January 26, 2020

3131 words 15 mins read

Paper Group ANR 1395

Semisupervised Clustering by Queries and Locally Encodable Source Coding. Bayesian inversion for nanowire field-effect sensors. Prediction of Workplace Injuries. Feature-Set-Engineering for Detecting Freezing of Gait in Parkinson’s Disease using Deep Recurrent Neural Networks. Learning to Interactively Learn and Assist. Automatic Surface Area and V …

Semisupervised Clustering by Queries and Locally Encodable Source Coding


Title	Semisupervised Clustering by Queries and Locally Encodable Source Coding
Authors	Arya Mazumdar, Soumyabrata Pal
Abstract	Source coding is the canonical problem of data compression in information theory. In a {\em locally encodable} source coding, each compressed bit depends on only few bits of the input. In this paper, we show that a recently popular model of semisupervised clustering is equivalent to locally encodable source coding. In this model, the task is to perform multiclass labeling of unlabeled elements. At the beginning, we can ask in parallel a set of simple queries to an oracle who provides (possibly erroneous) binary answers to the queries. The queries cannot involve more than two (or a fixed constant number $\Delta$ of) elements. Now the labeling of all the elements (or clustering) must be performed based on the (noisy) query answers. The goal is to recover all the correct labelings while minimizing the number of such queries. The equivalence to locally encodable source codes leads us to find lower bounds on the number of queries required in variety of scenarios. We are also able to show fundamental limitations of pairwise `same cluster’ queries - and propose pairwise AND queries, that provably performs better in many situations. \|
Tasks
Published	2019-03-31
URL	http://arxiv.org/abs/1904.00507v1
PDF	http://arxiv.org/pdf/1904.00507v1.pdf
PWC	https://paperswithcode.com/paper/semisupervised-clustering-by-queries-and
Repo
Framework

Bayesian inversion for nanowire field-effect sensors


Title	Bayesian inversion for nanowire field-effect sensors
Authors	Amirreza Khodadadian, Benjamin Stadlbauer, Clemens Heitzinger
Abstract	Nanowire field-effect sensors have recently been developed for label-free detection of biomolecules. In this work, we introduce a computational technique based on Bayesian estimation to determine the physical parameters of the sensor and, more importantly, the properties of the analyte molecules. To that end, we first propose a PDE based model to simulate the device charge transport and electrochemical behavior. Then, the adaptive Metropolis algorithm with delayed rejection (DRAM) is applied to estimate the posterior distribution of unknown parameters, namely molecule charge density, molecule density, doping concentration, and electron and hole mobilities. We determine the device and molecules properties simultaneously, and we also calculate the molecule density as the only parameter after having determined the device parameters. This approach makes it possible not only to determine unknown parameters, but it also shows how well each parameter can be determined by yielding the probability density function (pdf).
Tasks
Published	2019-04-12
URL	https://arxiv.org/abs/1904.09848v2
PDF	https://arxiv.org/pdf/1904.09848v2.pdf
PWC	https://paperswithcode.com/paper/190409848
Repo
Framework

Prediction of Workplace Injuries


Title	Prediction of Workplace Injuries
Authors	Mehdi Sadeqi, Azin Asgarian, Ariel Sibilia
Abstract	Workplace injuries result in substantial human and financial losses. As reported by the International Labour Organization (ILO), there are more than 374 million work-related injuries reported every year. In this study, we investigate the problem of injury risk prediction and prevention in a work environment. While injuries represent a significant number across all organizations, they are rare events within a single organization. Hence, collecting a sufficiently large dataset from a single organization is extremely difficult. In addition, the collected datasets are often highly imbalanced which increases the problem difficulty. Finally, risk predictions need to provide additional context for injuries to be prevented. We propose and evaluate the following for a complete solution: 1) several ensemble-based resampling methods to address the class imbalance issues, 2) a novel transfer learning approach to transfer the knowledge across organizations, and 3) various techniques to uncover the association and causal effect of different variables on injury risk, while controlling for relevant confounding factors.
Tasks	Transfer Learning
Published	2019-06-05
URL	https://arxiv.org/abs/1906.03080v1
PDF	https://arxiv.org/pdf/1906.03080v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-workplace-injuries
Repo
Framework

Feature-Set-Engineering for Detecting Freezing of Gait in Parkinson’s Disease using Deep Recurrent Neural Networks


Title	Feature-Set-Engineering for Detecting Freezing of Gait in Parkinson’s Disease using Deep Recurrent Neural Networks
Authors	Spyroula Masiala, Willem Huijbers, Martin Atzmueller
Abstract	Freezing of gait (FoG) is a common gait disability in Parkinson’s disease, that usually appears in its advanced stage. Freeze episodes are associated with falls, injuries, and psychological consequences, negatively affecting the patients’ quality of life. For detecting FoG episodes automatically, a highly accurate detection method is necessary. This paper presents an approach for detecting FoG episodes utilizing a deep recurrent neural network (RNN) on 3D-accelerometer measurements. We investigate suitable features and feature combinations extracted from the sensors’ time series data. Specifically, for detecting FoG episodes, we apply a deep RNN with Long Short-Term Memory cells. In our experiments, we perform both user dependent and user independent experiments, to detect freeze episodes. Our experimental results show that the frequency domain features extracted from the trunk sensor are the most informative feature group in the subject independent method, achieving an average AUC score of 93%, Specificity of 90% and Sensitivity of 81%. Moreover, frequency and statistical features of all the sensors are identified as the best single input for the subject dependent method, achieving an average AUC score of 97%, Specificity of 96% and Sensitivity of 87%. Overall, in a comparison to state-of-the-art approaches from literature as baseline methods, our proposed approach outperforms these significantly.
Tasks	Time Series
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03428v1
PDF	https://arxiv.org/pdf/1909.03428v1.pdf
PWC	https://paperswithcode.com/paper/feature-set-engineering-for-detecting
Repo
Framework

Learning to Interactively Learn and Assist


Title	Learning to Interactively Learn and Assist
Authors	Mark Woodward, Chelsea Finn, Karol Hausman
Abstract	When deploying autonomous agents in the real world, we need effective ways of communicating objectives to them. Traditional skill learning has revolved around reinforcement and imitation learning, each with rigid constraints on the format of information exchanged between the human and the agent. While scalar rewards carry little information, demonstrations require significant effort to provide and may carry more information than is necessary. Furthermore, rewards and demonstrations are often defined and collected before training begins, when the human is most uncertain about what information would help the agent. In contrast, when humans communicate objectives with each other, they make use of a large vocabulary of informative behaviors, including non-verbal communication, and often communicate throughout learning, responding to observed behavior. In this way, humans communicate intent with minimal effort. In this paper, we propose such interactive learning as an alternative to reward or demonstration-driven learning. To accomplish this, we introduce a multi-agent training framework that enables an agent to learn from another agent who knows the current task. Through a series of experiments, we demonstrate the emergence of a variety of interactive learning behaviors, including information-sharing, information-seeking, and question-answering. Most importantly, we find that our approach produces an agent that is capable of learning interactively from a human user, without a set of explicit demonstrations or a reward function, and achieving significantly better performance cooperatively with a human than a human performing the task alone.
Tasks	Imitation Learning, Question Answering
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10187v3
PDF	https://arxiv.org/pdf/1906.10187v3.pdf
PWC	https://paperswithcode.com/paper/learning-to-interactively-learn-and-assist
Repo
Framework

Automatic Surface Area and Volume Prediction on Ellipsoidal Ham using Deep Learning


Title	Automatic Surface Area and Volume Prediction on Ellipsoidal Ham using Deep Learning
Authors	Y. S. Gan, Sze-Teng Liong, Yen-Chang Huang
Abstract	This paper presents novel methods to predict the surface and volume of the ham through a camera. This implies that the conventional weight measurement to obtain in the object’s volume can be neglected and hence it is economically effective. Both of the measurements are obtained in the following two ways: manually and automatically. The former is assume as the true or exact measurement and the latter is through a computer vision technique with some geometrical analysis that includes mathematical derived functions. For the automatic implementation, most of the existing approaches extract the features of the food material based on handcrafted features and to the best of our knowledge this is the first attempt to estimate the surface area and volume on ham with deep learning features. We address the estimation task with a Mask Region-based CNN (Mask R-CNN) approach, which well performs the ham detection and semantic segmentation from a video. The experimental results demonstrate that the algorithm proposed is robust as promising surface area and volume estimation are obtained for two angles of the ellipsoidal ham (i.e., horizontal and vertical positions). Specifically, in the vertical ham point of view, it achieves an overall accuracy up to 95% whereas the horizontal ham reaches 80% of accuracy.
Tasks	Semantic Segmentation
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04947v1
PDF	http://arxiv.org/pdf/1901.04947v1.pdf
PWC	https://paperswithcode.com/paper/automatic-surface-area-and-volume-prediction
Repo
Framework

Pre-trained Language Model Representations for Language Generation


Title	Pre-trained Language Model Representations for Language Generation
Authors	Sergey Edunov, Alexei Baevski, Michael Auli
Abstract	Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and apply it to neural machine translation and abstractive summarization. We find that pre-trained representations are most effective when added to the encoder network which slows inference by only 14%. Our experiments in machine translation show gains of up to 5.3 BLEU in a simulated resource-poor setup. While returns diminish with more labeled data, we still observe improvements when millions of sentence-pairs are available. Finally, on abstractive summarization we achieve a new state of the art on the full text version of CNN/DailyMail.
Tasks	Abstractive Text Summarization, Language Modelling, Machine Translation, Text Generation
Published	2019-03-22
URL	http://arxiv.org/abs/1903.09722v2
PDF	http://arxiv.org/pdf/1903.09722v2.pdf
PWC	https://paperswithcode.com/paper/pre-trained-language-model-representations
Repo
Framework

Distilling Knowledge From a Deep Pose Regressor Network


Title	Distilling Knowledge From a Deep Pose Regressor Network
Authors	Muhamad Risqi U. Saputra, Pedro P. B. de Gusmao, Yasin Almalioglu, Andrew Markham, Niki Trigoni
Abstract	This paper presents a novel method to distill knowledge from a deep pose regressor network for efficient Visual Odometry (VO). Standard distillation relies on “dark knowledge” for successful knowledge transfer. As this knowledge is not available in pose regression and the teacher prediction is not always accurate, we propose to emphasize the knowledge transfer only when we trust the teacher. We achieve this by using teacher loss as a confidence score which places variable relative importance on the teacher prediction. We inject this confidence score to the main training task via Attentive Imitation Loss (AIL) and when learning the intermediate representation of the teacher through Attentive Hint Training (AHT) approach. To the best of our knowledge, this is the first work which successfully distill the knowledge from a deep pose regression network. Our evaluation on the KITTI and Malaga dataset shows that we can keep the student prediction close to the teacher with up to 92.95% parameter reduction and 2.12x faster in computation time.
Tasks	Transfer Learning, Visual Odometry
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00858v1
PDF	https://arxiv.org/pdf/1908.00858v1.pdf
PWC	https://paperswithcode.com/paper/distilling-knowledge-from-a-deep-pose
Repo
Framework

MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms


Title	MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
Authors	Aida Amini, Saadia Gabriel, Peter Lin, Rik Koncel-Kedziorski, Yejin Choi, Hannaneh Hajishirzi
Abstract	We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver that learns to map problems to operation programs. Due to annotation challenges, current datasets in this domain have been either relatively small in scale or did not offer precise operational annotations over diverse problem types. We introduce a new representation language to model precise operation programs corresponding to each math problem that aim to improve both the performance and the interpretability of the learned models. Using this representation language, our new dataset, MathQA, significantly enhances the AQuA dataset with fully-specified operational programs. We additionally introduce a neural sequence-to-program model enhanced with automatic problem categorization. Our experiments show improvements over competitive baselines in our MathQA as well as the AQuA dataset. The results are still significantly lower than human performance indicating that the dataset poses new challenges for future research. Our dataset is available at: https://math-qa.github.io/math-QA/
Tasks	Math Word Problem Solving
Published	2019-05-30
URL	https://arxiv.org/abs/1905.13319v1
PDF	https://arxiv.org/pdf/1905.13319v1.pdf
PWC	https://paperswithcode.com/paper/mathqa-towards-interpretable-math-word
Repo
Framework

Towards Evaluating User Profiling Methods Based on Explicit Ratings on Item Features


Title	Towards Evaluating User Profiling Methods Based on Explicit Ratings on Item Features
Authors	Luca Luciano Costanzo, Yashar Deldjoo, Maurizio Ferrari Dacrema, Markus Schedl, Paolo Cremonesi
Abstract	In order to improve the accuracy of recommendations, many recommender systems nowadays use side information beyond the user rating matrix, such as item content. These systems build user profiles as estimates of users’ interest on content (e.g., movie genre, director or cast) and then evaluate the performance of the recommender system as a whole e.g., by their ability to recommend relevant and novel items to the target user. The user profile modelling stage, which is a key stage in content-driven RS is barely properly evaluated due to the lack of publicly available datasets that contain user preferences on content features of items. To raise awareness of this fact, we investigate differences between explicit user preferences and implicit user profiles. We create a dataset of explicit preferences towards content features of movies, which we release publicly. We then compare the collected explicit user feature preferences and implicit user profiles built via state-of-the-art user profiling models. Our results show a maximum average pairwise cosine similarity of 58.07% between the explicit feature preferences and the implicit user profiles modelled by the best investigated profiling method and considering movies’ genres only. For actors and directors, this maximum similarity is only 9.13% and 17.24%, respectively. This low similarity between explicit and implicit preference models encourages a more in-depth study to investigate and improve this important user profile modelling step, which will eventually translate into better recommendations.
Tasks	Recommendation Systems
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11055v1
PDF	https://arxiv.org/pdf/1908.11055v1.pdf
PWC	https://paperswithcode.com/paper/towards-evaluating-user-profiling-methods
Repo
Framework

Towards Supervised Extractive Text Summarization via RNN-based Sequence Classification


Title	Towards Supervised Extractive Text Summarization via RNN-based Sequence Classification
Authors	Eduardo Brito, Max Lübbering, David Biesner, Lars Patrick Hillebrand, Christian Bauckhage
Abstract	This article briefly explains our submitted approach to the DocEng’19 competition on extractive summarization. We implemented a recurrent neural network based model that learns to classify whether an article’s sentence belongs to the corresponding extractive summary or not. We bypass the lack of large annotated news corpora for extractive summarization by generating extractive summaries from abstractive ones, which are available from the CNN corpus.
Tasks	Text Summarization
Published	2019-11-13
URL	https://arxiv.org/abs/1911.06121v1
PDF	https://arxiv.org/pdf/1911.06121v1.pdf
PWC	https://paperswithcode.com/paper/towards-supervised-extractive-text
Repo
Framework

Leveraging Multi-view Image Sets for Unsupervised Intrinsic Image Decomposition and Highlight Separation


Title	Leveraging Multi-view Image Sets for Unsupervised Intrinsic Image Decomposition and Highlight Separation
Authors	Renjiao Yi, Ping Tan, Stephen Lin
Abstract	We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos online, which exhibit large illumination variations that make them suitable for training of reflectance separation and can facilitate object-level decomposition. The main contribution of our approach is a proposed image representation based on local color distributions that allows training to be insensitive to the local misalignments of multi-view images. In addition, we present a new guidance cue for unsupervised training that exploits synergy between highlight separation and intrinsic image decomposition. Over a broad range of objects, our technique is shown to yield state-of-the-art results for both of these tasks.
Tasks	Intrinsic Image Decomposition
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07262v1
PDF	https://arxiv.org/pdf/1911.07262v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-multi-view-image-sets-for
Repo
Framework

Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks


Title	Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks
Authors	Stefano Savazzi, Monica Nicoli, Vittorio Rampa
Abstract	Federated learning (FL) is emerging as a new paradigm to train machine learning models in distributed systems. Rather than sharing, and disclosing, the training dataset with the server, the model parameters (e.g. neural networks weights and biases) are optimized collectively by large populations of interconnected devices, acting as local learners. FL can be applied to power-constrained IoT devices with slow and sporadic connections. In addition, it does not need data to be exported to third parties, preserving privacy. Despite these benefits, a main limit of existing approaches is the centralized optimization which relies on a server for aggregation and fusion of local parameters; this has the drawback of a single point of failure and scaling issues for increasing network size. The paper proposes a fully distributed (or server-less) learning approach: the proposed FL algorithms leverage the cooperation of devices that perform data operations inside the network by iterating local computations and mutual interactions via consensus-based methods. The approach lays the groundwork for integration of FL within 5G and beyond networks characterized by decentralized connectivity and computing, with intelligence distributed over the end-devices. The proposed methodology is verified by experimental datasets collected inside an industrial IoT environment.
Tasks
Published	2019-12-27
URL	https://arxiv.org/abs/1912.13163v1
PDF	https://arxiv.org/pdf/1912.13163v1.pdf
PWC	https://paperswithcode.com/paper/federated-learning-with-cooperating-devices-a
Repo
Framework

Correlated Feature Selection for Tweet Spam Classification using Artificial Neural Networks


Title	Correlated Feature Selection for Tweet Spam Classification using Artificial Neural Networks
Authors	Prakamya Mishra
Abstract	Identification of spam messages is a very challenging task for social networks due to its large size and complex nature. The purpose of this paper is to undertake the analysis of spamming on Twitter. To classify spams efficiently it is necessary to first understand the features of the spam tweets as well as identify attributes of the spammer. We extract both tweet based features and user based features for our analysis and observe the correlation between these features. This step is necessary as we can reduce the training time if we combine the features that are highly correlated. To perform our analysis we use artificial neural networks and train the model to classify the tweets as spam or non-spam. Using Correlational Artificial Neural Network gives us the highest accuracy of 97.57% when compared with four other classifiers SVM, Kernel SVM, K Nearest Neighbours and Artificial Neural Network.
Tasks	Feature Selection
Published	2019-11-06
URL	https://arxiv.org/abs/1911.05495v2
PDF	https://arxiv.org/pdf/1911.05495v2.pdf
PWC	https://paperswithcode.com/paper/correlated-feature-selection-for-tweet-spam
Repo
Framework

An Efficient Detection of Malware by Naive Bayes Classifier Using GPGPU


Title	An Efficient Detection of Malware by Naive Bayes Classifier Using GPGPU
Authors	Sanjay K. Sahay, Mayank Chaudhari
Abstract	Due to continuous increase in the number of malware (according to AV-Test institute total ~8 x 10^8 malware are already known, and every day they register ~2.5 x 10^4 malware) and files in the computational devices, it is very important to design a system which not only effectively but can also efficiently detect the new or previously unseen malware to prevent/minimize the damages. Therefore, this paper presents a novel group-wise approach for the efficient detection of malware by parallelizing the classification using the power of GPGPU and shown that by using the Naive Bayes classifier the detection speed-up can be boosted up to 200x. The investigation also shows that the classification time increases significantly with the number of features.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.13746v1
PDF	https://arxiv.org/pdf/1905.13746v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-detection-of-malware-by-naive
Repo
Framework