85% accuracy, where a 'majority vote' multi-measurement scheme can boost the accuracy to 95% within 5 consecutive measurements. In addition, we demonstrate frequency-domain finite impulse response (FIR) linear-time-invariant (LTI) operations, enabling a powerful combination of traditional and AI signal processing. We also demonstrate the scalability of our architecture by computing nearly 4 million fully-analog multiplies-and-accumulates for MNIST digit classification. Our latency estimation model shows that due to the Shannon capacity-limited analog data movement, MAFT-ONN is hundreds of times faster than traditional RF receivers operating at their theoretical peak performance.

arXiv:2207.06216공식 코드 · Papers with Code

Goal-Oriented Sensitivity Analysis of Hyperparameters in Deep Learning

Tackling new machine learning problems with neural networks always means optimizing numerous hyperparameters that define their structure and strongly impact their performances. In this work, we study the use of goal-oriented sensitivity analysis, based on the Hilbert-Schmidt Independence Criterion (HSIC), for hyperparameter analysis and optimization. Hyperparameters live in spaces that are often complex and awkward. They can be of different natures (categorical, discrete, boolean, continuous), interact, and have inter-dependencies. All this makes it non-trivial to perform classical sensitivity analysis. We alleviate these difficulties to obtain a robust analysis index that is able to quantify hyperparameters' relative impact on a neural network's final error. This valuable tool allows us to better understand hyperparameters and to make hyperparameter optimization more interpretable. We illustrate the benefits of this knowledge in the context of hyperparameter optimization and derive an HSIC-based optimization algorithm that we apply on MNIST and Cifar, classical machine learning data sets, but also on the approximation of Runge function and Bateman equations solution, of interest for scientific machine learning. This method yields neural networks that are both competitive and cost-effective.

arXiv:2207.06080공식 코드 · Papers with Code

Efficient Augmentation for Imbalanced Deep Learning

Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's internal representation of imbalanced image data and measure the generalization gap between a model's feature embeddings in the training and test sets, showing that the gap is wider for minority classes. This insight enables us to design an efficient three-phase CNN training framework for imbalanced data. The framework involves training the network end-to-end on imbalanced data to learn accurate feature embeddings, performing data augmentation in the learned embedded space to balance the train distribution, and fine-tuning the classifier head on the embedded balanced training data. We propose Expansive Over-Sampling (EOS) as a data augmentation technique to utilize in the training framework. EOS forms synthetic training instances as convex combinations between the minority class samples and their nearest enemies in the embedded space to reduce the generalization gap. The proposed framework improves the accuracy over leading cost-sensitive and resampling methods commonly used in imbalanced learning. Moreover, it is more computationally efficient than standard data pre-processing methods, such as SMOTE and GAN-based oversampling, as it requires fewer parameters and less training time.

arXiv:2207.05931

Towards understanding how momentum improves generalization in deep learning

Stochastic gradient descent (SGD) with momentum is widely used for training modern deep learning architectures. While it is well-understood that using momentum can lead to faster convergence rate in various settings, it has also been observed that momentum yields higher generalization. Prior work argue that momentum stabilizes the SGD noise during training and this leads to higher generalization. In this paper, we adopt another perspective and first empirically show that gradient descent with momentum (GD+M) significantly improves generalization compared to gradient descent (GD) in some deep learning problems. From this observation, we formally study how momentum improves generalization. We devise a binary classification setting where a one-hidden layer (over-parameterized) convolutional neural network trained with GD+M provably generalizes better than the same network trained with GD, when both algorithms are similarly initialized. The key insight in our analysis is that momentum is beneficial in datasets where the examples share some feature but differ in their margin. Contrary to GD that memorizes the small margin data, GD+M still learns the feature in these data thanks to its historical gradients. Lastly, we empirically validate our theoretical findings.

arXiv:2207.05634공식 코드 · Papers with Code

GANzzle: Reframing jigsaw puzzle solving as a retrieval task using a generative mental image

Puzzle solving is a combinatorial challenge due to the difficulty of matching adjacent pieces. Instead, we infer a mental image from all pieces, which a given piece can then be matched against avoiding the combinatorial explosion. Exploiting advancements in Generative Adversarial methods, we learn how to reconstruct the image given a set of unordered pieces, allowing the model to learn a joint embedding space to match an encoding of each piece to the cropped layer of the generator. Therefore we frame the problem as a R@1 retrieval task, and then solve the linear assignment using differentiable Hungarian attention, making the process end-to-end. In doing so our model is puzzle size agnostic, in contrast to prior deep learning methods which are single size. We evaluate on two new large-scale datasets, where our model is on par with deep learning methods, while generalizing to multiple puzzle sizes.