PyTorchKR Papers

최신 논문

총 3,318편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2001.09382공식 코드 · Papers with Code

GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention. The problem is challenging since it requires not only generating chemically valid molecular structures but also optimizing their chemical properties in the meantime. Inspired by the recent progress in deep generative models, in this paper we propose a flow-based autoregressive model for graph generation called GraphAF. GraphAF combines the advantages of both autoregressive and flow-based approaches and enjoys: (1) high model flexibility for data density estimation; (2) efficient parallel computation for training; (3) an iterative sampling process, which allows leveraging chemical domain knowledge for valency checking. Experimental results show that GraphAF is able to generate 68% chemically valid molecules even without chemical knowledge rules and 100% valid molecules with chemical rules. The training process of GraphAF is two times faster than the existing state-of-the-art approach GCPN. After fine-tuning the model for goal-directed property optimization with reinforcement learning, GraphAF achieves state-of-the-art performance on both chemical property optimization and constrained property optimization.

arXiv:1106.6251

Kernels for Vector-Valued Functions: a Review

Kernel methods are among the most popular techniques in machine learning. From a frequentist/discriminative perspective they play a central role in regularization theory as they provide a natural choice for the hypotheses space and the regularization functional through the notion of reproducing kernel Hilbert spaces. From a Bayesian/generative perspective they are the key in the context of Gaussian processes, where the kernel function is also known as the covariance function. Traditionally, kernel methods have been used in supervised learning problem with scalar outputs and indeed there has been a considerable amount of work devoted to designing and learning kernels. More recently there has been an increasing interest in methods that deal with multiple outputs, motivated partly by frameworks like multitask learning. In this paper, we review different methods to design or learn valid kernel functions for multiple outputs, paying particular attention to the connection between probabilistic and functional methods.

arXiv:2001.07861

Optimal estimation of sparse topic models

Topic models have become popular tools for dimension reduction and exploratory analysis of text data which consists in observed frequencies of a vocabulary of $p$ words in $n$ documents, stored in a $p\times n$ matrix. The main premise is that the mean of this data matrix can be factorized into a product of two non-negative matrices: a $p\times K$ word-topic matrix $A$ and a $K\times n$ topic-document matrix $W$. This paper studies the estimation of $A$ that is possibly element-wise sparse, and the number of topics $K$ is unknown. In this under-explored context, we derive a new minimax lower bound for the estimation of such $A$ and propose a new computationally efficient algorithm for its recovery. We derive a finite sample upper bound for our estimator, and show that it matches the minimax lower bound in many scenarios. Our estimate adapts to the unknown sparsity of $A$ and our analysis is valid for any finite $n$, $p$, $K$ and document lengths. Empirical results on both synthetic data and semi-synthetic data show that our proposed estimator is a strong competitor of the existing state-of-the-art algorithms for both non-sparse $A$ and sparse $A$, and has superior performance is many scenarios of interest.

arXiv:2001.07243

Autocamera Calibration for traffic surveillance cameras with wide angle lenses

We propose a method for automatic calibration of a traffic surveillance camera with wide-angle lenses. Video footage of a few minutes is sufficient for the entire calibration process to take place. This method takes in the height of the camera from the ground plane as the only user input to overcome the scale ambiguity. The calibration is performed in two stages, 1. Intrinsic Calibration 2. Extrinsic Calibration. Intrinsic calibration is achieved by assuming an equidistant fisheye distortion and an ideal camera model. Extrinsic calibration is accomplished by estimating the two vanishing points, on the ground plane, from the motion of vehicles at perpendicular intersections. The first stage of intrinsic calibration is also valid for thermal cameras. Experiments have been conducted to demonstrate the effectiveness of this approach on visible as well as thermal cameras. Index Terms: fish-eye, calibration, thermal camera, intelligent transportation systems, vanishing points

arXiv:2001.06678

Evolutionary Neural Architecture Search for Retinal Vessel Segmentation

The accurate retinal vessel segmentation (RVS) is of great significance to assist doctors in the diagnosis of ophthalmology diseases and other systemic diseases. Manually designing a valid neural network architecture for retinal vessel segmentation requires high expertise and a large workload. In order to improve the performance of vessel segmentation and reduce the workload of manually designing neural network, we propose novel approach which applies neural architecture search (NAS) to optimize an encoder-decoder architecture for retinal vessel segmentation. A modified evolutionary algorithm is used to evolve the architectures of encoder-decoder framework with limited computing resources. The evolved model obtained by the proposed approach achieves top performance among all compared methods on the three datasets, namely DRIVE, STARE and CHASE_DB1, but with much fewer parameters. Moreover, the results of cross-training show that the evolved model is with considerable scalability, which indicates a great potential for clinical disease diagnosis.

arXiv:2001.06725

Effects of sparse rewards of different magnitudes in the speed of learning of model-based actor critic methods

Actor critic methods with sparse rewards in model-based deep reinforcement learning typically require a deterministic binary reward function that reflects only two possible outcomes: if, for each step, the goal has been achieved or not. Our hypothesis is that we can influence an agent to learn faster by applying an external environmental pressure during training, which adversely impacts its ability to get higher rewards. As such, we deviate from the classical paradigm of sparse rewards and add a uniformly sampled reward value to the baseline reward to show that (1) sample efficiency of the training process can be correlated to the adversity experienced during training, (2) it is possible to achieve higher performance in less time and with less resources, (3) we can reduce the performance variability experienced seed over seed, (4) there is a maximum point after which more pressure will not generate better results, and (5) that random positive incentives have an adverse effect when using a negative reward strategy, making an agent under those conditions learn poorly and more slowly. These results have been shown to be valid for Deep Deterministic Policy Gradients using Hindsight Experience Replay in a well known Mujoco environment, but we argue that they could be generalized to other methods and environments as well.

arXiv:2001.05862

An Investigation of Feature-based Nonrigid Image Registration using Gaussian Process

For a wide range of clinical applications, such as adaptive treatment planning or intraoperative image update, feature-based deformable registration (FDR) approaches are widely employed because of their simplicity and low computational complexity. FDR algorithms estimate a dense displacement field by interpolating a sparse field, which is given by the established correspondence between selected features. In this paper, we consider the deformation field as a Gaussian Process (GP), whereas the selected features are regarded as prior information on the valid deformations. Using GP, we are able to estimate the both dense displacement field and a corresponding uncertainty map at once. Furthermore, we evaluated the performance of different hyperparameter settings for squared exponential kernels with synthetic, phantom and clinical data respectively. The quantitative comparison shows, GP-based interpolation has performance on par with state-of-the-art B-spline interpolation. The greatest clinical benefit of GP-based interpolation is that it gives a reliable estimate of the mathematical uncertainty of the calculated dense displacement map.

arXiv:2001.05650

Control of the Final-Phase of Closed-Loop Visual Grasping using Image-Based Visual Servoing

This paper considers the final approach phase of visual-closed-loop grasping where the RGB-D camera is no longer able to provide valid depth information. Many current robotic grasping controllers are not closed-loop and therefore fail for moving objects. Closed-loop grasp controllers based on RGB-D imagery can track a moving object, but fail when the sensor's minimum object distance is violated just before grasping. To overcome this we propose the use of image-based visual servoing (IBVS) to guide the robot to the object-relative grasp pose using camera RGB information. IBVS robustly moves the camera to a goal pose defined implicitly in terms of an image-plane feature configuration. In this work, the goal image feature coordinates are predicted from RGB-D data to enable RGB-only tracking once depth data becomes unavailable -- this enables more reliable grasping of previously unseen moving objects. Experimental results are provided.

arXiv:2001.05513

Optimal rates for independence testing via $U$-statistic permutation tests

We study the problem of independence testing given independent and identically distributed pairs taking values in a $\sigma$-finite, separable measure space. Defining a natural measure of dependence $D(f)$ as the squared $L^2$-distance between a joint density $f$ and the product of its marginals, we first show that there is no valid test of independence that is uniformly consistent against alternatives of the form $\{f: D(f) \geq \rho^2 \}$. We therefore restrict attention to alternatives that impose additional Sobolev-type smoothness constraints, and define a permutation test based on a basis expansion and a $U$-statistic estimator of $D(f)$ that we prove is minimax optimal in terms of its separation rates in many instances. Finally, for the case of a Fourier basis on $[0,1]^2$, we provide an approximation to the power function that offers several additional insights. Our methodology is implemented in the R package USP.

arXiv:2001.05285

Detecting New Word Meanings: A Comparison of Word Embedding Models in Spanish

Semantic neologisms (SN) are defined as words that acquire a new word meaning while maintaining their form. Given the nature of this kind of neologisms, the task of identifying these new word meanings is currently performed manually by specialists at observatories of neology. To detect SN in a semi-automatic way, we developed a system that implements a combination of the following strategies: topic modeling, keyword extraction, and word sense disambiguation. The role of topic modeling is to detect the themes that are treated in the input text. Themes within a text give clues about the particular meaning of the words that are used, for example: viral has one meaning in the context of computer science (CS) and another when talking about health. To extract keywords, we used TextRank with POS tag filtering. With this method, we can obtain relevant words that are already part of the Spanish lexicon. We use a deep learning model to determine if a given keyword could have a new meaning. Embeddings that are different from all the known meanings (or topics) indicate that a word might be a valid SN candidate. In this study, we examine the following word embedding models: Word2Vec, Sense2Vec, and FastText. The models were trained with equivalent parameters using Wikipedia in Spanish as corpora. Then we used a list of words and their concordances (obtained from our database of neologisms) to show the different embeddings that each model yields. Finally, we present a comparison of these outcomes with the concordances of each word to show how we can determine if a word could be a valid candidate for SN.

arXiv:2001.05363

Doubly Sparse Variational Gaussian Processes

The use of Gaussian process models is typically limited to datasets with a few tens of thousands of observations due to their complexity and memory footprint. The two most commonly used methods to overcome this limitation are 1) the variational sparse approximation which relies on inducing points and 2) the state-space equivalent formulation of Gaussian processes which can be seen as exploiting some sparsity in the precision matrix. We propose to take the best of both worlds: we show that the inducing point framework is still valid for state space models and that it can bring further computational and memory savings. Furthermore, we provide the natural gradient formulation for the proposed variational parameterisation. Finally, this work makes it possible to use the state-space formulation inside deep Gaussian process models as illustrated in one of the experiments.

arXiv:2001.05267

Correcting Decalibration of Stereo Cameras in Self-Driving Vehicles

We address the problem of optical decalibration in mobile stereo camera setups, especially in context of autonomous vehicles. In real world conditions, an optical system is subject to various sources of anticipated and unanticipated mechanical stress (vibration, rough handling, collisions). Mechanical stress changes the geometry between the cameras that make up the stereo pair, and as a consequence, the pre-calculated epipolar geometry is no longer valid. Our method is based on optimization of camera geometry parameters and plugs directly into the output of the stereo matching algorithm. Therefore, it is able to recover calibration parameters on image pairs obtained from a decalibrated stereo system with minimal use of additional computing resources. The number of successfully recovered depth pixels is used as an objective function, which we aim to maximize. Our simulation confirms that the method can run constantly in parallel to stereo estimation and thus help keep the system calibrated in real time. Results confirm that the method is able to recalibrate all the parameters except for the baseline distance, which scales the absolute depth readings. However, that scaling factor could be uniquely determined using any kind of absolute range finding methods (e.g. a single beam time-of-flight sensor).

arXiv:2001.04107공식 코드 · Papers with Code

Montage: A Neural Network Language Model-Guided JavaScript Engine Fuzzer

JavaScript (JS) engine vulnerabilities pose significant security threats affecting billions of web browsers. While fuzzing is a prevalent technique for finding such vulnerabilities, there have been few studies that leverage the recent advances in neural network language models (NNLMs). In this paper, we present Montage, the first NNLM-guided fuzzer for finding JS engine vulnerabilities. The key aspect of our technique is to transform a JS abstract syntax tree (AST) into a sequence of AST subtrees that can directly train prevailing NNLMs. We demonstrate that Montage is capable of generating valid JS tests, and show that it outperforms previous studies in terms of finding vulnerabilities. Montage found 37 real-world bugs, including three CVEs, in the latest JS engines, demonstrating its efficacy in finding JS engine bugs.

arXiv:2001.04170

Joint Reasoning for Multi-Faceted Commonsense Knowledge

Commonsense knowledge (CSK) supports a variety of AI applications, from visual understanding to chatbots. Prior works on acquiring CSK, such as ConceptNet, have compiled statements that associate concepts, like everyday objects or activities, with properties that hold for most or some instances of the concept. Each concept is treated in isolation from other concepts, and the only quantitative measure (or ranking) of properties is a confidence score that the statement is valid. This paper aims to overcome these limitations by introducing a multi-faceted model of CSK statements and methods for joint reasoning over sets of inter-related statements. Our model captures four different dimensions of CSK statements: plausibility, typicality, remarkability and salience, with scoring and ranking along each dimension. For example, hyenas drinking water is typical but not salient, whereas hyenas eating carcasses is salient. For reasoning and ranking, we develop a method with soft constraints, to couple the inference over concepts that are related in in a taxonomic hierarchy. The reasoning is cast into an integer linear programming (ILP), and we leverage the theory of reduction costs of a relaxed LP to compute informative rankings. This methodology is applied to several large CSK collections. Our evaluation shows that we can consolidate these inputs into much cleaner and more expressive knowledge. Results are available at https://dice.mpi-inf.mpg.de.

arXiv:2001.03813

Fundamental Limits of Prediction, Generalization, and Recursion: An Entropic-Innovations Perspective

In this paper, we examine the fundamental performance limits of prediction, with or without side information. More specifically, we derive generic lower bounds on the $\mathcal{L}_p$ norms of the prediction errors that are valid for any prediction algorithms and for any data distributions. Meanwhile, we combine the entropic analysis from information theory and the innovations approach from prediction/estimation theory to characterize the conditions (in terms of, e.g., directed information or mutual information) to achieve the bounds. We also investigate the implications of the results in analyzing the fundamental limits of generalization in fitting (learning) problems from the perspective of prediction with side information, as well as the fundamental limits of recursive algorithms by viewing them as generalized prediction problems.

arXiv:2001.03040

Deep Network Approximation for Smooth Functions

This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously. To that end, we first prove that multivariate polynomials can be approximated by deep ReLU networks of width $\mathcal{O}(N)$ and depth $\mathcal{O}(L)$ with an approximation error $\mathcal{O}(N^{-L})$. Through local Taylor expansions and their deep ReLU network approximations, we show that deep ReLU networks of width $\mathcal{O}(N\ln N)$ and depth $\mathcal{O}(L\ln L)$ can approximate $f\in C^s([0,1]^d)$ with a nearly optimal approximation error $\mathcal{O}(\|f\|_{C^s([0,1]^d)}N^{-2s/d}L^{-2s/d})$. Our estimate is non-asymptotic in the sense that it is valid for arbitrary width and depth specified by $N\in\mathbb{N}^+$ and $L\in\mathbb{N}^+$, respectively.

arXiv:2001.02610공식 코드 · Papers with Code

iDLG: Improved Deep Leakage from Gradients

It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recently, Zhu et al. presented an approach which shows the possibility to obtain private training data from the publicly shared gradients. In their Deep Leakage from Gradient (DLG) method, they synthesize the dummy data and corresponding labels with the supervision of shared gradients. However, DLG has difficulty in convergence and discovering the ground-truth labels consistently. In this paper, we find that sharing gradients definitely leaks the ground-truth labels. We propose a simple but reliable approach to extract accurate data from the gradients. Particularly, our approach can certainly extract the ground-truth labels as opposed to DLG, hence we name it Improved DLG (iDLG). Our approach is valid for any differentiable model trained with cross-entropy loss over one-hot labels. We mathematically illustrate how our method can extract ground-truth labels from the gradients and empirically demonstrate the advantages over DLG.

arXiv:2001.01095

High-Dimensional Independence Testing via Maximum and Average Distance Correlations

This paper investigates the utilization of maximum and average distance correlations for multivariate independence testing. We characterize their consistency properties in high-dimensional settings with respect to the number of marginally dependent dimensions, compare the advantages of each test statistic, examine their respective null distributions, and present a fast chi-square-based testing procedure. The resulting tests are non-parametric and applicable to both Euclidean distance and the Gaussian kernel as the underlying metric. To better understand the practical use cases of the proposed tests, we evaluate the empirical performance of the maximum distance correlation, average distance correlation, and the original distance correlation across various multivariate dependence scenarios, as well as conduct a real data experiment to test the presence of various cancer types and peptide levels in human plasma.

arXiv:2001.00927

A Probability Density Theory for Spin-Glass Systems

Spin-glass systems are universal models for representing many-body phenomena in statistical physics and computer science. High quality solutions of NP-hard combinatorial optimization problems can be encoded into low energy states of spin-glass systems. In general, evaluating the relevant physical and computational properties of such models is difficult due to critical slowing down near a phase transition. Ideally, one could use recent advances in deep learning for characterizing the low-energy properties of these complex systems. Unfortunately, many of the most promising machine learning approaches are only valid for distributions over continuous variables and thus cannot be directly applied to discrete spin-glass models. To this end, we develop a continuous probability density theory for spin-glass systems with arbitrary dimensions, interactions, and local fields. We show how our formulation geometrically encodes key physical and computational properties of the spin-glass in an instance-wise fashion without the need for quenched disorder averaging. We show that our approach is beyond the mean-field theory and identify a transition from a convex to non-convex energy landscape as the temperature is lowered past a critical temperature. We apply our formalism to a number of spin-glass models including the Sherrington-Kirkpatrick (SK) model, spins on random Erd\H{o}s-R\'enyi graphs, and random restricted Boltzmann machines.

arXiv:1912.13464

Model Inversion Networks for Model-Based Optimization

In this work, we aim to solve data-driven optimization problems, where the goal is to find an input that maximizes an unknown score function given access to a dataset of inputs with corresponding scores. When the inputs are high-dimensional and valid inputs constitute a small subset of this space (e.g., valid protein sequences or valid natural images), such model-based optimization problems become exceptionally difficult, since the optimizer must avoid out-of-distribution and invalid inputs. We propose to address such problem with model inversion networks (MINs), which learn an inverse mapping from scores to inputs. MINs can scale to high-dimensional input spaces and leverage offline logged data for both contextual and non-contextual optimization problems. MINs can also handle both purely offline data sources and active data collection. We evaluate MINs on tasks from the Bayesian optimization literature, high-dimensional model-based optimization problems over images and protein designs, and contextual bandit optimization from logged data.