Paper Group ANR 75
Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features. Machine Learning on Volatile Instances. Tractogram filtering of anatomically non-plausible fibers with geometric deep learning. Experiments on Manual Thesaurus based Query Expansion for Ad-hoc Monolingual Gujarati Information Retrieval Task …
Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features
| Title | Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features |
| Authors | Cunhang Fan, Bin Liu, Jianhua Tao, Jiangyan Yi, Zhengqi Wen |
| Abstract | Multi-channel deep clustering (MDC) has acquired a good performance for speech separation. However, MDC only applies the spatial features as the additional information. So it is difficult to learn mutual relationship between spatial and spectral features. Besides, the training objective of MDC is defined at embedding vectors, rather than real separated sources, which may damage the separation performance. In this work, we propose a deep attention fusion method to dynamically control the weights of the spectral and spatial features and combine them deeply. In addition, to solve the training objective problem of MDC, the real separated sources are used as the training objectives. Specifically, we apply the deep clustering network to extract deep embedding features. Instead of using the unsupervised K-means clustering to estimate binary masks, another supervised network is utilized to learn soft masks from these deep embedding features. Our experiments are conducted on a spatialized reverberant version of WSJ0-2mix dataset. Experimental results show that the proposed method outperforms MDC baseline and even better than the oracle ideal binary mask (IBM). |
| Tasks | Deep Attention, Speech Separation |
| Published | 2020-02-05 |
| URL | https://arxiv.org/abs/2002.01626v1 |
| https://arxiv.org/pdf/2002.01626v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-and-spectral-deep-attention-fusion |
| Repo | |
| Framework | |
Machine Learning on Volatile Instances
| Title | Machine Learning on Volatile Instances |
| Authors | Xiaoxi Zhang, Jianyu Wang, Gauri Joshi, Carlee Joe-Wong |
| Abstract | Due to the massive size of the neural network models and training datasets used in machine learning today, it is imperative to distribute stochastic gradient descent (SGD) by splitting up tasks such as gradient evaluation across multiple worker nodes. However, running distributed SGD can be prohibitively expensive because it may require specialized computing resources such as GPUs for extended periods of time. We propose cost-effective strategies to exploit volatile cloud instances that are cheaper than standard instances, but may be interrupted by higher priority workloads. To the best of our knowledge, this work is the first to quantify how variations in the number of active worker nodes (as a result of preemption) affects SGD convergence and the time to train the model. By understanding these trade-offs between preemption probability of the instances, accuracy, and training time, we are able to derive practical strategies for configuring distributed SGD jobs on volatile instances such as Amazon EC2 spot instances and other preemptible cloud instances. Experimental results show that our strategies achieve good training performance at substantially lower cost. |
| Tasks | |
| Published | 2020-03-12 |
| URL | https://arxiv.org/abs/2003.05649v1 |
| https://arxiv.org/pdf/2003.05649v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-on-volatile-instances |
| Repo | |
| Framework | |
Tractogram filtering of anatomically non-plausible fibers with geometric deep learning
| Title | Tractogram filtering of anatomically non-plausible fibers with geometric deep learning |
| Authors | Pietro Astolfi, Ruben Verhagen, Laurent Petit, Emanuele Olivetti, Jonathan Masci, Davide Boscaini, Paolo Avesani |
| Abstract | Tractograms are virtual representations of the white matter fibers of the brain. They are of primary interest for tasks like presurgical planning, and investigation of neuroplasticity or brain disorders. Each tractogram is composed of millions of fibers encoded as 3D polylines. Unfortunately, a large portion of those fibers are not anatomically plausible and can be considered artifacts of the tracking algorithms. Common methods for tractogram filtering are based on signal reconstruction, a principled approach, but unable to consider the knowledge of brain anatomy. In this work, we address the problem of tractogram filtering as a supervised learning problem by exploiting the ground truth annotations obtained with a recent heuristic method, which labels fibers as either anatomically plausible or non-plausible according to well-established anatomical properties. The intuitive idea is to model a fiber as a point cloud and the goal is to investigate whether and how a geometric deep learning model might capture its anatomical properties. Our contribution is an extension of the Dynamic Edge Convolution model that exploits the sequential relations of points in a fiber and discriminates with high accuracy plausible/non-plausible fibers. |
| Tasks | |
| Published | 2020-03-24 |
| URL | https://arxiv.org/abs/2003.11013v1 |
| https://arxiv.org/pdf/2003.11013v1.pdf | |
| PWC | https://paperswithcode.com/paper/tractogram-filtering-of-anatomically-non |
| Repo | |
| Framework | |
Experiments on Manual Thesaurus based Query Expansion for Ad-hoc Monolingual Gujarati Information Retrieval Tasks
| Title | Experiments on Manual Thesaurus based Query Expansion for Ad-hoc Monolingual Gujarati Information Retrieval Tasks |
| Authors | Hardik Joshi, Jyoti Pareek |
| Abstract | In this paper, we present the experimental work done on Query Expansion (QE) for retrieval tasks of Gujarati text documents. In information retrieval, it is very difficult to estimate the exact user need, query expansion adds terms to the original query, which provides more information about the user need. There are various approaches to query expansion. In our work, manual thesaurus based query expansion was performed to evaluate the performance of widely used information retrieval models for Gujarati text documents. Results show that query expansion improves the recall of text documents. |
| Tasks | Information Retrieval |
| Published | 2020-01-18 |
| URL | https://arxiv.org/abs/2001.08085v1 |
| https://arxiv.org/pdf/2001.08085v1.pdf | |
| PWC | https://paperswithcode.com/paper/experiments-on-manual-thesaurus-based-query |
| Repo | |
| Framework | |
Latent-variable Private Information Retrieval
| Title | Latent-variable Private Information Retrieval |
| Authors | Islam Samy, Mohamed A. Attia, Ravi Tandon, Loukas Lazos |
| Abstract | In many applications, content accessed by users (movies, videos, news articles, etc.) can leak sensitive latent attributes, such as religious and political views, sexual orientation, ethnicity, gender, and others. To prevent such information leakage, the goal of classical PIR is to hide the identity of the content/message being accessed, which subsequently also hides the latent attributes. This solution, while private, can be too costly, particularly, when perfect (information-theoretic) privacy constraints are imposed. For instance, for a single database holding $K$ messages, privately retrieving one message is possible if and only if the user downloads the entire database of $K$ messages. Retrieving content privately, however, may not be necessary to perfectly hide the latent attributes. Motivated by the above, we formulate and study the problem of latent-variable private information retrieval (LV-PIR), which aims at allowing the user efficiently retrieve one out of $K$ messages (indexed by $\theta$) without revealing any information about the latent variable (modeled by $S$). We focus on the practically relevant setting of a single database and show that one can significantly reduce the download cost of LV-PIR (compared to the classical PIR) based on the correlation between $\theta$ and $S$. We present a general scheme for LV-PIR as a function of the statistical relationship between $\theta$ and $S$, and also provide new results on the capacity/download cost of LV-PIR. Several open problems and new directions are also discussed. |
| Tasks | Information Retrieval |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.05998v1 |
| https://arxiv.org/pdf/2001.05998v1.pdf | |
| PWC | https://paperswithcode.com/paper/latent-variable-private-information-retrieval |
| Repo | |
| Framework | |
Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels
| Title | Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels |
| Authors | Xianbin Lv, Dongxian Wu, Shu-Tao Xia |
| Abstract | Training deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Probabilistic modeling, which consists of a classifier and a transition matrix, depicts the transformation from true labels to noisy labels and is a promising approach. However, recent probabilistic methods directly apply transition matrix to DNN, neglect DNN’s susceptibility to overfitting, and achieve unsatisfactory performance, especially under the uniform noise. In this paper, inspired by label smoothing, we proposed a novel method, in which a smoothed transition matrix is used for updating DNN, to restrict the overfitting of DNN in probabilistic modeling. Our method is termed Matrix Smoothing. We also empirically demonstrate that our method not only improves the robustness of probabilistic modeling significantly, but also even obtains a better estimation of the transition matrix. |
| Tasks | |
| Published | 2020-03-26 |
| URL | https://arxiv.org/abs/2003.11904v1 |
| https://arxiv.org/pdf/2003.11904v1.pdf | |
| PWC | https://paperswithcode.com/paper/matrix-smoothing-a-regularization-for-dnn |
| Repo | |
| Framework | |
Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World
| Title | Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World |
| Authors | Daniel J. Fremont, Edward Kim, Yash Vardhan Pant, Sanjit A. Seshia, Atul Acharya, Xantha Bruso, Paul Wells, Steve Lemke, Qiang Yu, Shalin Mehta |
| Abstract | We present a new approach to automated scenario-based testing of the safety of autonomous vehicles, especially those using advanced artificial intelligence-based components, spanning both simulation-based evaluation as well as testing in the real world. Our approach is based on formal methods, combining formal specification of scenarios and safety properties, algorithmic test case generation using formal simulation, test case selection for track testing, executing test cases on the track, and analyzing the resulting data. Experiments with a real autonomous vehicle at an industrial testing ground support our hypotheses that (i) formal simulation can be effective at identifying test cases to run on the track, and (ii) the gap between simulated and real worlds can be systematically evaluated and bridged. |
| Tasks | Autonomous Vehicles |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.07739v1 |
| https://arxiv.org/pdf/2003.07739v1.pdf | |
| PWC | https://paperswithcode.com/paper/formal-scenario-based-testing-of-autonomous |
| Repo | |
| Framework | |
Unbiased evaluation of ranking metrics reveals consistent performance in science and technology citation data
| Title | Unbiased evaluation of ranking metrics reveals consistent performance in science and technology citation data |
| Authors | Shuqi Xu, Manuel Sebastian Mariani, Linyuan Lü, Matúš Medo |
| Abstract | Despite the increasing use of citation-based metrics for research evaluation purposes, we do not know yet which metrics best deliver on their promise to gauge the significance of a scientific paper or a patent. We assess 17 network-based metrics by their ability to identify milestone papers and patents in three large citation datasets. We find that traditional information-retrieval evaluation metrics are strongly affected by the interplay between the age distribution of the milestone items and age biases of the evaluated metrics. Outcomes of these metrics are therefore not representative of the metrics’ ranking ability. We argue in favor of a modified evaluation procedure that explicitly penalizes biased metrics and allows us to reveal metrics’ performance patterns that are consistent across the datasets. PageRank and LeaderRank turn out to be the best-performing ranking metrics when their age bias is suppressed by a simple transformation of the scores that they produce, whereas other popular metrics, including citation count, HITS and Collective Influence, produce significantly worse ranking results. |
| Tasks | Information Retrieval |
| Published | 2020-01-15 |
| URL | https://arxiv.org/abs/2001.05414v1 |
| https://arxiv.org/pdf/2001.05414v1.pdf | |
| PWC | https://paperswithcode.com/paper/unbiased-evaluation-of-ranking-metrics |
| Repo | |
| Framework | |
BERT Can See Out of the Box: On the Cross-modal Transferability of Text Representations
| Title | BERT Can See Out of the Box: On the Cross-modal Transferability of Text Representations |
| Authors | Thomas Scialom, Patrick Bordes, Paul-Alexis Dray, Jacopo Staiano, Patrick Gallinari |
| Abstract | Pre-trained language models such as BERT have recently contributed to significant advances in Natural Language Processing tasks. Interestingly, while multilingual BERT models have demonstrated impressive results, recent works have shown how monolingual BERT can also be competitive in zero-shot cross-lingual settings. This suggests that the abstractions learned by these models can transfer across languages, even when trained on monolingual data. In this paper, we investigate whether such generalization potential applies to other modalities, such as vision: does BERT contain abstractions that generalize beyond text? We introduce BERT-gen, an architecture for text generation based on BERT, able to leverage on either mono- or multi- modal representations. The results reported under different configurations indicate a positive answer to our research question, and the proposed model obtains substantial improvements over the state-of-the-art on two established Visual Question Generation datasets. |
| Tasks | Question Generation, Text Generation |
| Published | 2020-02-25 |
| URL | https://arxiv.org/abs/2002.10832v1 |
| https://arxiv.org/pdf/2002.10832v1.pdf | |
| PWC | https://paperswithcode.com/paper/bert-can-see-out-of-the-box-on-the-cross |
| Repo | |
| Framework | |
Noise-tolerant, Reliable Active Classification with Comparison Queries
| Title | Noise-tolerant, Reliable Active Classification with Comparison Queries |
| Authors | Max Hopkins, Daniel Kane, Shachar Lovett, Gaurav Mahajan |
| Abstract | With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in theory and in practice. We study the paradigm of active learning, in which algorithms with access to large pools of data may adaptively choose what samples to label in the hope of exponentially increasing efficiency. By introducing comparisons, an additional type of query comparing two points, we provide the first time and query efficient algorithms for learning non-homogeneous linear separators robust to bounded (Massart) noise. We further provide algorithms for a generalization of the popular Tsybakov low noise condition, and show how comparisons provide a strong reliability guarantee that is often impractical or impossible with only labels - returning a classifier that makes no errors with high probability. |
| Tasks | Active Learning |
| Published | 2020-01-15 |
| URL | https://arxiv.org/abs/2001.05497v1 |
| https://arxiv.org/pdf/2001.05497v1.pdf | |
| PWC | https://paperswithcode.com/paper/noise-tolerant-reliable-active-classification |
| Repo | |
| Framework | |
Hybrid Model For Intrusion Detection Systems
| Title | Hybrid Model For Intrusion Detection Systems |
| Authors | Baha Rababah, Srija Srivastava |
| Abstract | With the increasing number of new attacks on ever growing network traffic, it is becoming challenging to alert immediately any malicious activities to avoid loss of sensitive data and money. This is making intrusion detection as one of the major areas of concern in network security. Anomaly based network intrusion detection technique is one of the most commonly used technique. Depending upon the dataset used to test those techniques, the accuracy varies. Most of the times this dataset does not represent the real network traffic. Considering this, this project involves analysis of different machine learning algorithms used in intrusion detection systems, when tested upon two datasets which are similar to current real world network traffic(CICIDS2017) and an improvement of KDD 99 (NSL-KDD). After the analysis of different intrusion detection systems on both the datasets, this project aimed to develop a new hybrid model for intrusion detection systems. This new hybrid approach combines decision tree and random forest algorithms using stacking scheme to achieve an accuracy of 85.2% and precision of 86.2% for NSL-KDD dataset, and achieve an accuracy of 98% and precision of 98% for CICIDS2017 dataset. |
| Tasks | Intrusion Detection, Network Intrusion Detection |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08585v1 |
| https://arxiv.org/pdf/2003.08585v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-model-for-intrusion-detection-systems |
| Repo | |
| Framework | |
Multi-objective Consensus Clustering Framework for Flight Search Recommendation
| Title | Multi-objective Consensus Clustering Framework for Flight Search Recommendation |
| Authors | Sujoy Chatterjee, Nicolas Pasquier, Simon Nanty, Maria A. Zuluaga |
| Abstract | In the travel industry, online customers book their travel itinerary according to several features, like cost and duration of the travel or the quality of amenities. To provide personalized recommendations for travel searches, an appropriate segmentation of customers is required. Clustering ensemble approaches were developed to overcome well-known problems of classical clustering approaches, that each rely on a different theoretical model and can thus identify in the data space only clusters corresponding to this model. Clustering ensemble approaches combine multiple clustering results, each from a different algorithmic configuration, for generating more robust consensus clusters corresponding to agreements between initial clusters. We present a new clustering ensemble multi-objective optimization-based framework developed for analyzing Amadeus customer search data and improve personalized recommendations. This framework optimizes diversity in the clustering ensemble search space and automatically determines an appropriate number of clusters without requiring user’s input. Experimental results compare the efficiency of this approach with other existing approaches on Amadeus customer search data in terms of internal (Adjusted Rand Index) and external (Amadeus business metric) validations. |
| Tasks | |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.10241v2 |
| https://arxiv.org/pdf/2002.10241v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-consensus-clustering |
| Repo | |
| Framework | |
VisionGuard: Runtime Detection of Adversarial Inputs to Perception Systems
| Title | VisionGuard: Runtime Detection of Adversarial Inputs to Perception Systems |
| Authors | Yiannis Kantaros, Taylor Carpenter, Sangdon Park, Radoslav Ivanov, Sooyong Jang, Insup Lee, James Weimer |
| Abstract | Deep neural network (DNN) models have proven to be vulnerable to adversarial attacks. In this paper, we propose VisionGuard, a novel attack- and dataset-agnostic and computationally-light defense mechanism for adversarial inputs to DNN-based perception systems. In particular, VisionGuard relies on the observation that adversarial images are sensitive to lossy compression transformations. Specifically, to determine if an image is adversarial, VisionGuard checks if the output of the target classifier on a given input image changes significantly after feeding it a transformed version of the image under investigation. Moreover, we show that VisionGuard is computationally-light both at runtime and design-time which makes it suitable for real-time applications that may also involve large-scale image domains. To highlight this, we demonstrate the efficiency of VisionGuard on ImageNet, a task that is computationally challenging for the majority of relevant defenses. Finally, we include extensive comparative experiments on the MNIST, CIFAR10, and ImageNet datasets that show that VisionGuard outperforms existing defenses in terms of scalability and detection performance. |
| Tasks | |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2002.09792v1 |
| https://arxiv.org/pdf/2002.09792v1.pdf | |
| PWC | https://paperswithcode.com/paper/visionguard-runtime-detection-of-adversarial |
| Repo | |
| Framework | |
Spherical Principal Curves
| Title | Spherical Principal Curves |
| Authors | Jang-Hyun Kim, Jongmin Lee, Hee-Seok Oh |
| Abstract | This paper presents a new approach for dimension reduction of data observed in a sphere. Several dimension reduction techniques have recently developed for the analysis of non-Euclidean data. As a pioneer work, Hauberg (2016) attempted to implement principal curves on Riemannian manifolds. However, this approach uses approximations to deal with data on Riemannian manifolds, which causes distorted results. In this study, we propose a new approach to construct principal curves on a sphere by a projection of the data onto a continuous curve. Our approach lies in the same line of Hastie and Stuetzle (1989) that proposed principal curves for Euclidean space data. We further investigate the stationarity of the proposed principal curves that satisfy the self-consistency on a sphere. Results from real data analysis with earthquake data and simulation examples demonstrate the promising empirical properties of the proposed approach. |
| Tasks | Dimensionality Reduction |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.02578v1 |
| https://arxiv.org/pdf/2003.02578v1.pdf | |
| PWC | https://paperswithcode.com/paper/spherical-principal-curves |
| Repo | |
| Framework | |
Cumulant-free closed-form formulas for some common (dis)similarities between densities of an exponential family
| Title | Cumulant-free closed-form formulas for some common (dis)similarities between densities of an exponential family |
| Authors | Frank Nielsen, Richard Nock |
| Abstract | It is well-known that the Bhattacharyya, Hellinger, Kullback-Leibler, $\alpha$-divergences, and Jeffreys’ divergences between densities belonging to a same exponential family have generic closed-form formulas relying on the strictly convex and real-analytic cumulant function characterizing the exponential family. In this work, we report (dis)similarity formulas which bypass the explicit use of the cumulant function and highlight the role of quasi-arithmetic means and their multivariate mean operator extensions. In practice, these cumulant-free formulas are handy when implementing these (dis)similarities using legacy Application Programming Interfaces (APIs) since our method requires only to partially factorize the densities canonically of the considered exponential family. |
| Tasks | |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.02469v1 |
| https://arxiv.org/pdf/2003.02469v1.pdf | |
| PWC | https://paperswithcode.com/paper/cumulant-free-closed-form-formulas-for-some |
| Repo | |
| Framework | |
