Paper Group ANR 233
Efficient Training of Deep Classifiers for Wireless Source Identification using Test SNR Estimates. Effect of context in swipe gesture-based continuous authentication on smartphones. Rumor Detection and Classification for Twitter Data. A Heterogeneous Graphical Model to Understand User-Level Sentiments in Social Media. Correct-and-Memorize: Learnin …
Efficient Training of Deep Classifiers for Wireless Source Identification using Test SNR Estimates
| Title | Efficient Training of Deep Classifiers for Wireless Source Identification using Test SNR Estimates |
| Authors | Xingchen Wang, Shengtai Ju, Xiwen Zhang, Sharan Ramjee, Aly El Gamal |
| Abstract | We investigate the potential of training time reduction for deep learning algorithms that process received wireless signals, if an accurate test Signal to Noise Ratio (SNR) estimate is available. Our focus is on two tasks that facilitate source identification: 1- Identifying the modulation type, 2- Identifying the wireless technology and channel index in the 2.4 GHZ ISM band. For benchmarking, we rely on a fast growing recent literature on testing deep learning algorithms against two well-known synthetic datasets. We first demonstrate that using training data corresponding only to the test SNR value leads to dramatic reductions in training time - that can reach up to 35x - while incurring a small loss in average test accuracy, as it improves the accuracy for low test SNR values. Further, we show that an erroneous test SNR estimate with a small positive offset is better for training than another having the same error magnitude with a negative offset. Secondly, we introduce a greedy training SNR Boosting algorithm that leads to uniform improvement in test accuracy across all tested SNR values, while using only a small subset of training SNR values at each test SNR. Finally, we discuss, with empirical evidence, the potential of bootstrap aggregating (Bagging) based on training SNR values to improve generalization at low test SNR |
| Tasks | |
| Published | 2019-12-26 |
| URL | https://arxiv.org/abs/1912.11896v1 |
| https://arxiv.org/pdf/1912.11896v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-training-of-deep-classifiers-for |
| Repo | |
| Framework | |
Effect of context in swipe gesture-based continuous authentication on smartphones
| Title | Effect of context in swipe gesture-based continuous authentication on smartphones |
| Authors | Pekka Siirtola, Jukka Komulainen, Vili Kellokumpu |
| Abstract | This work investigates how context should be taken into account when performing continuous authentication of a smartphone user based on touchscreen and accelerometer readings extracted from swipe gestures. The study is conducted on the publicly available HMOG dataset consisting of 100 study subjects performing pre-defined reading and navigation tasks while sitting and walking. It is shown that context-specific models are needed for different smartphone usage and human activity scenarios to minimize authentication error. Also, the experimental results suggests that utilization of phone movement improves swipe gesture-based verification performance only when the user is moving. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11780v1 |
| https://arxiv.org/pdf/1905.11780v1.pdf | |
| PWC | https://paperswithcode.com/paper/effect-of-context-in-swipe-gesture-based |
| Repo | |
| Framework | |
Rumor Detection and Classification for Twitter Data
| Title | Rumor Detection and Classification for Twitter Data |
| Authors | Sardar Hamidian, Mona T Diab |
| Abstract | With the pervasiveness of online media data as a source of information verifying the validity of this information is becoming even more important yet quite challenging. Rumors spread a large quantity of misinformation on microblogs. In this study we address two common issues within the context of microblog social media. First we detect rumors as a type of misinformation propagation and next we go beyond detection to perform the task of rumor classification. WE explore the problem using a standard data set. We devise novel features and study their impact on the task. We experiment with various levels of preprocessing as a precursor of the classification as well as grouping of features. We achieve and f-measure of over 0.82 in RDC task in mixed rumors data set and 84 percent in a single rumor data set using a two-step classification approach. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1912.08926v1 |
| https://arxiv.org/pdf/1912.08926v1.pdf | |
| PWC | https://paperswithcode.com/paper/rumor-detection-and-classification-for |
| Repo | |
| Framework | |
A Heterogeneous Graphical Model to Understand User-Level Sentiments in Social Media
| Title | A Heterogeneous Graphical Model to Understand User-Level Sentiments in Social Media |
| Authors | Rahul Radhakrishnan Iyer, Jing Chen, Haonan Sun, Keyang Xu |
| Abstract | Social Media has seen a tremendous growth in the last decade and is continuing to grow at a rapid pace. With such adoption, it is increasingly becoming a rich source of data for opinion mining and sentiment analysis. The detection and analysis of sentiment in social media is thus a valuable topic and attracts a lot of research efforts. Most of the earlier efforts focus on supervised learning approaches to solve this problem, which require expensive human annotations and therefore limits their practical use. In our work, we propose a semi-supervised approach to predict user-level sentiments for specific topics. We define and utilize a heterogeneous graph built from the social networks of the users with the knowledge that connected users in social networks typically share similar sentiments. Compared with the previous works, we have several novelties: (1) we incorporate the influences/authoritativeness of the users into the model, 2) we include comment-based and like-based user-user links to the graph, 3) we superimpose multiple heterogeneous graphs into one thereby allowing multiple types of links to exist between two users. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.07911v1 |
| https://arxiv.org/pdf/1912.07911v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-heterogeneous-graphical-model-to-understand |
| Repo | |
| Framework | |
Correct-and-Memorize: Learning to Translate from Interactive Revisions
| Title | Correct-and-Memorize: Learning to Translate from Interactive Revisions |
| Authors | Rongxiang Weng, Hao Zhou, Shujian Huang, Lei Li, Yifan Xia, Jiajun Chen |
| Abstract | State-of-the-art machine translation models are still not on par with human translators. Previous work takes human interactions into the neural machine translation process to obtain improved results in target languages. However, not all model-translation errors are equal – some are critical while others are minor. In the meanwhile, the same translation mistakes occur repeatedly in a similar context. To solve both issues, we propose CAMIT, a novel method for translating in an interactive environment. Our proposed method works with critical revision instructions, therefore allows human to correct arbitrary words in model-translated sentences. In addition, CAMIT learns from and softly memorizes revision actions based on the context, alleviating the issue of repeating mistakes. Experiments in both ideal and real interactive translation settings demonstrate that our proposed \method enhances machine translation results significantly while requires fewer revision instructions from human compared to previous methods. |
| Tasks | Machine Translation |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.03468v2 |
| https://arxiv.org/pdf/1907.03468v2.pdf | |
| PWC | https://paperswithcode.com/paper/correct-and-memorize-learning-to-translate |
| Repo | |
| Framework | |
Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations
| Title | Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations |
| Authors | Carlo Baldassi, Enrico M. Malatesta, Riccardo Zecchina |
| Abstract | Rectified Linear Units (ReLU) have become the main model for the neural units in current deep learning systems. This choice has been originally suggested as a way to compensate for the so called vanishing gradient problem which can undercut stochastic gradient descent (SGD) learning in networks composed of multiple layers. Here we provide analytical results on the effects of ReLUs on the capacity and on the geometrical landscape of the solution space in two-layer neural networks with either binary or real-valued weights. We study the problem of storing an extensive number of random patterns and find that, quite unexpectedly, the capacity of the network remains finite as the number of neurons in the hidden layer increases, at odds with the case of threshold units in which the capacity diverges. Possibly more important, a large deviation approach allows us to find that the geometrical landscape of the solution space has a peculiar structure: while the majority of solutions are close in distance but still isolated, there exist rare regions of solutions which are much more dense than the similar ones in the case of threshold units. These solutions are robust to perturbations of the weights and can tolerate large perturbations of the inputs. The analytical results are corroborated by numerical findings. |
| Tasks | |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07578v4 |
| https://arxiv.org/pdf/1907.07578v4.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-geometry-of-solutions-and-on-the |
| Repo | |
| Framework | |
RUN through the Streets: A New Dataset and Baseline Models for Realistic Urban Navigation
| Title | RUN through the Streets: A New Dataset and Baseline Models for Realistic Urban Navigation |
| Authors | Tzuf Paz-Argaman, Reut Tsarfaty |
| Abstract | Following navigation instructions in natural language requires a composition of language, action, and knowledge of the environment. Knowledge of the environment may be provided via visual sensors or as a symbolic world representation referred to as a map. Here we introduce the Realistic Urban Navigation (RUN) task, aimed at interpreting navigation instructions based on a real, dense, urban map. Using Amazon Mechanical Turk, we collected a dataset of 2515 instructions aligned with actual routes over three regions of Manhattan. We propose a strong baseline for the task and empirically investigate which aspects of the neural architecture are important for the RUN success. Our results empirically show that entity abstraction, attention over words and worlds, and a constantly updating world-state, significantly contribute to task accuracy. |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08970v1 |
| https://arxiv.org/pdf/1909.08970v1.pdf | |
| PWC | https://paperswithcode.com/paper/run-through-the-streets-a-new-dataset-and |
| Repo | |
| Framework | |
Variational Information Bottleneck for Unsupervised Clustering: Deep Gaussian Mixture Embedding
| Title | Variational Information Bottleneck for Unsupervised Clustering: Deep Gaussian Mixture Embedding |
| Authors | Yigit Ugur, George Arvanitakis, Abdellatif Zaidi |
| Abstract | In this paper, we develop an unsupervised generative clustering framework that combines the Variational Information Bottleneck and the Gaussian Mixture Model. Specifically, in our approach, we use the Variational Information Bottleneck method and model the latent space as a mixture of Gaussians. We derive a bound on the cost function of our model that generalizes the Evidence Lower Bound (ELBO) and provide a variational inference type algorithm that allows computing it. In the algorithm, the coders’ mappings are parametrized using neural networks, and the bound is approximated by Monte Carlo sampling and optimized with stochastic gradient descent. Numerical results on real datasets are provided to support the efficiency of our method. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11741v3 |
| https://arxiv.org/pdf/1905.11741v3.pdf | |
| PWC | https://paperswithcode.com/paper/variational-information-bottleneck-for |
| Repo | |
| Framework | |
Challenges in Search on Streaming Services: Netflix Case Study
| Title | Challenges in Search on Streaming Services: Netflix Case Study |
| Authors | Sudarshan Lamkhede, Sudeep Das |
| Abstract | We discuss salient challenges of building a search experience for a streaming media service such as Netflix. We provide an overview of the role of recommendations within the search context to aid content discovery and support searches for unavailable (out-of-catalog) entities. We also stress the importance of keystroke-level instant search experience, and the technical challenges associated with implementing it across different devices and languages for a global audience. |
| Tasks | |
| Published | 2019-03-11 |
| URL | http://arxiv.org/abs/1903.04638v1 |
| http://arxiv.org/pdf/1903.04638v1.pdf | |
| PWC | https://paperswithcode.com/paper/challenges-in-search-on-streaming-services |
| Repo | |
| Framework | |
Enhancing Passive Non-Line-of-Sight Imaging Using Polarization Cues
| Title | Enhancing Passive Non-Line-of-Sight Imaging Using Polarization Cues |
| Authors | Kenichiro Tanaka, Yasuhiro Mukaigawa, Achuta Kadambi |
| Abstract | This paper presents a method of passive non-line-of-sight (NLOS) imaging using polarization cues. A key observation is that the oblique light has a different polarimetric signal. It turns out this effect is due to the polarization axis rotation, a phenomena which can be used to better condition the light transport matrix for non-line-of-sight imaging. Our analysis and results show that the use of a polarizer in front of the camera is not only a separate technique, but it can be seen as an enhancement technique for more advanced forms of passive NLOS imaging. For example, this paper shows that polarization can enhance passive NLOS imaging both with and without occluders. In all tested cases, despite the light attenuation from polarization optics, recovery of the occluded images is improved. |
| Tasks | |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1911.12906v1 |
| https://arxiv.org/pdf/1911.12906v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-passive-non-line-of-sight-imaging |
| Repo | |
| Framework | |
How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question?
| Title | How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question? |
| Authors | Yaoli Mao, Dakuo Wang, Michael Muller, Kush R. Varshney, Ioana Baldini, Casey Dugan, AleksandraMojsilović |
| Abstract | In recent years there has been an increasing trend in which data scientists and domain experts work together to tackle complex scientific questions. However, such collaborations often face challenges. In this paper, we aim to decipher this collaboration complexity through a semi-structured interview study with 22 interviewees from teams of bio-medical scientists collaborating with data scientists. In the analysis, we adopt the Olsons’ four-dimensions framework proposed in Distance Matters to code interview transcripts. Our findings suggest that besides the glitches in the collaboration readiness, technology readiness, and coupling of work dimensions, the tensions that exist in the common ground building process influence the collaboration outcomes, and then persist in the actual collaboration process. In contrast to prior works’ general account of building a high level of common ground, the breakdowns of content common ground together with the strengthen of process common ground in this process is more beneficial for scientific discovery. We discuss why that is and what the design suggestions are, and conclude the paper with future directions and limitations. |
| Tasks | |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1909.03486v1 |
| https://arxiv.org/pdf/1909.03486v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-data-scientists-work-together-with-domain |
| Repo | |
| Framework | |
Extending Causal Models from Machines into Humans
| Title | Extending Causal Models from Machines into Humans |
| Authors | Severin Kacianka, Amjad Ibrahim, Alexander Pretschner, Alexander Trende, Andreas Lüdtke |
| Abstract | Causal Models are increasingly suggested as a means to reason about the behavior of cyber-physical systems in socio-technical contexts. They allow us to analyze courses of events and reason about possible alternatives. Until now, however, such reasoning is confined to the technical domain and limited to single systems or at most groups of systems. The humans that are an integral part of any such socio-technical system are usually ignored or dealt with by “expert judgment”. We show how a technical causal model can be extended with models of human behavior to cover the complexity and interplay between humans and technical systems. This integrated socio-technical causal model can then be used to reason not only about actions and decisions taken by the machine, but also about those taken by humans interacting with the system. In this paper we demonstrate the feasibility of merging causal models about machines with causal models about humans and illustrate the usefulness of this approach with a highly automated vehicle example. |
| Tasks | |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1911.04869v1 |
| https://arxiv.org/pdf/1911.04869v1.pdf | |
| PWC | https://paperswithcode.com/paper/extending-causal-models-from-machines-into |
| Repo | |
| Framework | |
Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification
| Title | Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification |
| Authors | T M Feroz Ali, Kalpesh K Patel, Rajbabu Velmurugan, Subhasis Chaudhuri |
| Abstract | Person re-identification addresses the problem of matching pedestrian images across disjoint camera views. Design of feature descriptor and distance metric learning are the two fundamental tasks in person re-identification. In this paper, we propose a metric learning framework for person re-identification, where the discriminative metric space is learned using Kernel Fisher Discriminant Analysis (KFDA), to simultaneously maximize the inter-class variance as well as minimize the intra-class variance. We derive a Mahalanobis metric induced by KFDA and argue that KFDA is efficient to be applied for metric learning in person re-identification. We also show how the efficiency of KFDA in metric learning can be further enhanced for person re-identification by using two simple yet efficient multiple kernel learning methods. We conduct extensive experiments on three benchmark datasets for person re-identification and demonstrate that the proposed approaches have competitive performance with state-of-the-art methods. |
| Tasks | Metric Learning, Person Re-Identification |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03923v1 |
| https://arxiv.org/pdf/1910.03923v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-kernel-fisher-discriminant-metric |
| Repo | |
| Framework | |
View Confusion Feature Learning for Person Re-identification
| Title | View Confusion Feature Learning for Person Re-identification |
| Authors | Fangyi Liu, Lei Zhang |
| Abstract | Person re-identification is an important task in video surveillance that aims to associate people across camera views at different locations and time. View variability is always a challenging problem seriously degrading person re-identification performance. Most of the existing methods either focus on how to learn view invariant feature or how to combine view-wise features. In this paper, we mainly focus on how to learn view-invariant features by getting rid of view specific information through a view confusion learning mechanism. Specifically, we propose an end-toend trainable framework, called View Confusion Feature Learning (VCFL), for person Re-ID across cameras. To the best of our knowledge, VCFL is originally proposed to learn view-invariant identity-wise features, and it is a kind of combination of view-generic and view-specific methods. Classifiers and feature centers are utilized to achieve view confusion. Furthermore, we extract sift-guided features by using bag-of-words model to help supervise the training of deep networks and enhance the view invariance of features. In experiments, our approach is validated on three benchmark datasets including CUHK01, CUHK03, and MARKET1501, which show the superiority of the proposed method over several state-of-the-art approaches |
| Tasks | Person Re-Identification |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03849v1 |
| https://arxiv.org/pdf/1910.03849v1.pdf | |
| PWC | https://paperswithcode.com/paper/view-confusion-feature-learning-for-person-re |
| Repo | |
| Framework | |
Adaptive Communication Bounds for Distributed Online Learning
| Title | Adaptive Communication Bounds for Distributed Online Learning |
| Authors | Michael Kamp, Mario Boley, Michael Mock, Daniel Keren, Assaf Schuster, Izchak Sharfman |
| Abstract | We consider distributed online learning protocols that control the exchange of information between local learners in a round-based learning scenario. The learning performance of such a protocol is intuitively optimal if approximately the same loss is incurred as in a hypothetical serial setting. If a protocol accomplishes this, it is inherently impossible to achieve a strong communication bound at the same time. In the worst case, every input is essential for the learning performance, even for the serial setting, and thus needs to be exchanged between the local learners. However, it is reasonable to demand a bound that scales well with the hardness of the serialized prediction problem, as measured by the loss received by a serial online learning algorithm. We provide formal criteria based on this intuition and show that they hold for a simplified version of a previously published protocol. |
| Tasks | |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12896v1 |
| https://arxiv.org/pdf/1911.12896v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-communication-bounds-for-distributed |
| Repo | |
| Framework | |
