October 18, 2019

3132 words 15 mins read

Paper Group ANR 450

On Strategyproof Conference Peer Review. Exponential inequalities for nonstationary Markov Chains. Potentially Guided Bidirectionalized RRT* for Fast Optimal Path Planning in Cluttered Environments. XOGAN: One-to-Many Unsupervised Image-to-Image Translation. Full-pulse Tomographic Reconstruction with Deep Neural Networks. Comparative Evaluation of …

On Strategyproof Conference Peer Review


Title	On Strategyproof Conference Peer Review
Authors	Yichong Xu, Han Zhao, Xiaofei Shi, Jeremy Zhang, Nihar B. Shah
Abstract	We consider peer review in a conference setting where there is typically an overlap between the set of reviewers and the set of authors. This overlap can incentivize strategic reviews to influence the final ranking of one’s own papers. In this work, we address this problem through the lens of social choice, and present a theoretical framework for strategyproof and efficient peer review. We first present and analyze an algorithm for reviewer-assignment and aggregation that guarantees strategyproofness and a natural efficiency property called unanimity, when the authorship graph satisfies a simple property. Our algorithm is based on the so-called partitioning method, and can be thought as a generalization of this method to conference peer review settings. We then empirically show that the requisite property on the authorship graph is indeed satisfied in the submission data from the ICLR conference, and further demonstrate a simple trick to make the partitioning method more practically appealing for conference peer review. Finally, we complement our positive results with negative theoretical results where we prove that under various ways of strengthening the requirements, it is impossible for any algorithm to be strategyproof and efficient.
Tasks
Published	2018-06-16
URL	https://arxiv.org/abs/1806.06266v3
PDF	https://arxiv.org/pdf/1806.06266v3.pdf
PWC	https://paperswithcode.com/paper/on-strategyproof-conference-peer-review
Repo
Framework

Exponential inequalities for nonstationary Markov Chains


Title	Exponential inequalities for nonstationary Markov Chains
Authors	Pierre Alquier, Paul Doukhan, Xiequan Fan
Abstract	Exponential inequalities are main tools in machine learning theory. To prove exponential inequalities for non i.i.d random variables allows to extend many learning techniques to these variables. Indeed, much work has been done both on inequalities and learning theory for time series, in the past 15 years. However, for the non independent case, almost all the results concern stationary time series. This excludes many important applications: for example any series with a periodic behavior is non-stationary. In this paper, we extend the basic tools of Dedecker and Fan (2015) to nonstationary Markov chains. As an application, we provide a Bernstein-type inequality, and we deduce risk bounds for the prediction of periodic autoregressive processes with an unknown period.
Tasks	Time Series
Published	2018-08-27
URL	https://arxiv.org/abs/1808.08811v3
PDF	https://arxiv.org/pdf/1808.08811v3.pdf
PWC	https://paperswithcode.com/paper/exponential-inequalities-for-nonstationary
Repo
Framework

Potentially Guided Bidirectionalized RRT* for Fast Optimal Path Planning in Cluttered Environments


Title	Potentially Guided Bidirectionalized RRT* for Fast Optimal Path Planning in Cluttered Environments
Authors	Zaid Tahir, Ahmed H. Qureshi, Yasar Ayaz, Raheel Nawaz
Abstract	Rapidly-exploring Random Tree star (RRT) has recently gained immense popularity in the motion planning community as it provides a probabilistically complete and asymptotically optimal solution without requiring the complete information of the obstacle space. In spite of all of its advantages, RRT converges to an optimal solution very slowly. Hence to improve the convergence rate, its bidirectional variants were introduced, the Bi-directional RRT* (B-RRT) and Intelligent Bi-directional RRT (IB-RRT). However, as both variants perform pure exploration, they tend to suffer in highly cluttered environments. In order to overcome these limitations, we introduce a new concept of potentially guided bidirectional trees in our proposed Potentially Guided Intelligent Bi-directional RRT (PIB-RRT) and Potentially Guided Bi-directional RRT (PB-RRT*). The proposed algorithms greatly improve the convergence rate and have a more efficient memory utilization. Theoretical and experimental evaluation of the proposed algorithms have been made and compared to the latest state of the art motion planning algorithms under different challenging environmental conditions and have proven their remarkable improvement in efficiency and convergence rate.
Tasks	Motion Planning
Published	2018-07-22
URL	http://arxiv.org/abs/1807.08325v1
PDF	http://arxiv.org/pdf/1807.08325v1.pdf
PWC	https://paperswithcode.com/paper/potentially-guided-bidirectionalized-rrt-for
Repo
Framework

XOGAN: One-to-Many Unsupervised Image-to-Image Translation


Title	XOGAN: One-to-Many Unsupervised Image-to-Image Translation
Authors	Yongqi Zhang
Abstract	Unsupervised image-to-image translation aims at learning the relationship between samples from two image domains without supervised pair information. The relationship between two domain images can be one-to-one, one-to-many or many-to-many. In this paper, we study the one-to-many unsupervised image translation problem in which an input sample from one domain can correspond to multiple samples in the other domain. To learn the complex relationship between the two domains, we introduce an additional variable to control the variations in our one-to-many mapping. A generative model with an XO-structure, called the XOGAN, is proposed to learn the cross domain relationship among the two domains and the ad- ditional variables. Not only can we learn to translate between the two image domains, we can also handle the translated images with additional variations. Experiments are performed on unpaired image generation tasks, including edges-to-objects translation and facial image translation. We show that the proposed XOGAN model can generate plausible images and control variations, such as color and texture, of the generated images. Moreover, while state-of-the-art unpaired image generation algorithms tend to generate images with monotonous colors, XOGAN can generate more diverse results.
Tasks	Image Generation, Image-to-Image Translation, Unsupervised Image-To-Image Translation
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07277v1
PDF	http://arxiv.org/pdf/1805.07277v1.pdf
PWC	https://paperswithcode.com/paper/xogan-one-to-many-unsupervised-image-to-image
Repo
Framework

Full-pulse Tomographic Reconstruction with Deep Neural Networks


Title	Full-pulse Tomographic Reconstruction with Deep Neural Networks
Authors	Diogo R. Ferreira, Pedro J. Carvalho, Horácio Fernandes
Abstract	Plasma tomography consists in reconstructing the 2D radiation profile in a poloidal cross-section of a fusion device, based on line-integrated measurements along several lines of sight. The reconstruction process is computationally intensive and, in practice, only a few reconstructions are usually computed per pulse. In this work, we trained a deep neural network based on a large collection of sample tomograms that have been produced at JET over several years. Once trained, the network is able to reproduce those results with high accuracy. More importantly, it can compute all the tomographic reconstructions for a given pulse in just a few seconds. This makes it possible to visualize several phenomena – such as plasma heating, disruptions and impurity transport – over the course of a discharge.
Tasks	Tomographic Reconstructions
Published	2018-02-02
URL	http://arxiv.org/abs/1802.02242v1
PDF	http://arxiv.org/pdf/1802.02242v1.pdf
PWC	https://paperswithcode.com/paper/full-pulse-tomographic-reconstruction-with
Repo
Framework

Comparative Evaluation of Tree-Based Ensemble Algorithms for Short-Term Travel Time Prediction


Title	Comparative Evaluation of Tree-Based Ensemble Algorithms for Short-Term Travel Time Prediction
Authors	Saleh Mousa, Sherif Ishak
Abstract	Disseminating accurate travel time information to road users helps achieve traffic equilibrium and reduce traffic congestion. The deployment of Connected Vehicles technology will provide unique opportunities for the implementation of travel time prediction models. The aim of this study is twofold: (1) estimate travel times in the freeway network at five-minute intervals using Basic Safety Messages (BSM); (2) develop an eXtreme Gradient Boosting (XGB) model for short-term travel time prediction on freeways. The XGB tree-based ensemble prediction model is evaluated against common tree-based ensemble algorithms and the evaluations are performed at five-minute intervals over a 30-minute horizon. BSMs generated by the Safety Pilot Model Deployment conducted in Ann Arbor, Michigan, were used. Nearly two billion messages were processed for providing travel time estimates for the entire freeway network. A Combination of grid search and five-fold cross-validation techniques using the travel time estimates were used for developing the prediction models and tuning their parameters. About 9.6 km freeway stretch was used for evaluating the XGB together with the most common tree-based ensemble algorithms. The results show that XGB is superior to all other algorithms, followed by the Gradient Boosting. XGB travel time predictions were accurate and consistent with variations during peak periods, with mean absolute percentage error in prediction about 5.9% and 7.8% for 5-minute and 30-minute horizons, respectively. Additionally, through applying the developed models to another 4.7 km stretch along the eastbound segment of M-14, the XGB demonstrated its considerable advantages in travel time prediction during congested and uncongested conditions.
Tasks
Published	2018-10-23
URL	http://arxiv.org/abs/1810.10102v1
PDF	http://arxiv.org/pdf/1810.10102v1.pdf
PWC	https://paperswithcode.com/paper/comparative-evaluation-of-tree-based-ensemble
Repo
Framework

Towards an Unsupervised Entrainment Distance in Conversational Speech using Deep Neural Networks


Title	Towards an Unsupervised Entrainment Distance in Conversational Speech using Deep Neural Networks
Authors	Md Nasir, Brian Baucom, Shrikanth Narayanan, Panayiotis Georgiou
Abstract	Entrainment is a known adaptation mechanism that causes interaction participants to adapt or synchronize their acoustic characteristics. Understanding how interlocutors tend to adapt to each other’s speaking style through entrainment involves measuring a range of acoustic features and comparing those via multiple signal comparison methods. In this work, we present a turn-level distance measure obtained in an unsupervised manner using a Deep Neural Network (DNN) model, which we call Neural Entrainment Distance (NED). This metric establishes a framework that learns an embedding from the population-wide entrainment in an unlabeled training corpus. We use the framework for a set of acoustic features and validate the measure experimentally by showing its efficacy in distinguishing real conversations from fake ones created by randomly shuffling speaker turns. Moreover, we show real world evidence of the validity of the proposed measure. We find that high value of NED is associated with high ratings of emotional bond in suicide assessment interviews, which is consistent with prior studies.
Tasks
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08782v1
PDF	http://arxiv.org/pdf/1804.08782v1.pdf
PWC	https://paperswithcode.com/paper/towards-an-unsupervised-entrainment-distance
Repo
Framework

Order matters: Distributional properties of speech to young children bootstraps learning of semantic representations


Title	Order matters: Distributional properties of speech to young children bootstraps learning of semantic representations
Authors	Philip A Huebner, Jon A Willits
Abstract	Some researchers claim that language acquisition is critically dependent on experiencing linguistic input in order of increasing complexity. We set out to test this hypothesis using a simple recurrent neural network (SRN) trained to predict word sequences in CHILDES, a 5-million-word corpus of speech directed to children. First, we demonstrated that age-ordered CHILDES exhibits a gradual increase in linguistic complexity. Next, we compared the performance of two groups of SRNs trained on CHILDES which had either been age-ordered or not. Specifically, we assessed learning of grammatical and semantic structure and showed that training on age-ordered input facilitates learning of semantic, but not of sequential structure. We found that this advantage is eliminated when the models were trained on input with utterance boundary information removed.
Tasks	Language Acquisition
Published	2018-02-02
URL	http://arxiv.org/abs/1802.00768v1
PDF	http://arxiv.org/pdf/1802.00768v1.pdf
PWC	https://paperswithcode.com/paper/order-matters-distributional-properties-of
Repo
Framework

Backpropagation and Biological Plausibility


Title	Backpropagation and Biological Plausibility
Authors	Alessandro Betti, Marco Gori, Giuseppe Marra
Abstract	By and large, Backpropagation (BP) is regarded as one of the most important neural computation algorithms at the basis of the progress in machine learning, including the recent advances in deep learning. However, its computational structure has been the source of many debates on its arguable biological plausibility. In this paper, it is shown that when framing supervised learning in the Lagrangian framework, while one can see a natural emergence of Backpropagation, biologically plausible local algorithms can also be devised that are based on the search for saddle points in the learning adjoint space composed of weights, neural outputs, and Lagrangian multipliers. This might open the doors to a truly novel class of learning algorithms where, because of the introduction of the notion of support neurons, the optimization scheme also plays a fundamental role in the construction of the architecture.
Tasks
Published	2018-08-21
URL	http://arxiv.org/abs/1808.06934v1
PDF	http://arxiv.org/pdf/1808.06934v1.pdf
PWC	https://paperswithcode.com/paper/backpropagation-and-biological-plausibility
Repo
Framework

Hidden Hamiltonian Cycle Recovery via Linear Programming


Title	Hidden Hamiltonian Cycle Recovery via Linear Programming
Authors	Vivek Bagaria, Jian Ding, David Tse, Yihong Wu, Jiaming Xu
Abstract	We introduce the problem of hidden Hamiltonian cycle recovery, where there is an unknown Hamiltonian cycle in an $n$-vertex complete graph that needs to be inferred from noisy edge measurements. The measurements are independent and distributed according to $\calP_n$ for edges in the cycle and $\calQ_n$ otherwise. This formulation is motivated by a problem in genome assembly, where the goal is to order a set of contigs (genome subsequences) according to their positions on the genome using long-range linking measurements between the contigs. Computing the maximum likelihood estimate in this model reduces to a Traveling Salesman Problem (TSP). Despite the NP-hardness of TSP, we show that a simple linear programming (LP) relaxation, namely the fractional $2$-factor (F2F) LP, recovers the hidden Hamiltonian cycle with high probability as $n \to \infty$ provided that $\alpha_n - \log n \to \infty$, where $\alpha_n \triangleq -2 \log \int \sqrt{d P_n d Q_n}$ is the R'enyi divergence of order $\frac{1}{2}$. This condition is information-theoretically optimal in the sense that, under mild distributional assumptions, $\alpha_n \geq (1+o(1)) \log n$ is necessary for any algorithm to succeed regardless of the computational cost. Departing from the usual proof techniques based on dual witness construction, the analysis relies on the combinatorial characterization (in particular, the half-integrality) of the extreme points of the F2F polytope. Represented as bicolored multi-graphs, these extreme points are further decomposed into simpler “blossom-type” structures for the large deviation analysis and counting arguments. Evaluation of the algorithm on real data shows improvements over existing approaches.
Tasks
Published	2018-04-15
URL	http://arxiv.org/abs/1804.05436v1
PDF	http://arxiv.org/pdf/1804.05436v1.pdf
PWC	https://paperswithcode.com/paper/hidden-hamiltonian-cycle-recovery-via-linear
Repo
Framework

Learning Video-Story Composition via Recurrent Neural Network


Title	Learning Video-Story Composition via Recurrent Neural Network
Authors	Guangyu Zhong, Yi-Hsuan Tsai, Sifei Liu, Zhixun Su, Ming-Hsuan Yang
Abstract	In this paper, we propose a learning-based method to compose a video-story from a group of video clips that describe an activity or experience. We learn the coherence between video clips from real videos via the Recurrent Neural Network (RNN) that jointly incorporates the spatial-temporal semantics and motion dynamics to generate smooth and relevant compositions. We further rearrange the results generated by the RNN to make the overall video-story compatible with the storyline structure via a submodular ranking optimization process. Experimental results on the video-story dataset show that the proposed algorithm outperforms the state-of-the-art approach.
Tasks
Published	2018-01-31
URL	http://arxiv.org/abs/1801.10281v1
PDF	http://arxiv.org/pdf/1801.10281v1.pdf
PWC	https://paperswithcode.com/paper/learning-video-story-composition-via
Repo
Framework

Geometry of Friston’s active inference


Title	Geometry of Friston’s active inference
Authors	Martin Biehl
Abstract	We reconstruct Karl Friston’s active inference and give a geometrical interpretation of it.
Tasks
Published	2018-11-20
URL	http://arxiv.org/abs/1811.08241v1
PDF	http://arxiv.org/pdf/1811.08241v1.pdf
PWC	https://paperswithcode.com/paper/geometry-of-fristons-active-inference
Repo
Framework

Active Learning for Wireless IoT Intrusion Detection


Title	Active Learning for Wireless IoT Intrusion Detection
Authors	Kai Yang, Jie Ren, Yanqiao Zhu, Weiyi Zhang
Abstract	Internet of Things (IoT) is becoming truly ubiquitous in our everyday life, but it also faces unique security challenges. Intrusion detection is critical for the security and safety of a wireless IoT network. This paper discusses the human-in-the-loop active learning approach for wireless intrusion detection. We first present the fundamental challenges against the design of a successful Intrusion Detection System (IDS) for wireless IoT network. We then briefly review the rudimentary concepts of active learning and propose its employment in the diverse applications of wireless intrusion detection. Experimental example is also presented to show the significant performance improvement of the active learning method over traditional supervised learning approach. While machine learning techniques have been widely employed for intrusion detection, the application of human-in-the-loop machine learning that leverages both machine and human intelligence to intrusion detection of IoT is still in its infancy. We hope this article can assist the readers in understanding the key concepts of active learning and spur further research in this area.
Tasks	Active Learning, Intrusion Detection
Published	2018-08-04
URL	http://arxiv.org/abs/1808.01412v1
PDF	http://arxiv.org/pdf/1808.01412v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-for-wireless-iot-intrusion
Repo
Framework

ClassiNet – Predicting Missing Features for Short-Text Classification


Title	ClassiNet – Predicting Missing Features for Short-Text Classification
Authors	Danushka Bollegala, Vincent Atanasov, Takanori Maehara, Ken-ichi Kawarabayashi
Abstract	The fundamental problem in short-text classification is \emph{feature sparseness} – the lack of feature overlap between a trained model and a test instance to be classified. We propose \emph{ClassiNet} – a network of classifiers trained for predicting missing features in a given instance, to overcome the feature sparseness problem. Using a set of unlabeled training instances, we first learn binary classifiers as feature predictors for predicting whether a particular feature occurs in a given instance. Next, each feature predictor is represented as a vertex $v_i$ in the ClassiNet where a one-to-one correspondence exists between feature predictors and vertices. The weight of the directed edge $e_{ij}$ connecting a vertex $v_i$ to a vertex $v_j$ represents the conditional probability that given $v_i$ exists in an instance, $v_j$ also exists in the same instance. We show that ClassiNets generalize word co-occurrence graphs by considering implicit co-occurrences between features. We extract numerous features from the trained ClassiNet to overcome feature sparseness. In particular, for a given instance $\vec{x}$, we find similar features from ClassiNet that did not appear in $\vec{x}$, and append those features in the representation of $\vec{x}$. Moreover, we propose a method based on graph propagation to find features that are indirectly related to a given short-text. We evaluate ClassiNets on several benchmark datasets for short-text classification. Our experimental results show that by using ClassiNet, we can statistically significantly improve the accuracy in short-text classification tasks, without having to use any external resources such as thesauri for finding related features.
Tasks	Text Classification
Published	2018-04-14
URL	http://arxiv.org/abs/1804.05260v1
PDF	http://arxiv.org/pdf/1804.05260v1.pdf
PWC	https://paperswithcode.com/paper/classinet-predicting-missing-features-for
Repo
Framework

Rough set based lattice structure for knowledge representation in medical expert systems: low back pain management case study


Title	Rough set based lattice structure for knowledge representation in medical expert systems: low back pain management case study
Authors	Debarpita Santra, Swapan Kumar Basu, Jyotsna Kumar Mandal, Subrata Goswami
Abstract	The aim of medical knowledge representation is to capture the detailed domain knowledge in a clinically efficient manner and to offer a reliable resolution with the acquired knowledge. The knowledge base to be used by a medical expert system should allow incremental growth with inclusion of updated knowledge over the time. As knowledge are gathered from a variety of knowledge sources by different knowledge engineers, the problem of redundancy is an important concern here due to increased processing time of knowledge and occupancy of large computational storage to accommodate all the gathered knowledge. Also there may exist many inconsistent knowledge in the knowledge base. In this paper, we have proposed a rough set based lattice structure for knowledge representation in medical expert systems which overcomes the problem of redundancy and inconsistency in knowledge and offers computational efficiency with respect to both time and space. We have also generated an optimal set of decision rules that would be used directly by the inference engine. The reliability of each rule has been measured using a new metric called credibility factor, and the certainty and coverage factors of a decision rule have been re-defined. With a set of decisions rules arranged in descending order according to their reliability measures, the medical expert system will consider the highly reliable and certain rules at first, then it would search for the possible and uncertain rules at later stage, if recommended by physicians. The proposed knowledge representation technique has been illustrated using an example from the domain of low back pain. The proposed scheme ensures completeness, consistency, integrity, non-redundancy, and ease of access.
Tasks
Published	2018-10-02
URL	http://arxiv.org/abs/1810.01560v1
PDF	http://arxiv.org/pdf/1810.01560v1.pdf
PWC	https://paperswithcode.com/paper/rough-set-based-lattice-structure-for
Repo
Framework