Paper Group ANR 1592
Exploiting Event Log Event Attributes in RNN Based Prediction. SGD: General Analysis and Improved Rates. Sound Event Recognition in a Smart City Surveillance Context. Distributed Learning with Sublinear Communication. Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog System. CNN-based Survival Model for Pancreatic Du …
Exploiting Event Log Event Attributes in RNN Based Prediction
| Title | Exploiting Event Log Event Attributes in RNN Based Prediction |
| Authors | Markku Hinkka, Teemu Lehto, Keijo Heljanko |
| Abstract | In predictive process analytics, current and historical process data in event logs is used to predict the future, e.g., to predict the next activity or how long a process will still require to complete. Recurrent neural networks (RNN) and its subclasses have been demonstrated to be well suited for creating prediction models. Thus far, event attributes have not been fully utilized in these models. The biggest challenge in exploiting them in prediction models is the potentially large amount of event attributes and attribute values. We present a novel clustering technique that allows for trade-offs between prediction accuracy and the time needed for model training and prediction. As an additional finding, we also find that this clustering method combined with having raw event attribute values in some cases provides even better prediction accuracy at the cost of additional time required for training and prediction. |
| Tasks | |
| Published | 2019-04-15 |
| URL | https://arxiv.org/abs/1904.06895v3 |
| https://arxiv.org/pdf/1904.06895v3.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-event-log-data-attributes-in-rnn |
| Repo | |
| Framework | |
SGD: General Analysis and Improved Rates
| Title | SGD: General Analysis and Improved Rates |
| Authors | Robert Mansel Gower, Nicolas Loizou, Xun Qian, Alibek Sailanbayev, Egor Shulgin, Peter Richtarik |
| Abstract | We propose a general yet simple theorem describing the convergence of SGD under the arbitrary sampling paradigm. Our theorem describes the convergence of an infinite array of variants of SGD, each of which is associated with a specific probability law governing the data selection rule used to form mini-batches. This is the first time such an analysis is performed, and most of our variants of SGD were never explicitly considered in the literature before. Our analysis relies on the recently introduced notion of expected smoothness and does not rely on a uniform bound on the variance of the stochastic gradients. By specializing our theorem to different mini-batching strategies, such as sampling with replacement and independent sampling, we derive exact expressions for the stepsize as a function of the mini-batch size. With this we can also determine the mini-batch size that optimizes the total complexity, and show explicitly that as the variance of the stochastic gradient evaluated at the minimum grows, so does the optimal mini-batch size. For zero variance, the optimal mini-batch size is one. Moreover, we prove insightful stepsize-switching rules which describe when one should switch from a constant to a decreasing stepsize regime. |
| Tasks | |
| Published | 2019-01-27 |
| URL | http://arxiv.org/abs/1901.09401v4 |
| http://arxiv.org/pdf/1901.09401v4.pdf | |
| PWC | https://paperswithcode.com/paper/sgd-general-analysis-and-improved-rates |
| Repo | |
| Framework | |
Sound Event Recognition in a Smart City Surveillance Context
| Title | Sound Event Recognition in a Smart City Surveillance Context |
| Authors | Tito Spadini, Dimitri Leandro de Oliveira Silva, Ricardo Suyama |
| Abstract | Due to the growing demand for improving surveillance capabilities in smart cities, systems need to be developed to provide better monitoring capabilities to competent authorities, agencies responsible for strategic resource management, and emergency call centers. This work assumes that, as a complementary monitoring solution, the use of a system capable of detecting the occurrence of sound events, performing the Sound Events Recognition (SER) task, is highly convenient. In order to contribute to the classification of such events, this paper explored several classifiers over the SESA dataset, composed of audios of three hazard classes (gunshots, explosions, and sirens) and a class of casual sounds that could be misinterpreted as some of the other sounds. The best result was obtained by SGD, with an accuracy of 72.13% with 6.81 ms classification time, reinforcing the viability of such an approach. |
| Tasks | |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1910.12369v2 |
| https://arxiv.org/pdf/1910.12369v2.pdf | |
| PWC | https://paperswithcode.com/paper/sound-event-recognition-in-a-smart-city |
| Repo | |
| Framework | |
Distributed Learning with Sublinear Communication
| Title | Distributed Learning with Sublinear Communication |
| Authors | Jayadev Acharya, Christopher De Sa, Dylan J. Foster, Karthik Sridharan |
| Abstract | In distributed statistical learning, $N$ samples are split across $m$ machines and a learner wishes to use minimal communication to learn as well as if the examples were on a single machine. This model has received substantial interest in machine learning due to its scalability and potential for parallel speedup. However, in high-dimensional settings, where the number examples is smaller than the number of features (“dimension”), the speedup afforded by distributed learning may be overshadowed by the cost of communicating a single example. This paper investigates the following question: When is it possible to learn a $d$-dimensional model in the distributed setting with total communication sublinear in $d$? Starting with a negative result, we show that for learning $\ell_1$-bounded or sparse linear models, no algorithm can obtain optimal error until communication is linear in dimension. Our main result is that that by slightly relaxing the standard boundedness assumptions for linear models, we can obtain distributed algorithms that enjoy optimal error with communication logarithmic in dimension. This result is based on a family of algorithms that combine mirror descent with randomized sparsification/quantization of iterates, and extends to the general stochastic convex optimization model. |
| Tasks | Quantization |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.11259v2 |
| http://arxiv.org/pdf/1902.11259v2.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-learning-with-sublinear |
| Repo | |
| Framework | |
Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog System
| Title | Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog System |
| Authors | Richard Csaky |
| Abstract | This is the application document for the 2019 Amazon Alexa competition. We give an overall vision of our conversational experience, as well as a sample conversation that we would like our dialog system to achieve by the end of the competition. We believe personalization, knowledge, and self-play are important components towards better chatbots. These are further highlighted by our detailed system architecture proposal and novelty section. Finally, we describe how we would ensure an engaging experience, how this research would impact the field, and related work. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05016v1 |
| https://arxiv.org/pdf/1909.05016v1.pdf | |
| PWC | https://paperswithcode.com/paper/proposal-towards-a-personalized-knowledge |
| Repo | |
| Framework | |
CNN-based Survival Model for Pancreatic Ductal Adenocarcinoma in Medical Imaging
| Title | CNN-based Survival Model for Pancreatic Ductal Adenocarcinoma in Medical Imaging |
| Authors | Yucheng Zhang, Edrise M. Lobo-Mueller, Paul Karanicolas, Steven Gallinger, Masoom A. Haider, Farzad Khalvati |
| Abstract | Cox proportional hazard model (CPH) is commonly used in clinical research for survival analysis. In quantitative medical imaging (radiomics) studies, CPH plays an important role in feature reduction and modeling. However, the underlying linear assumption of CPH model limits the prognostic performance. In addition, the multicollinearity of radiomic features and multiple testing problem further impedes the CPH models performance. In this work, using transfer learning, a convolutional neural network (CNN) based survival model was built and tested on preoperative CT images of resectable Pancreatic Ductal Adenocarcinoma (PDAC) patients. The proposed CNN-based survival model outperformed the traditional CPH-based radiomics approach in terms of concordance index by 22%, providing a better fit for patients’ survival patterns. The proposed CNN-based survival model outperforms CPH-based radiomics pipeline in PDAC prognosis. This approach offers a better fit for survival patterns based on CT images and overcomes the limitations of conventional survival models. |
| Tasks | Survival Analysis, Transfer Learning |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10729v1 |
| https://arxiv.org/pdf/1906.10729v1.pdf | |
| PWC | https://paperswithcode.com/paper/cnn-based-survival-model-for-pancreatic |
| Repo | |
| Framework | |
Marine Mammal Species Classification using Convolutional Neural Networks and a Novel Acoustic Representation
| Title | Marine Mammal Species Classification using Convolutional Neural Networks and a Novel Acoustic Representation |
| Authors | Mark Thomas, Bruce Martin, Katie Kowarski, Briand Gaudet, Stan Matwin |
| Abstract | Research into automated systems for detecting and classifying marine mammals in acoustic recordings is expanding internationally due to the necessity to analyze large collections of data for conservation purposes. In this work, we present a Convolutional Neural Network that is capable of classifying the vocalizations of three species of whales, non-biological sources of noise, and a fifth class pertaining to ambient noise. In this way, the classifier is capable of detecting the presence and absence of whale vocalizations in an acoustic recording. Through transfer learning, we show that the classifier is capable of learning high-level representations and can generalize to additional species. We also propose a novel representation of acoustic signals that builds upon the commonly used spectrogram representation by way of interpolating and stacking multiple spectrograms produced using different Short-time Fourier Transform (STFT) parameters. The proposed representation is particularly effective for the task of marine mammal species classification where the acoustic events we are attempting to classify are sensitive to the parameters of the STFT. |
| Tasks | Transfer Learning |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.13188v1 |
| https://arxiv.org/pdf/1907.13188v1.pdf | |
| PWC | https://paperswithcode.com/paper/marine-mammal-species-classification-using |
| Repo | |
| Framework | |
Optimizing Sequential Medical Treatments with Auto-Encoding Heuristic Search in POMDPs
| Title | Optimizing Sequential Medical Treatments with Auto-Encoding Heuristic Search in POMDPs |
| Authors | Luchen Li, Matthieu Komorowski, Aldo A. Faisal |
| Abstract | Health-related data is noisy and stochastic in implying the true physiological states of patients, limiting information contained in single-moment observations for sequential clinical decision making. We model patient-clinician interactions as partially observable Markov decision processes (POMDPs) and optimize sequential treatment based on belief states inferred from history sequence. To facilitate inference, we build a variational generative model and boost state representation with a recurrent neural network (RNN), incorporating an auxiliary loss from sequence auto-encoding. Meanwhile, we optimize a continuous policy of drug levels with an actor-critic method where policy gradients are obtained from a stablized off-policy estimate of advantage function, with the value of belief state backed up by parallel best-first suffix trees. We exploit our methodology in optimizing dosages of vasopressor and intravenous fluid for sepsis patients using a retrospective intensive care dataset and evaluate the learned policy with off-policy policy evaluation (OPPE). The results demonstrate that modelling as POMDPs yields better performance than MDPs, and that incorporating heuristic search improves sample efficiency. |
| Tasks | Decision Making |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07465v1 |
| https://arxiv.org/pdf/1905.07465v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-sequential-medical-treatments-with |
| Repo | |
| Framework | |
Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking
| Title | Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking |
| Authors | TianXing Li, Zhi Yu, Edmund Phung, Brendan Duke, Irina Kezele, Parham Aarabi |
| Abstract | Recent works on convolutional neural networks (CNNs) for facial alignment have demonstrated unprecedented accuracy on a variety of large, publicly available datasets. However, the developed models are often both cumbersome and computationally expensive, and are not adapted to applications on resource restricted devices. In this work, we look into developing and training compact facial alignment models that feature fast inference speed and small deployment size, making them suitable for applications on the aforementioned category of devices. Our main contribution lies in designing such small models while maintaining high accuracy of facial alignment. The models we propose make use of light CNN architectures adapted to the facial alignment problem for accurate two-stage prediction of facial landmark coordinates from low-resolution output heatmaps. We further combine the developed facial tracker with a rendering method, and build a real-time makeup try-on demo that runs client-side in smartphone Web browsers. More results and demo are in our project page: http://research.modiface.com/makeup-try-on-cvprw2019/ |
| Tasks | |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02260v2 |
| https://arxiv.org/pdf/1906.02260v2.pdf | |
| PWC | https://paperswithcode.com/paper/lightweight-real-time-makeup-try-on-in-mobile |
| Repo | |
| Framework | |
A Books Recommendation Approach Based on Online Bookstore Data
| Title | A Books Recommendation Approach Based on Online Bookstore Data |
| Authors | Xinyu Wei, Jiahui Chen, Jing Chen, Bernie Liu |
| Abstract | In the era of information explosion, facing complex information, it is difficult for users to choose the information of interest, and businesses also need detailed information on ways to let the ad stand out. By this time, it is recommended that a good way. We firstly by using random interviews, simulations, asking experts, summarizes methods outlined the main factors affecting the scores of books that users drew. In order to further illustrate the impact of these factors, we also by combining the AHP consistency test, then fuzzy evaluation method, empowered each factor, influencing factors and the degree of influence come. For the second question, predict user evaluation of the listed books from the predict annex. First, given the books Annex labels, user data extraction scorebooks and mathematical analysis of data obtained from SPSS user preferences and then use software to nearest neighbor analysis to result in predicted value. |
| Tasks | |
| Published | 2019-06-15 |
| URL | https://arxiv.org/abs/1906.06542v1 |
| https://arxiv.org/pdf/1906.06542v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-books-recommendation-approach-based-on |
| Repo | |
| Framework | |
Less (Data) Is More: Why Small Data Holds the Key to the Future of Artificial Intelligence
| Title | Less (Data) Is More: Why Small Data Holds the Key to the Future of Artificial Intelligence |
| Authors | Ciro Greco, Andrea Polonioli, Jacopo Tagliabue |
| Abstract | The claims that big data holds the key to enterprise successes and that Artificial Intelligence is going to replace humanity have become increasingly more popular over the past few years, both in academia and in the industry. However, while these claims may indeed capture some truth, they have also been massively oversold, or so we contend here. The goal of this paper is two-fold. First, we provide a qualified defence of the value of less data within the context of AI. This is done by carefully reviewing two distinct problems for big data driven AI, namely a) the limited track record of Deep Learning in key areas such as Natural Language Processing, b) the regulatory and business significance of being able to learn from few data points. Second, we briefly sketch what we refer to as a case of AI with humans and for humans, namely an AI paradigm whereby the systems we build are privacy-oriented and focused on human-machine collaboration, not competition. Combining our claims above, we conclude that when seen through the lens of cognitively inspired AI, the bright future of the discipline is about less data, not more, and more humans, not fewer. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.10424v1 |
| https://arxiv.org/pdf/1907.10424v1.pdf | |
| PWC | https://paperswithcode.com/paper/less-data-is-more-why-small-data-holds-the |
| Repo | |
| Framework | |
Question-type Driven Question Generation
| Title | Question-type Driven Question Generation |
| Authors | Wenjie Zhou, Minghua Zhang, Yunfang Wu |
| Abstract | Question generation is a challenging task which aims to ask a question based on an answer and relevant context. The existing works suffer from the mismatching between question type and answer, i.e. generating a question with type $how$ while the answer is a personal name. We propose to automatically predict the question type based on the input answer and context. Then, the question type is fused into a seq2seq model to guide the question generation, so as to deal with the mismatching problem. We achieve significant improvement on the accuracy of question type prediction and finally obtain state-of-the-art results for question generation on both SQuAD and MARCO datasets. |
| Tasks | Question Generation |
| Published | 2019-08-31 |
| URL | https://arxiv.org/abs/1909.00140v1 |
| https://arxiv.org/pdf/1909.00140v1.pdf | |
| PWC | https://paperswithcode.com/paper/question-type-driven-question-generation |
| Repo | |
| Framework | |
Machine Learning Approaches for Detecting the Depression from Resting-State Electroencephalogram (EEG): A Review Study
| Title | Machine Learning Approaches for Detecting the Depression from Resting-State Electroencephalogram (EEG): A Review Study |
| Authors | Milena Čukić Radenković, Victoria Lopez Lopez |
| Abstract | In this paper, we aimed at reviewing present literature on employing nonlinear analysis in combination with machine learning methods, in depression detection or prediction task. We are focusing on an affordable data-driven approach, applicable for everyday clinical practice, and in particular, those based on electroencephalographic (EEG) recordings. Among those studies utilizing EEG, we are discussing a group of applications used for detecting the depression based on the resting state EEG (detection studies) and interventional studies (using stimulus in their protocols or aiming to predict the outcome of therapy). We conclude with a discussion and review of guidelines to improve the reliability of developed models that could serve the improvement of diagnostic and more accurate treatment of depression. |
| Tasks | EEG |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.03115v1 |
| https://arxiv.org/pdf/1909.03115v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-approaches-for-detecting-the |
| Repo | |
| Framework | |
Face Reflectance and Geometry Modeling via Differentiable Ray Tracing
| Title | Face Reflectance and Geometry Modeling via Differentiable Ray Tracing |
| Authors | Abdallah Dib, Gaurav Bharaj, Junghyun Ahn, Cedric Thebault, Philippe-Henri Gosselin, Louis Chevallier |
| Abstract | We present a novel strategy to automatically reconstruct 3D faces from monocular images with explicitly disentangled facial geometry (pose, identity and expression), reflectance (diffuse and specular albedo), and self-shadows. The scene lights are modeled as a virtual light stage with pre-oriented area lights used in conjunction with differentiable Monte-Carlo ray tracing to optimize the scene and face parameters. With correctly disentangled self-shadows and specular reflection parameters, we can not only obtain robust facial geometry reconstruction, but also gain explicit control over these parameters, with several practical applications. We can change facial expressions with accurate resultant self-shadows or relight the scene and obtain accurate specular reflection and several other parameter combinations. |
| Tasks | |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.05200v1 |
| https://arxiv.org/pdf/1910.05200v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-reflectance-and-geometry-modeling-via |
| Repo | |
| Framework | |
Private Identity Testing for High-Dimensional Distributions
| Title | Private Identity Testing for High-Dimensional Distributions |
| Authors | Clément L. Canonne, Gautam Kamath, Audra McMillan, Jonathan Ullman, Lydia Zakynthinou |
| Abstract | In this work we present novel differentially private identity (goodness-of-fit) testers for natural and widely studied classes of multivariate product distributions: Gaussians in $\mathbb{R}^d$ with known covariance and product distributions over ${\pm 1}^{d}$. Our testers have improved sample complexity compared to those derived from previous techniques, and are the first testers whose sample complexity matches the order-optimal minimax sample complexity of $O(d^{1/2}/\alpha^2)$ in many parameter regimes. We construct two types of testers, exhibiting tradeoffs between sample complexity and computational complexity. Finally, we provide a two-way reduction between testing a subclass of multivariate product distributions and testing univariate distributions, and thereby obtain upper and lower bounds for testing this subclass of product distributions. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11947v2 |
| https://arxiv.org/pdf/1905.11947v2.pdf | |
| PWC | https://paperswithcode.com/paper/private-identity-testing-for-high-dimensional |
| Repo | |
| Framework | |
