Paper Group ANR 626
Jointly optimal dereverberation and beamforming. Component-Wise Boosting of Targets for Multi-Output Prediction. On the Convergence of Model Free Learning in Mean Field Games. Condition monitoring and early diagnostics methodologies for hydropower plants. WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis. A …
Jointly optimal dereverberation and beamforming
| Title | Jointly optimal dereverberation and beamforming |
| Authors | Christoph Boeddeker, Tomohiro Nakatani, Keisuke Kinoshita, Reinhold Haeb-Umbach |
| Abstract | We previously proposed an optimal (in the maximum likelihood sense) convolutional beamformer that can perform simultaneous denoising and dereverberation, and showed its superiority over the widely used cascade of a WPE dereverberation filter and a conventional MPDR beamformer. However, it has not been fully investigated which components in the convolutional beamformer yield such superiority. To this end, this paper presents a new derivation of the convolutional beamformer that allows us to factorize it into a WPE dereverberation filter, and a special type of a (non-convolutional) beamformer, referred to as a wMPDR beamformer, without loss of optimality. With experiments, we show that the superiority of the convolutional beamformer in fact comes from its wMPDR part. |
| Tasks | Denoising |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.13707v1 |
| https://arxiv.org/pdf/1910.13707v1.pdf | |
| PWC | https://paperswithcode.com/paper/jointly-optimal-dereverberation-and |
| Repo | |
| Framework | |
Component-Wise Boosting of Targets for Multi-Output Prediction
| Title | Component-Wise Boosting of Targets for Multi-Output Prediction |
| Authors | Quay Au, Daniel Schalk, Giuseppe Casalicchio, Ramona Schoedel, Clemens Stachl, Bernd Bischl |
| Abstract | Multi-output prediction deals with the prediction of several targets of possibly diverse types. One way to address this problem is the so called problem transformation method. This method is often used in multi-label learning, but can also be used for multi-output prediction due to its generality and simplicity. In this paper, we introduce an algorithm that uses the problem transformation method for multi-output prediction, while simultaneously learning the dependencies between target variables in a sparse and interpretable manner. In a first step, predictions are obtained for each target individually. Target dependencies are then learned via a component-wise boosting approach. We compare our new method with similar approaches in a benchmark using multi-label, multivariate regression and mixed-type datasets. |
| Tasks | Multi-Label Learning |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.03943v1 |
| http://arxiv.org/pdf/1904.03943v1.pdf | |
| PWC | https://paperswithcode.com/paper/component-wise-boosting-of-targets-for-multi |
| Repo | |
| Framework | |
On the Convergence of Model Free Learning in Mean Field Games
| Title | On the Convergence of Model Free Learning in Mean Field Games |
| Authors | Romuald Elie, Julien Pérolat, Mathieu Laurière, Matthieu Geist, Olivier Pietquin |
| Abstract | Learning by experience in Multi-Agent Systems (MAS) is a difficult and exciting task, due to the lack of stationarity of the environment, whose dynamics evolves as the population learns. In order to design scalable algorithms for systems with a large population of interacting agents (e.g. swarms), this paper focuses on Mean Field MAS, where the number of agents is asymptotically infinite. Recently, a very active burgeoning field studies the effects of diverse reinforcement learning algorithms for agents with no prior information on a stationary Mean Field Game (MFG) and learn their policy through repeated experience. We adopt a high perspective on this problem and analyze in full generality the convergence of a fictitious iterative scheme using any single agent learning algorithm at each step. We quantify the quality of the computed approximate Nash equilibrium, in terms of the accumulated errors arising at each learning iteration step. Notably, we show for the first time convergence of model free learning algorithms towards non-stationary MFG equilibria, relying only on classical assumptions on the MFG dynamics. We illustrate our theoretical results with a numerical experiment in a continuous action-space environment, where the approximate best response of the iterative fictitious play scheme is computed with a deep RL algorithm. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02633v3 |
| https://arxiv.org/pdf/1907.02633v3.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-fictitious-play-for-mean-field |
| Repo | |
| Framework | |
Condition monitoring and early diagnostics methodologies for hydropower plants
| Title | Condition monitoring and early diagnostics methodologies for hydropower plants |
| Authors | Alessandro Betti, Emanuele Crisostomi, Gianluca Paolinelli, Antonio Piazzi, Fabrizio Ruffini, Mauro Tucci |
| Abstract | Hydropower plants are one of the most convenient option for power generation, as they generate energy exploiting a renewable source, they have relatively low operating and maintenance costs, and they may be used to provide ancillary services, exploiting the large reservoirs of available water. The recent advances in Information and Communication Technologies (ICT) and in machine learning methodologies are seen as fundamental enablers to upgrade and modernize the current operation of most hydropower plants, in terms of condition monitoring, early diagnostics and eventually predictive maintenance. While very few works, or running technologies, have been documented so far for the hydro case, in this paper we propose a novel Key Performance Indicator (KPI) that we have recently developed and tested on operating hydropower plants. In particular, we show that after more than one year of operation it has been able to identify several faults, and to support the operation and maintenance tasks of plant operators. Also, we show that the proposed KPI outperforms conventional multivariable process control charts, like the Hotelling $t_2$ index. |
| Tasks | |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.06242v1 |
| https://arxiv.org/pdf/1911.06242v1.pdf | |
| PWC | https://paperswithcode.com/paper/condition-monitoring-and-early-diagnostics |
| Repo | |
| Framework | |
WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis
| Title | WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis |
| Authors | Tianfu Li, Zhibin Zhao, Chuang Sun, Li Cheng, Xuefeng Chen, Ruqiang Yan, Robert X. Gao |
| Abstract | Convolutional neural network (CNN), with ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, explanation on the physical meaning of a CNN architecture has rarely been studied. In this paper, a novel wavelet driven deep neural network termed as WaveletKernelNet (WKN) is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful filters. Furthermore, only the scale parameter and translation parameter are directly learned from raw data at this CWConv layer. This provides a very effective way to obtain a customized filter bank, specifically tuned for extracting defect-related impact component embedded in the vibration signal. In addition, three experimental verification using data from laboratory environment are carried out to verify effectiveness of the proposed method for mechanical fault diagnosis. The results show the importance of the designed CWConv layer and the output of CWConv layer is interpretable. Besides, it is found that WKN has fewer parameters, higher fault classification accuracy and faster convergence speed than standard CNN. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.07925v2 |
| https://arxiv.org/pdf/1911.07925v2.pdf | |
| PWC | https://paperswithcode.com/paper/waveletkernelnet-an-interpretable-deep-neural |
| Repo | |
| Framework | |
AKM$^2$D : An Adaptive Framework for Online Sensing and Anomaly Quantification
| Title | AKM$^2$D : An Adaptive Framework for Online Sensing and Anomaly Quantification |
| Authors | Hao Yan, Kamran Paynabar, Jianjun Shi |
| Abstract | In point-based sensing systems such as coordinate measuring machines (CMM) and laser ultrasonics where complete sensing is impractical due to the high sensing time and cost, adaptive sensing through a systematic exploration is vital for online inspection and anomaly quantification. Most of the existing sequential sampling methodologies focus on reducing the overall fitting error for the entire sampling space. However, in many anomaly quantification applications, the main goal is to estimate sparse anomalous regions in the pixel-level accurately. In this paper, we develop a novel framework named Adaptive Kernelized Maximum-Minimum Distance AKM$^2$D to speed up the inspection and anomaly detection process through an intelligent sequential sampling scheme integrated with fast estimation and detection. The proposed method balances the sampling efforts between the space-filling sampling (exploration) and focused sampling near the anomalous region (exploitation). The proposed methodology is validated by conducting simulations and a case study of anomaly detection in composite sheets using a guided wave test. |
| Tasks | Anomaly Detection |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.02119v1 |
| https://arxiv.org/pdf/1910.02119v1.pdf | |
| PWC | https://paperswithcode.com/paper/akm2d-an-adaptive-framework-for-online |
| Repo | |
| Framework | |
Emergent Properties of Finetuned Language Representation Models
| Title | Emergent Properties of Finetuned Language Representation Models |
| Authors | Alexandre Matton, Luke de Oliveira |
| Abstract | Large, self-supervised transformer-based language representation models have recently received significant amounts of attention, and have produced state-of-the-art results across a variety of tasks simply by scaling up pre-training on larger and larger corpora. Such models usually produce high dimensional vectors, on top of which additional task-specific layers and architectural modifications are added to adapt them to specific downstream tasks. Though there exists ample evidence that such models work well, we aim to understand what happens when they work well. We analyze the redundancy and location of information contained in output vectors for one such language representation model – BERT. We show empirical evidence that the [CLS] embedding in BERT contains highly redundant information, and can be compressed with minimal loss of accuracy, especially for finetuned models, dovetailing into open threads in the field about the role of over-parameterization in learning. We also shed light on the existence of specific output dimensions which alone give very competitive results when compared to using all dimensions of output vectors. |
| Tasks | |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10832v1 |
| https://arxiv.org/pdf/1910.10832v1.pdf | |
| PWC | https://paperswithcode.com/paper/emergent-properties-of-finetuned-language |
| Repo | |
| Framework | |
An Efficient Model for Sentiment Analysis of Electronic Product Reviews in Vietnamese
| Title | An Efficient Model for Sentiment Analysis of Electronic Product Reviews in Vietnamese |
| Authors | Suong N. Hoang, Linh V. Nguyen, Tai Huynh, Vuong T. Pham |
| Abstract | In the past few years, the growth of e-commerce and digital marketing in Vietnam has generated a huge volume of opinionated data. Analyzing those data would provide enterprises with insight for better business decisions. In this work, as part of the Advosights project, we study sentiment analysis of product reviews in Vietnamese. The final solution is based on Self-attention neural networks, a flexible architecture for text classification task with about 90.16% of accuracy in 0.0124 second, a very fast inference time. |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13162v1 |
| https://arxiv.org/pdf/1910.13162v1.pdf | |
| PWC | https://paperswithcode.com/paper/191013162 |
| Repo | |
| Framework | |
Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics
| Title | Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics |
| Authors | Bingzhe Wu, Chaochao Chen, Shiwan Zhao, Cen Chen, Yuan Yao, Guangyu Sun, Li Wang, Xiaolu Zhang, Jun Zhou |
| Abstract | Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD) is an effective method to enable Bayesian deep learning on large-scale datasets. Previous theoretical studies have shown various appealing properties of SGLD, ranging from the convergence properties to the generalization bounds. In this paper, we study the properties of SGLD from a novel perspective of membership privacy protection (i.e., preventing the membership attack). The membership attack, which aims to determine whether a specific sample is used for training a given DNN model, has emerged as a common threat against deep learning algorithms. To this end, we build a theoretical framework to analyze the information leakage (w.r.t. the training dataset) of a model trained using SGLD. Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent. Moreover, our theoretical analysis can be naturally extended to other types of Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods. Empirical results on different datasets and models verify our theoretical findings and suggest that the SGLD algorithm can not only reduce the information leakage but also improve the generalization ability of the DNN models in real-world applications. |
| Tasks | |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02249v1 |
| https://arxiv.org/pdf/1910.02249v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-membership-privacy-in |
| Repo | |
| Framework | |
Conditional independence testing: a predictive perspective
| Title | Conditional independence testing: a predictive perspective |
| Authors | Marco Henrique de Almeida Inácio, Rafael Izbicki, Rafael Bassi Stern |
| Abstract | Conditional independence testing is a key problem required by many machine learning and statistics tools. In particular, it is one way of evaluating the usefulness of some features on a supervised prediction problem. We propose a novel conditional independence test in a predictive setting, and show that it achieves better power than competing approaches in several settings. Our approach consists in deriving a p-value using a permutation test where the predictive power using the unpermuted dataset is compared with the predictive power of using dataset where the feature(s) of interest are permuted. We conclude that the method achives sensible results on simulated and real datasets. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1908.00105v1 |
| https://arxiv.org/pdf/1908.00105v1.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-independence-testing-a-predictive |
| Repo | |
| Framework | |
Adaptive Lighting for Data-Driven Non-Line-of-Sight 3D Localization and Object Identification
| Title | Adaptive Lighting for Data-Driven Non-Line-of-Sight 3D Localization and Object Identification |
| Authors | Sreenithy Chandran, Suren Jayasuriya |
| Abstract | Non-line-of-sight (NLOS) imaging of objects not visible to either the camera or illumination source is a challenging task with vital applications including surveillance and robotics. Recent NLOS reconstruction advances have been achieved using time-resolved measurements which requires expensive and specialized detectors and laser sources. In contrast, we propose a data-driven approach for NLOS 3D localization and object identification requiring only a conventional camera and projector. To generalize to complex line-of-sight (LOS) scenes with non-planar surfaces and occlusions, we introduce an adaptive lighting algorithm. This algorithm, based on radiosity, identifies and illuminates scene patches in the LOS which most contribute to the NLOS light paths, and can factor in system power constraints. We achieve an average identification of 87.1% object identification for four classes of objects, and average localization of the NLOS object’s centroid with a mean-squared error (MSE) of 1.97 cm in the occluded region for real data taken from a hardware prototype. These results demonstrate the advantage of combining the physics of light transport with active illumination for data-driven NLOS imaging. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11595v2 |
| https://arxiv.org/pdf/1905.11595v2.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-lighting-for-data-driven-non-line-of |
| Repo | |
| Framework | |
DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences
| Title | DefSLAM: Tracking and Mapping of Deforming Scenes from Monocular Sequences |
| Authors | Jose Lamarca, Shaifali Parashar, Adrien Bartoli, J. M. M. Montiel |
| Abstract | We present the first monocular SLAM capable of operating in deforming scenes in real-time. Our DefSLAM approach fuses isometric Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM) techniques to deal with the exploratory sequences typical of SLAM. A deformation tracking thread recovers the pose of the camera and the deformation of the observed map at frame rate by means of SfT. A deformation mapping thread runs in parallel to update the template at keyframe rate by means of NRSfM with a batch of covisible keyframes. In our experiments, DefSLAM processes sequences of deforming scenes both in a laboratory controlled experiment and in medical endoscopy sequences, being able to produce accurate 3D models of the scene with respect to the moving camera. |
| Tasks | |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.08918v1 |
| https://arxiv.org/pdf/1908.08918v1.pdf | |
| PWC | https://paperswithcode.com/paper/defslam-tracking-and-mapping-of-deforming |
| Repo | |
| Framework | |
Explaining an increase in predicted risk for clinical alerts
| Title | Explaining an increase in predicted risk for clinical alerts |
| Authors | Michaela Hardt, Alvin Rajkomar, Gerardo Flores, Andrew Dai, Michael Howell, Greg Corrado, Claire Cui, Moritz Hardt |
| Abstract | Much work aims to explain a model’s prediction on a static input. We consider explanations in a temporal setting where a stateful dynamical model produces a sequence of risk estimates given an input at each time step. When the estimated risk increases, the goal of the explanation is to attribute the increase to a few relevant inputs from the past. While our formal setup and techniques are general, we carry out an in-depth case study in a clinical setting. The goal here is to alert a clinician when a patient’s risk of deterioration rises. The clinician then has to decide whether to intervene and adjust the treatment. Given a potentially long sequence of new events since she last saw the patient, a concise explanation helps her to quickly triage the alert. We develop methods to lift static attribution techniques to the dynamical setting, where we identify and address challenges specific to dynamics. We then experimentally assess the utility of different explanations of clinical alerts through expert evaluation. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04911v1 |
| https://arxiv.org/pdf/1907.04911v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-an-increase-in-predicted-risk-for |
| Repo | |
| Framework | |
Dependency-based Text Graphs for Keyphrase and Summary Extraction with Applications to Interactive Content Retrieval
| Title | Dependency-based Text Graphs for Keyphrase and Summary Extraction with Applications to Interactive Content Retrieval |
| Authors | Paul Tarau, Eduardo Blanco |
| Abstract | We build a bridge between neural network-based machine learning and graph-based natural language processing and introduce a unified approach to keyphrase, summary and relation extraction by aggregating dependency graphs from links provided by a deep-learning based dependency parser. We reorganize dependency graphs to focus on the most relevant content elements of a sentence, integrate sentence identifiers as graph nodes and after ranking the graph, we extract our keyphrases and summaries from its largest strongly-connected component. We take advantage of the implicit structural information that dependency links bring to extract subject-verb-object, is-a and part-of relations. We put it all together into a proof-of-concept dialog engine that specializes the text graph with respect to a query and reveals interactively the document’s most relevant content elements. The open-source code of the integrated system is available at https://github.com/ptarau/DeepRank . Keywords: graph-based natural language processing, dependency graphs, keyphrase, summary and relation extraction, query-driven salient sentence extraction, logic-based dialog engine, synergies between neural and symbolic processing. |
| Tasks | Relation Extraction |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09742v1 |
| https://arxiv.org/pdf/1909.09742v1.pdf | |
| PWC | https://paperswithcode.com/paper/190909742 |
| Repo | |
| Framework | |
Global Locality in Event Extraction
| Title | Global Locality in Event Extraction |
| Authors | Elaheh ShafieiBavani, Antonio Jimeno Yepes, Xu Zhong |
| Abstract | Due to the exponential growth of biomedical literature, event and relation extraction are important tasks in biomedical text mining. Most work in relation extraction detect a single entity pair mention on a short span of text, which is not ideal due to long sentences that appear in biomedical contexts. We propose an approach to both event and relation extraction, for simultaneously predicting relationships between all mention pairs in a text. Our model includes a set of multi-head attentions and convolutions, an adaptation of the transformer architecture, which offers self-attention the ability to strengthen dependencies among related elements, and models the interaction between features extracted by multiple attention heads. Experiment results demonstrate that our approach outperforms the state-of-the-art on a set of benchmark biomedical corpora including BioNLP 2009, 2011, 2013 and BioCreative 2017 shared tasks. |
| Tasks | Relation Extraction |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.04822v1 |
| https://arxiv.org/pdf/1909.04822v1.pdf | |
| PWC | https://paperswithcode.com/paper/global-locality-in-event-extraction |
| Repo | |
| Framework | |
