April 3, 2020

3288 words 16 mins read

Paper Group ANR 34

Paper Group ANR 34

Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning. Mining International Political Norms from the GDELT Database. Predicting Performance of Asynchronous Differentially-Private Learning. SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints. Learning Dynamic and Personalized Comorbi …

Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning

Title Supporting DNN Safety Analysis and Retraining through Heatmap-based Unsupervised Learning
Authors Hazem Fahmy, Mojtaba Bagherzadeh, Fabrizio Pastore, Lionel Briand
Abstract Deep neural networks (DNNs) are increasingly critical in modern safety-critical systems, for example in their perception layer to analyze images. Unfortunately, there is a lack of methods to ensure the functional safety of DNN-based components. The machine learning literature suggests one should trust DNNs demonstrating high accuracy on test sets. In case of low accuracy, DNNs should be retrained using additional inputs similar to the error-inducing ones. We observe two major challenges with existing practices for safety-critical systems: (1) scenarios that are underrepresented in the test set may represent serious risks, which may lead to safety violations, and may not be noticed; (2) debugging DNNs is poorly supported when error causes are difficult to visually detect. To address these problems, we propose HUDD, an approach that automatically supports the identification of root causes for DNN errors. We automatically group error-inducing images whose results are due to common subsets of selected DNN neurons. HUDD identifies root causes by applying a clustering algorithm to matrices (i.e., heatmaps) capturing the relevance of every DNN neuron on the DNN outcome. Also, HUDD retrains DNNs with images that are automatically selected based on their relatedness to the identified image clusters. We have evaluated HUDD with DNNs from the automotive domain. The approach was able to automatically identify all the distinct root causes of DNN errors, thus supporting safety analysis. Also, our retraining approach has shown to be more effective at improving DNN accuracy than existing approaches.
Published 2020-02-03
URL https://arxiv.org/abs/2002.00863v1
PDF https://arxiv.org/pdf/2002.00863v1.pdf
PWC https://paperswithcode.com/paper/supporting-dnn-safety-analysis-and-retraining

Mining International Political Norms from the GDELT Database

Title Mining International Political Norms from the GDELT Database
Authors Rohit Murali, Suravi Patnaik, Stephen Cranefield
Abstract Researchers have long been interested in the role that norms can play in governing agent actions in multi-agent systems. Much work has been done on formalising normative concepts from human society and adapting them for the government of open software systems, and on the simulation of normative processes in human and artificial societies. However, there has been comparatively little work on applying normative MAS mechanisms to understanding the norms in human society. This work investigates this issue in the context of international politics. Using the GDELT dataset, containing machine-encoded records of international events extracted from news reports, we extracted bilateral sequences of inter-country events and applied a Bayesian norm mining mechanism to identify norms that best explained the observed behaviour. A statistical evaluation showed that the normative model fitted the data significantly better than a probabilistic discrete event model.
Published 2020-03-31
URL https://arxiv.org/abs/2003.14027v1
PDF https://arxiv.org/pdf/2003.14027v1.pdf
PWC https://paperswithcode.com/paper/mining-international-political-norms-from-the

Predicting Performance of Asynchronous Differentially-Private Learning

Title Predicting Performance of Asynchronous Differentially-Private Learning
Authors Farhad Farokhi, Mohamed Ali Kaafar
Abstract We consider training machine learning models using Training data located on multiple private and geographically-scattered servers with different privacy settings. Due to the distributed nature of the data, communicating with all collaborating private data owners simultaneously may prove challenging or altogether impossible. In this paper, we develop differentially-private asynchronous algorithms for collaboratively training machine-learning models on multiple private datasets. The asynchronous nature of the algorithms implies that a central learner interacts with the private data owners one-on-one whenever they are available for communication without needing to aggregate query responses to construct gradients of the entire fitness function. Therefore, the algorithm efficiently scales to many data owners. We define the cost of privacy as the difference between the fitness of a privacy-preserving machine-learning model and the fitness of trained machine-learning model in the absence of privacy concerns. We prove that we can forecast the performance of the proposed privacy-preserving asynchronous algorithms. We demonstrate that the cost of privacy has an upper bound that is inversely proportional to the combined size of the training datasets squared and the sum of the privacy budgets squared. We validate the theoretical results with experiments on financial and medical datasets. The experiments illustrate that collaboration among more than 10 data owners with at least 10,000 records with privacy budgets greater than or equal to 1 results in a superior machine-learning model in comparison to a model trained in isolation on only one of the datasets, illustrating the value of collaboration and the cost of the privacy. The number of the collaborating datasets can be lowered if the privacy budget is higher.
Published 2020-03-18
URL https://arxiv.org/abs/2003.08500v1
PDF https://arxiv.org/pdf/2003.08500v1.pdf
PWC https://paperswithcode.com/paper/predicting-performance-of-asynchronous

SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints

Title SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints
Authors Weikun Wu, Yan Zhang, David Wang, Yunqi Lei
Abstract Since the PointNet was proposed, deep learning on point cloud has been the concentration of intense 3D research. However, existing point-based methods usually are not adequate to extract the local features and the spatial pattern of a point cloud for further shape understanding. This paper presents an end-to-end framework, SK-Net, to jointly optimize the inference of spatial keypoint with the learning of feature representation of a point cloud for a specific point cloud task. One key process of SK-Net is the generation of spatial keypoints (Skeypoints). It is jointly conducted by two proposed regulating losses and a task objective function without knowledge of Skeypoint location annotations and proposals. Specifically, our Skeypoints are not sensitive to the location consistency but are acutely aware of shape. Another key process of SK-Net is the extraction of the local structure of Skeypoints (detail feature) and the local spatial pattern of normalized Skeypoints (pattern feature). This process generates a comprehensive representation, pattern-detail (PD) feature, which comprises the local detail information of a point cloud and reveals its spatial pattern through the part district reconstruction on normalized Skeypoints. Consequently, our network is prompted to effectively understand the correlation between different regions of a point cloud and integrate contextual information of the point cloud. In point cloud tasks, such as classification and segmentation, our proposed method performs better than or comparable with the state-of-the-art approaches. We also present an ablation study to demonstrate the advantages of SK-Net.
Published 2020-03-31
URL https://arxiv.org/abs/2003.14014v1
PDF https://arxiv.org/pdf/2003.14014v1.pdf
PWC https://paperswithcode.com/paper/sk-net-deep-learning-on-point-cloud-via-end

Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes

Title Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes
Authors Zhaozhi Qian, Ahmed M. Alaa, Alexis Bellot, Jem Rashbass, Mihaela van der Schaar
Abstract Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic health records we can observe the different diseases a patient has, but can only infer the temporal relationship between each co-morbid condition. Learning such temporal patterns from event data is crucial for understanding disease pathology and predicting prognoses. To this end, we develop deep diffusion processes (DDP) to model “dynamic comorbidity networks”, i.e., the temporal relationships between comorbid disease onsets expressed through a dynamic graph. A DDP comprises events modelled as a multi-dimensional point process, with an intensity function parameterized by the edges of a dynamic weighted graph. The graph structure is modulated by a neural network that maps patient history to edge weights, enabling rich temporal representations for disease trajectories. The DDP parameters decouple into clinically meaningful components, which enables serving the dual purpose of accurate risk prediction and intelligible representation of disease pathology. We illustrate these features in experiments using cancer registry data.
Published 2020-01-08
URL https://arxiv.org/abs/2001.02585v2
PDF https://arxiv.org/pdf/2001.02585v2.pdf
PWC https://paperswithcode.com/paper/learning-dynamic-and-personalized-comorbidity

Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention

Title Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention
Authors Yuma Koizumi, Kohei Yatabe, Marc Delcroix, Yoshiki Masuyama, Daiki Takeuchi
Abstract This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features; we extract a speaker representation used for adaptation directly from the test utterance. Conventional studies of deep neural network (DNN)–based speech enhancement mainly focus on building a speaker independent model. Meanwhile, in speech applications including speech recognition and synthesis, it is known that model adaptation to the target speaker improves the accuracy. Our research question is whether a DNN for speech enhancement can be adopted to unknown speakers without any auxiliary guidance signal in test-phase. To achieve this, we adopt multi-task learning of speech enhancement and speaker identification, and use the output of the final hidden layer of speaker identification branch as an auxiliary feature. In addition, we use multi-head self-attention for capturing long-term dependencies in the speech and noise. Experimental results on a public dataset show that our strategy achieves the state-of-the-art performance and also outperform conventional methods in terms of subjective quality.
Tasks Multi-Task Learning, Speaker Identification, Speech Enhancement, Speech Recognition
Published 2020-02-14
URL https://arxiv.org/abs/2002.05873v1
PDF https://arxiv.org/pdf/2002.05873v1.pdf
PWC https://paperswithcode.com/paper/speech-enhancement-using-self-adaptation-and

VOR Adaptation on a Humanoid iCub Robot Using a Spiking Cerebellar Model

Title VOR Adaptation on a Humanoid iCub Robot Using a Spiking Cerebellar Model
Authors Francisco Naveros, Niceto R. Luque, Eduardo Ros, Angelo Arleo
Abstract We embed a spiking cerebellar model within an adaptive real-time (RT) control loop that is able to operate a real robotic body (iCub) when performing different vestibulo-ocular reflex (VOR) tasks. The spiking neural network computation, including event- and time-driven neural dynamics, neural activity, and spike-timing dependent plasticity (STDP) mechanisms, leads to a nondeterministic computation time caused by the neural activity volleys encountered during cerebellar simulation. This nondeterministic computation time motivates the integration of an RT supervisor module that is able to ensure a well-orchestrated neural computation time and robot operation. Actually, our neurorobotic experimental setup (VOR) benefits from the biological sensory motor delay between the cerebellum and the body to buffer the computational overloads as well as providing flexibility in adjusting the neural computation time and RT operation. The RT supervisor module provides for incremental countermeasures that dynamically slow down or speed up the cerebellar simulation by either halting the simulation or disabling certain neural computation features (i.e., STDP mechanisms, spike propagation, and neural updates) to cope with the RT constraints imposed by the real robot operation. This neurorobotic experimental setup is applied to different horizontal and vertical VOR adaptive tasks that are widely used by the neuroscientific community to address cerebellar functioning. We aim to elucidate the manner in which the combination of the cerebellar neural substrate and the distributed plasticity shapes the cerebellar neural activity to mediate motor adaptation. This paper underlies the need for a two-stage learning process to facilitate VOR acquisition.
Published 2020-03-03
URL https://arxiv.org/abs/2003.01409v2
PDF https://arxiv.org/pdf/2003.01409v2.pdf
PWC https://paperswithcode.com/paper/vor-adaptation-on-a-humanoid-icub-robot-using

CPS: Class-level 6D Pose and Shape Estimation From Monocular Images

Title CPS: Class-level 6D Pose and Shape Estimation From Monocular Images
Authors Fabian Manhardt, Manuel Nickel, Sven Meier, Luca Minciullo, Nassir Navab
Abstract Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances. This naturally limits possible applications as, for instance, robots need to work with hundreds of different objects in a real environment. In this paper, we propose the first deep learning approach for class-wise monocular 6D pose estimation, coupled with metric shape retrieval. We propose a new loss formulation which directly optimizes over all parameters, i.e. 3D orientation, translation, scale and shape at the same time. Instead of decoupling each parameter, we transform the regressed shape, in the form of a point cloud, to 3D and directly measure its metric misalignment. We experimentally demonstrate that we can retrieve precise metric point clouds from a single image, which can also be further processed for e.g. subsequent rendering. Moreover, we show that our new 3D point cloud loss outperforms all baselines and gives overall good results despite the inherent ambiguity due to monocular data.
Tasks 6D Pose Estimation, Pose Estimation
Published 2020-03-12
URL https://arxiv.org/abs/2003.05848v2
PDF https://arxiv.org/pdf/2003.05848v2.pdf
PWC https://paperswithcode.com/paper/cps-class-level-6d-pose-and-shape-estimation

Object 6D Pose Estimation with Non-local Attention

Title Object 6D Pose Estimation with Non-local Attention
Authors Jianhan Mei, Henghui Ding, Xudong Jiang
Abstract In this paper, we address the challenging task of estimating 6D object pose from a single RGB image. Motivated by the deep learning based object detection methods, we propose a concise and efficient network that integrate 6D object pose parameter estimation into the object detection framework. Furthermore, for more robust estimation to occlusion, a non-local self-attention module is introduced. The experimental results show that the proposed method reaches the state-of-the-art performance on the YCB-video and the Linemod datasets.
Tasks 6D Pose Estimation, Object Detection, Pose Estimation
Published 2020-02-20
URL https://arxiv.org/abs/2002.08749v1
PDF https://arxiv.org/pdf/2002.08749v1.pdf
PWC https://paperswithcode.com/paper/object-6d-pose-estimation-with-non-local

A General Large Neighborhood Search Framework for Solving Integer Programs

Title A General Large Neighborhood Search Framework for Solving Integer Programs
Authors Jialin Song, Ravi Lanka, Yisong Yue, Bistra Dilkina
Abstract This paper studies how to design abstractions of large-scale combinatorial optimization problems that can leverage existing state-of-the-art solvers in general purpose ways, and that are amenable to data-driven design. The goal is to arrive at new approaches that can reliably outperform existing solvers in wall-clock time. We focus on solving integer programs, and ground our approach in the large neighborhood search (LNS) paradigm, which iteratively chooses a subset of variables to optimize while leaving the remainder fixed. The appeal of LNS is that it can easily use any existing solver as a subroutine, and thus can inherit the benefits of carefully engineered heuristic approaches and their software implementations. We also show that one can learn a good neighborhood selector from training data. Through an extensive empirical validation, we demonstrate that our LNS framework can significantly outperform, in wall-clock time, compared to state-of-the-art commercial solvers such as Gurobi.
Tasks Combinatorial Optimization
Published 2020-03-29
URL https://arxiv.org/abs/2004.00422v1
PDF https://arxiv.org/pdf/2004.00422v1.pdf
PWC https://paperswithcode.com/paper/a-general-large-neighborhood-search-framework

Deep semantic gaze embedding and scanpath comparison for expertise classification during OPT viewing

Title Deep semantic gaze embedding and scanpath comparison for expertise classification during OPT viewing
Authors Nora Castner, Thomas Kübler, Katharina Scheiter, Juilane Richter, Thérése Eder, Fabian Hüttig, Constanze Keutel, Enkelejda Kasneci
Abstract Modeling eye movement indicative of expertise behavior is decisive in user evaluation. However, it is indisputable that task semantics affect gaze behavior. We present a novel approach to gaze scanpath comparison that incorporates convolutional neural networks (CNN) to process scene information at the fixation level. Image patches linked to respective fixations are used as input for a CNN and the resulting feature vectors provide the temporal and spatial gaze information necessary for scanpath similarity comparison.We evaluated our proposed approach on gaze data from expert and novice dentists interpreting dental radiographs using a local alignment similarity score. Our approach was capable of distinguishing experts from novices with 93% accuracy while incorporating the image semantics. Moreover, our scanpath comparison using image patch features has the potential to incorporate task semantics from a variety of tasks
Published 2020-03-31
URL https://arxiv.org/abs/2003.13987v1
PDF https://arxiv.org/pdf/2003.13987v1.pdf
PWC https://paperswithcode.com/paper/deep-semantic-gaze-embedding-and-scanpath

DNN-Based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays

Title DNN-Based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays
Authors Nicolas Furnon, Romain Serizel, Irina Illina, Slim Essid
Abstract Multichannel processing is widely used for speech enhancement but several limitations appear when trying to deploy these solutions to the real-world. Distributed sensor arrays that consider several devices with a few microphones is a viable alternative that allows for exploiting the multiple devices equipped with microphones that we are using in our everyday life. In this context, we propose to extend the distributed adaptive node-specific signal estimation approach to a neural networks framework. At each node, a local filtering is performed to send one signal to the other nodes where a mask is estimated by a neural network in order to compute a global multi-channel Wiener filter. In an array of two nodes, we show that this additional signal can be efficiently taken into account to predict the masks and leads to better speech enhancement performances than when the mask estimation relies only on the local signals.
Tasks Speech Enhancement
Published 2020-02-13
URL https://arxiv.org/abs/2002.06016v2
PDF https://arxiv.org/pdf/2002.06016v2.pdf
PWC https://paperswithcode.com/paper/dnn-based-distributed-multichannel-mask

Eigen component analysis: A quantum theory incorporated machine learning technique to find linearly maximum separable components

Title Eigen component analysis: A quantum theory incorporated machine learning technique to find linearly maximum separable components
Authors Chen Miao, Shaohua Ma
Abstract For a linear system, the response to a stimulus is often superposed by its responses to other decomposed stimuli. In quantum mechanics, a state is the superposition of multiple eigenstates. Here, by taking advantage of the phase difference, a common feature as we identified in data sets, we propose eigen component analysis (ECA), an interpretable linear learning model that incorporates the principle of quantum mechanics into the design of algorithm design for feature extraction, classification, dictionary and deep learning, and adversarial generation, etc. The simulation of ECA, possessing a measurable $class\text{-}label$ $\mathcal{H}$, on a classical computer outperforms the existing classical linear models. Eigen component analysis network (ECAN), a network of contenated ECA models, enhances ECA and gains the potential to be not only integrated with nonlinear models, but also an interface for deep neural networks to implement on a quantum computer, by analogizing a data set as recordings of quantum states. Therefore, ECA and ECAN promise to expand the feasibility of linear learning models, by adopting the strategy of quantum machine learning to replace heavy nonlinear models with succinct linear operations in tackling complexity.
Tasks Quantum Machine Learning
Published 2020-03-23
URL https://arxiv.org/abs/2003.10199v2
PDF https://arxiv.org/pdf/2003.10199v2.pdf
PWC https://paperswithcode.com/paper/eigen-component-analysis-a-quantum-theory

An Automatic Attribute Based Access Control Policy Extraction from Access Logs

Title An Automatic Attribute Based Access Control Policy Extraction from Access Logs
Authors Leila Karimi, Maryam Aldairi, James Joshi, Mai Abdelhakim
Abstract With the rapid advances in computing and information technologies, traditional access control models have become inadequate in terms of capturing fine-grained, and expressive security requirements of newly emerging applications. An attribute-based access control (ABAC) model provides a more flexible approach for addressing the authorization needs of complex and dynamic systems. While organizations are interested in employing newer authorization models, migrating to such models pose as a significant challenge. Many large-scale businesses need to grant authorization to their user populations that are potentially distributed across disparate and heterogeneous computing environments. Each of these computing environments may have its own access control model. The manual development of a single policy framework for an entire organization is tedious, costly, and error-prone. In this paper, we present a methodology for automatically learning ABAC policy rules from access logs of a system to simplify the policy development process. The proposed approach employs an unsupervised learning-based algorithm for detecting patterns in access logs and extracting ABAC authorization rules from these patterns. In addition, we present two policy improvement algorithms, including rule pruning and policy refinement algorithms to generate a higher quality mined policy. Finally, we implement a prototype of the proposed approach to demonstrate its feasibility.
Published 2020-03-16
URL https://arxiv.org/abs/2003.07270v2
PDF https://arxiv.org/pdf/2003.07270v2.pdf
PWC https://paperswithcode.com/paper/an-automatic-attribute-based-access-control

Fast quantum learning with statistical guarantees

Title Fast quantum learning with statistical guarantees
Authors Carlo Ciliberto, Andrea Rocchetto, Alessandro Rudi, Leonard Wossnig
Abstract Within the framework of statistical learning theory it is possible to bound the minimum number of samples required by a learner to reach a target accuracy. We show that if the bound on the accuracy is taken into account, quantum machine learning algorithms – for which statistical guarantees are available – cannot achieve polylogarithmic runtimes in the input dimension. This calls for a careful revaluation of quantum speedups for learning problems, even in cases where quantum access to the data is naturally available.
Tasks Quantum Machine Learning
Published 2020-01-28
URL https://arxiv.org/abs/2001.10477v1
PDF https://arxiv.org/pdf/2001.10477v1.pdf
PWC https://paperswithcode.com/paper/fast-quantum-learning-with-statistical
comments powered by Disqus