January 28, 2020

3129 words 15 mins read

Paper Group ANR 1024

Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks. Human Motion Trajectory Prediction: A Survey. Joint Reasoning for Temporal and Causal Relations. Improving Humanness of Virtual Agents and Users’ Cooperation through Emotions. Conditional Generative Neural System for Probabilistic Trajectory Prediction. Giving Atte …

Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks


Title	Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks
Authors	Yunxiang Zhang, Samy Blusseau, Santiago Velasco-Forero, Isabelle Bloch, Jesus Angulo
Abstract	Following recent advances in morphological neural networks, we propose to study in more depth how Max-plus operators can be exploited to define morphological units and how they behave when incorporated in layers of conventional neural networks. Besides showing that they can be easily implemented with modern machine learning frameworks , we confirm and extend the observation that a Max-plus layer can be used to select important filters and reduce redundancy in its previous layer, without incurring performance loss. Experimental results demonstrate that the filter selection strategy enabled by a Max-plus is highly efficient and robust, through which we successfully performed model pruning on different neural network architectures. We also point out that there is a close connection between Maxout networks and our pruned Max-plus networks by comparing their respective characteristics. The code for reproducing our experiments is available online.
Tasks
Published	2019-03-19
URL	http://arxiv.org/abs/1903.08072v2
PDF	http://arxiv.org/pdf/1903.08072v2.pdf
PWC	https://paperswithcode.com/paper/max-plus-operators-applied-to-filter
Repo
Framework

Human Motion Trajectory Prediction: A Survey


Title	Human Motion Trajectory Prediction: A Survey
Authors	Andrey Rudenko, Luigi Palmieri, Michael Herman, Kris M. Kitani, Dariu M. Gavrila, Kai O. Arras
Abstract	With growing numbers of intelligent autonomous systems in human environments, the ability of such systems to perceive, understand and anticipate human behavior becomes increasingly important. Specifically, predicting future positions of dynamic agents and planning considering such predictions are key tasks for self-driving vehicles, service robots and advanced surveillance systems. This paper provides a survey of human motion trajectory prediction. We review, analyze and structure a large selection of work from different communities and propose a taxonomy that categorizes existing methods based on the motion modeling approach and level of contextual information used. We provide an overview of the existing datasets and performance metrics. We discuss limitations of the state of the art and outline directions for further research.
Tasks	Trajectory Prediction
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06113v3
PDF	https://arxiv.org/pdf/1905.06113v3.pdf
PWC	https://paperswithcode.com/paper/human-motion-trajectory-prediction-a-survey
Repo
Framework

Joint Reasoning for Temporal and Causal Relations


Title	Joint Reasoning for Temporal and Causal Relations
Authors	Qiang Ning, Zhili Feng, Hao Wu, Dan Roth
Abstract	Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must be before its effect in time, temporal and causal relations are closely related and one relation even dictates the other one in many cases. However, limited attention has been paid to studying these two relations jointly. This paper presents a joint inference framework for them using constrained conditional models (CCMs). Specifically, we formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints inherently in the nature of time and causality. We show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.04941v1
PDF	https://arxiv.org/pdf/1906.04941v1.pdf
PWC	https://paperswithcode.com/paper/joint-reasoning-for-temporal-and-causal-1
Repo
Framework

Improving Humanness of Virtual Agents and Users’ Cooperation through Emotions


Title	Improving Humanness of Virtual Agents and Users’ Cooperation through Emotions
Authors	Moojan Ghafurian, Neil Budnarain, Jesse Hoey
Abstract	In this paper, we analyze the performance of an agent developed according to a well-accepted appraisal theory of human emotion with respect to how it modulates play in the context of a social dilemma. We ask if the agent will be capable of generating interactions that are considered to be more human than machine-like. We conduct an experiment with 117 participants and show how participants rate our agent on dimensions of human-uniqueness (which separates humans from animals) and human-nature (which separates humans from machines). We show that our appraisal theoretic agent is perceived to be more human-like than baseline models, by significantly improving both human-nature and human-uniqueness aspects of the intelligent agent. We also show that perception of humanness positively affects enjoyment and cooperation in the social dilemma.
Tasks
Published	2019-03-10
URL	http://arxiv.org/abs/1903.03980v1
PDF	http://arxiv.org/pdf/1903.03980v1.pdf
PWC	https://paperswithcode.com/paper/improving-humanness-of-virtual-agents-and
Repo
Framework

Conditional Generative Neural System for Probabilistic Trajectory Prediction


Title	Conditional Generative Neural System for Probabilistic Trajectory Prediction
Authors	Jiachen Li, Hengbo Ma, Masayoshi Tomizuka
Abstract	Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are critical for intelligent systems such as autonomous vehicles and wheeled mobile robotics navigating in complex scenarios to achieve safe and high-quality decision making, motion planning and control. Due to the uncertain nature of the future, it is desired to make inference from a probability perspective instead of deterministic prediction. In this paper, we propose a conditional generative neural system (CGNS) for probabilistic trajectory prediction to approximate the data distribution, with which realistic, feasible and diverse future trajectory hypotheses can be sampled. The system combines the strengths of conditional latent space learning and variational divergence minimization, and leverages both static context and interaction information with soft attention mechanisms. We also propose a regularization method for incorporating soft constraints into deep neural networks with differentiable barrier functions, which can regulate and push the generated samples into the feasible regions. The proposed system is evaluated on several public benchmark datasets for pedestrian trajectory prediction and a roundabout naturalistic driving dataset collected by ourselves. The experimental results demonstrate that our model achieves better performance than various baseline approaches in terms of prediction accuracy.
Tasks	Autonomous Vehicles, Decision Making, Motion Planning, Trajectory Prediction
Published	2019-05-05
URL	https://arxiv.org/abs/1905.01631v2
PDF	https://arxiv.org/pdf/1905.01631v2.pdf
PWC	https://paperswithcode.com/paper/conditional-generative-neural-system-for
Repo
Framework

Giving Attention to the Unexpected: Using Prosody Innovations in Disfluency Detection


Title	Giving Attention to the Unexpected: Using Prosody Innovations in Disfluency Detection
Authors	Vicky Zayats, Mari Ostendorf
Abstract	Disfluencies in spontaneous speech are known to be associated with prosodic disruptions. However, most algorithms for disfluency detection use only word transcripts. Integrating prosodic cues has proved difficult because of the many sources of variability affecting the acoustic correlates. This paper introduces a new approach to extracting acoustic-prosodic cues using text-based distributional prediction of acoustic cues to derive vector z-score features (innovations). We explore both early and late fusion techniques for integrating text and prosody, showing gains over a high-accuracy text-only model.
Tasks
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04388v1
PDF	http://arxiv.org/pdf/1904.04388v1.pdf
PWC	https://paperswithcode.com/paper/giving-attention-to-the-unexpected-using
Repo
Framework

Minimax Nonparametric Two-sample Test


Title	Minimax Nonparametric Two-sample Test
Authors	Xin Xing, Zuofeng Shang, Pang Du, Ping Ma, Wenxuan Zhong, Jun S. Liu
Abstract	We consider the problem of comparing probability densities between two groups. To model the complex pattern of the underlying densities, we formulate the problem as a nonparametric density hypothesis testing problem. The major difficulty is that conventional tests may fail to distinguish the alternative from the null hypothesis under the controlled type I error. In this paper, we model log-transformed densities in a tensor product reproducing kernel Hilbert space (RKHS) and propose a probabilistic decomposition of this space. Under such a decomposition, we quantify the difference of the densities between two groups by the component norm in the probabilistic decomposition. Based on the Bernstein width, a sharp minimax lower bound of the distinguishable rate is established for the nonparametric two-sample test. We then propose a penalized likelihood ratio (PLR) test possessing the Wilks’ phenomenon with an asymptotically Chi-square distributed test statistic and achieving the established minimax testing rate. Simulations and real applications demonstrate that the proposed test outperforms the conventional approaches under various scenarios.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02171v3
PDF	https://arxiv.org/pdf/1911.02171v3.pdf
PWC	https://paperswithcode.com/paper/minimax-nonparametric-parallelism-test
Repo
Framework

Automatic Detection of Bowel Disease with Residual Networks


Title	Automatic Detection of Bowel Disease with Residual Networks
Authors	Robert Holland, Uday Patel, Phillip Lung, Elisa Chotzoglou, Bernhard Kainz
Abstract	Crohn’s disease, one of two inflammatory bowel diseases (IBD), affects 200,000 people in the UK alone, or roughly one in every 500. We explore the feasibility of deep learning algorithms for identification of terminal ileal Crohn’s disease in Magnetic Resonance Enterography images on a small dataset. We show that they provide comparable performance to the current clinical standard, the MaRIA score, while requiring only a fraction of the preparation and inference time. Moreover, bowels are subject to high variation between individuals due to the complex and free-moving anatomy. Thus we also explore the effect of difficulty of the classification at hand on performance. Finally, we employ soft attention mechanisms to amplify salient local features and add interpretability.
Tasks
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00276v1
PDF	https://arxiv.org/pdf/1909.00276v1.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-of-bowel-disease-with
Repo
Framework

Decentralized Bayesian Learning over Graphs


Title	Decentralized Bayesian Learning over Graphs
Authors	Anusha Lalitha, Xinghan Wang, Osman Kilinc, Yongxi Lu, Tara Javidi, Farinaz Koushanfar
Abstract	We propose a decentralized learning algorithm over a general social network. The algorithm leaves the training data distributed on the mobile devices while utilizing a peer to peer model aggregation method. The proposed algorithm allows agents with local data to learn a shared model explaining the global training data in a decentralized fashion. The proposed algorithm can be viewed as a Bayesian and peer-to-peer variant of federated learning in which each agent keeps a “posterior probability distribution” over a global model parameters. The agent update its “posterior” based on 1) the local training data and 2) the asynchronous communication and model aggregation with their 1-hop neighbors. This Bayesian formulation allows for a systematic treatment of model aggregation over any arbitrary connected graph. Furthermore, it provides strong analytic guarantees on converge in the realizable case as well as a closed form characterization of the rate of convergence. We also show that our methodology can be combined with efficient Bayesian inference techniques to train Bayesian neural networks in a decentralized manner. By empirical studies we show that our theoretical analysis can guide the design of network/social interactions and data partitioning to achieve convergence.
Tasks	Bayesian Inference
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10466v1
PDF	https://arxiv.org/pdf/1905.10466v1.pdf
PWC	https://paperswithcode.com/paper/decentralized-bayesian-learning-over-graphs
Repo
Framework

Deep Learning based Multiple Regression to Predict Total Column Water Vapor (TCWV) from Physical Parameters in West Africa by using Keras Library


Title	Deep Learning based Multiple Regression to Predict Total Column Water Vapor (TCWV) from Physical Parameters in West Africa by using Keras Library
Authors	Daouda Diouf, Awa Niang, Sylvie Thiria
Abstract	Total column water vapor is an important factor for the weather and climate. This study apply deep learning based multiple regression to map the TCWV with elements that can improve spatiotemporal prediction. In this study, we predict the TCWV with the use of ERA5 that is the fifth generation ECMWF atmospheric reanalysis of the global climate. We use an appropriate deep learning based multiple regression algorithm using Keras library to improve nonlinear prediction between Total Column water vapor and predictors as Mean sea level pressure, Surface pressure, Sea surface temperature, 100 metre U wind component, 100 metre V wind component, 10 metre U wind component, 10 metre V wind component, 2 metre dew point temperature, 2 metre temperature. The results obtained permit to build a predictor which modelling TCWV with a mean abs error (MAE) equal to 3.60 kg/m2 and a coefficient of determination R2 equal to 0.90.
Tasks
Published	2019-12-12
URL	https://arxiv.org/abs/1912.07388v1
PDF	https://arxiv.org/pdf/1912.07388v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-multiple-regression-to
Repo
Framework

A semantic-aided particle filter approach for AUV localization


Title	A semantic-aided particle filter approach for AUV localization
Authors	Francesco Maurelli, Szymon Krupinski
Abstract	This paper presents a novel approach to AUV localization, based on a semantic-aided particle filter. Particle filters have been used successfully for robotics localization since many years. Most of the approaches are however based on geometric measurements and geometric information and simulations. In the past years more and more efforts from research goes towards cognitive robotics and the marine domain is not exception. Moving from signal to symbol becomes therefore paramount for more complex applications. This paper presents a contribution in the well-known area of underwater localization, incorporating semantic information. An extension to the standard particle filter approach is presented, based on semantic information of the environment. A comparison with the geometric approach shows the advantages of a semantic layer to successfully perform self-localization.
Tasks
Published	2019-05-17
URL	https://arxiv.org/abs/1905.07470v1
PDF	https://arxiv.org/pdf/1905.07470v1.pdf
PWC	https://paperswithcode.com/paper/a-semantic-aided-particle-filter-approach-for
Repo
Framework

Identification of Pediatric Sepsis Subphenotypes for Enhanced Machine Learning Predictive Performance: A Latent Profile Analysis


Title	Identification of Pediatric Sepsis Subphenotypes for Enhanced Machine Learning Predictive Performance: A Latent Profile Analysis
Authors	Tom Velez, Tony Wang, Ioannis Koutroulis, James Chamberlain, Amit Uppal, Seife Yohannes, Tim Tschampel, Emilia Apostolova
Abstract	Background: While machine learning (ML) models are rapidly emerging as promising screening tools in critical care medicine, the identification of homogeneous subphenotypes within populations with heterogeneous conditions such as pediatric sepsis may facilitate attainment of high-predictive performance of these prognostic algorithms. This study is aimed to identify subphenotypes of pediatric sepsis and demonstrate the potential value of partitioned data/subtyping-based training. Methods: This was a retrospective study of clinical data extracted from medical records of 6,446 pediatric patients that were admitted at a major hospital system in the DC area. Vitals and labs associated with patients meeting the diagnostic criteria for sepsis were used to perform latent profile analysis. Modern ML algorithms were used to explore the predictive performance benefits of reduced training data heterogeneity via label profiling. Results: In total 134 (2.1%) patients met the diagnostic criteria for sepsis in this cohort and latent profile analysis identified four profiles/subphenotypes of pediatric sepsis. Profiles 1 and 3 had the lowest mortality and included pediatric patients from different age groups. Profile 2 were characterized by respiratory dysfunction; profile 4 by neurological dysfunction and highest mortality rate (22.2%). Machine learning experiments comparing the predictive performance of models derived without training data profiling against profile targeted models suggest statistically significant improved performance of prediction can be obtained. For example, area under ROC curve (AUC) obtained to predict profile 4 with 24-hour data (AUC = .998, p < .0001) compared favorably with the AUC obtained from the model considering all profiles as a single homogeneous group (AUC = .918) with 24-hour data.
Tasks
Published	2019-08-23
URL	https://arxiv.org/abs/1908.09038v1
PDF	https://arxiv.org/pdf/1908.09038v1.pdf
PWC	https://paperswithcode.com/paper/identification-of-pediatric-sepsis
Repo
Framework

When Multiple Agents Learn to Schedule: A Distributed Radio Resource Management Framework


Title	When Multiple Agents Learn to Schedule: A Distributed Radio Resource Management Framework
Authors	Navid Naderializadeh, Jaroslaw Sydir, Meryem Simsek, Hosein Nikopour, Shilpa Talwar
Abstract	Interference among concurrent transmissions in a wireless network is a key factor limiting the system performance. One way to alleviate this problem is to manage the radio resources in order to maximize either the average or the worst-case performance. However, joint consideration of both metrics is often neglected as they are competing in nature. In this article, a mechanism for radio resource management using multi-agent deep reinforcement learning (RL) is proposed, which strikes the right trade-off between maximizing the average and the $5^{th}$ percentile user throughput. Each transmitter in the network is equipped with a deep RL agent, receiving partial observations from the network (e.g., channel quality, interference level, etc.) and deciding whether to be active or inactive at each scheduling interval for given radio resources, a process referred to as link scheduling. Based on the actions of all agents, the network emits a reward to the agents, indicating how good their joint decisions were. The proposed framework enables the agents to make decisions in a distributed manner, and the reward is designed in such a way that the agents strive to guarantee a minimum performance, leading to a fair resource allocation among all users across the network. Simulation results demonstrate the superiority of our approach compared to decentralized baselines in terms of average and $5^{th}$ percentile user throughput, while achieving performance close to that of a centralized exhaustive search approach. Moreover, the proposed framework is robust to mismatches between training and testing scenarios. In particular, it is shown that an agent trained on a network with low transmitter density maintains its performance and outperforms the baselines when deployed in a network with a higher transmitter density.
Tasks
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08792v1
PDF	https://arxiv.org/pdf/1906.08792v1.pdf
PWC	https://paperswithcode.com/paper/when-multiple-agents-learn-to-schedule-a
Repo
Framework

Three Methods for Training on Bandit Feedback


Title	Three Methods for Training on Bandit Feedback
Authors	Dmytro Mykhaylov, David Rohde, Flavian Vasile, Martin Bompaire, Olivier Jeunen
Abstract	There are three quite distinct ways to train a machine learning model on recommender system logs. The first method is to model the reward prediction for each possible recommendation to the user, at the scoring time the best recommendation is found by computing an argmax over the personalized recommendations. This method obeys principles such as the conditionality principle and the likelihood principle. A second method is useful when the model does not fit reality and underfits. In this case, we can use the fact that we know the distribution of historical recommendations (concentrated on previously identified good actions with some exploration) to adjust the errors in the fit to be evenly distributed over all actions. Finally, the inverse propensity score can be used to produce an estimate of the decision rules expected performance. The latter two methods violate the conditionality and likelihood principle but are shown to have good performance in certain settings. In this paper we review the literature around this fundamental, yet often overlooked choice and do some experiments using the RecoGym simulation environment.
Tasks	Recommendation Systems
Published	2019-04-24
URL	https://arxiv.org/abs/1904.10799v2
PDF	https://arxiv.org/pdf/1904.10799v2.pdf
PWC	https://paperswithcode.com/paper/three-methods-for-training-on-bandit-feedback
Repo
Framework

Second-Order Group Influence Functions for Black-Box Predictions


Title	Second-Order Group Influence Functions for Black-Box Predictions
Authors	Samyadeep Basu, Xuchen You, Soheil Feizi
Abstract	With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influential group of training samples in a particular test prediction. Existing influence functions tackle this problem by using first-order approximations of the effect of removing a sample from the training set on model parameters. To compute the influence of a group of training samples (rather than an individual point) in model predictions, the change in optimal model parameters after removing that group from the training set can be large. Thus, in such cases, the first-order approximation can be loose. In this paper, we address this issue and propose second-order influence functions for identifying influential groups in test-time predictions. For linear models and across different sizes of groups, we show that using the proposed second-order influence function improves the correlation between the computed influence values and the ground truth ones. For nonlinear models based on neural networks, we empirically show that none of the existing first-order and the proposed second-order influence functions provide proper estimates of the ground-truth influences over all training samples. We empirically study this phenomenon by decomposing the influence values over contributions from different eigenvectors of the Hessian of the trained model.
Tasks
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00418v1
PDF	https://arxiv.org/pdf/1911.00418v1.pdf
PWC	https://paperswithcode.com/paper/second-order-group-influence-functions-for
Repo
Framework