January 28, 2020

3305 words 16 mins read

Paper Group ANR 943

Tiered Latent Representations and Latent Spaces for Molecular Graphs. CMU GetGoing: An Understandable and Memorable Dialog System for Seniors. REP: Predicting the Time-Course of Drug Sensitivity. Deep Context-Aware Kernel Networks. Explainable Failure Predictions with RNN Classifiers based on Time Series Data. Indoor Signal Focusing with Deep Learn …

Tiered Latent Representations and Latent Spaces for Molecular Graphs


Title	Tiered Latent Representations and Latent Spaces for Molecular Graphs
Authors	Daniel T. Chang
Abstract	Molecular graphs generally contain subgraphs (known as groups) that are identifiable and significant in composition, functionality, geometry, etc. Flat latent representations (node embeddings or graph embeddings) fail to represent, and support the use of, groups. Fully hierarchical latent representations, on the other hand, are difficult to learn and, even if learned, may be too complex to use or interpret. We propose tiered latent representations and latent spaces for molecular graphs as a simple way to explicitly represent and utilize groups, which consist of the atom (node) tier, the group tier and the molecule (graph) tier. Specifically, we propose an architecture for learning tiered latent representations and latent spaces using graph autoencoders, graph neural networks, differentiable group pooling and the membership matrix. We discuss its various components, major challenges and related work, for both a deterministic and a probabilistic model. We also briefly discuss the usage and exploration of tiered latent spaces. The tiered approach is applicable to other types of structured graphs similar in nature to molecular graphs.
Tasks
Published	2019-03-21
URL	http://arxiv.org/abs/1904.02653v1
PDF	http://arxiv.org/pdf/1904.02653v1.pdf
PWC	https://paperswithcode.com/paper/tiered-latent-representations-and-latent
Repo
Framework

CMU GetGoing: An Understandable and Memorable Dialog System for Seniors


Title	CMU GetGoing: An Understandable and Memorable Dialog System for Seniors
Authors	Shikib Mehri, Alan W Black, Maxine Eskenazi
Abstract	Voice-based technologies are typically developed for the average user, and thus generally not tailored to the specific needs of any subgroup of the population, like seniors. This paper presents CMU GetGoing, an accessible trip planning dialog system designed for senior users. The GetGoing system design is described in detail, with particular attention to the senior-tailored features. A user study is presented, demonstrating that the senior-tailored features significantly improve comprehension and retention of information.
Tasks
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01322v1
PDF	https://arxiv.org/pdf/1909.01322v1.pdf
PWC	https://paperswithcode.com/paper/cmu-getgoing-an-understandable-and-memorable
Repo
Framework

REP: Predicting the Time-Course of Drug Sensitivity


Title	REP: Predicting the Time-Course of Drug Sensitivity
Authors	Cheng Qian, Amin Emad, Nicholas D. Sidiropoulos
Abstract	The biological processes involved in a drug’s mechanisms of action are oftentimes dynamic, complex and difficult to discern. Time-course gene expression data is a rich source of information that can be used to unravel these complex processes, identify biomarkers of drug sensitivity and predict the response to a drug. However, the majority of previous work has not fully utilized this temporal dimension. In these studies, the gene expression data is either considered at one time-point (before the administration of the drug) or two timepoints (before and after the administration of the drug). This is clearly inadequate in modeling dynamic gene-drug interactions, especially for applications such as long-term drug therapy. In this work, we present a novel REcursive Prediction (REP) framework for drug response prediction by taking advantage of time-course gene expression data. Our goal is to predict drug response values at every stage of a long-term treatment, given the expression levels of genes collected in the previous time-points. To this end, REP employs a built-in recursive structure that exploits the intrinsic time-course nature of the data and integrates past values of drug responses for subsequent predictions. It also incorporates tensor completion that can not only alleviate the impact of noise and missing data, but also predict unseen gene expression levels (GELs). These advantages enable REP to estimate drug response at any stage of a given treatment from some GELs measured in the beginning of the treatment. Extensive experiments on a dataset corresponding to 53 multiple sclerosis patients treated with interferon are included to showcase the effectiveness of REP.
Tasks
Published	2019-07-27
URL	https://arxiv.org/abs/1907.11911v1
PDF	https://arxiv.org/pdf/1907.11911v1.pdf
PWC	https://paperswithcode.com/paper/rep-predicting-the-time-course-of-drug
Repo
Framework

Deep Context-Aware Kernel Networks


Title	Deep Context-Aware Kernel Networks
Authors	Mingyuan Jiu, Hichem Sahbi
Abstract	Context plays a crucial role in visual recognition as it provides complementary clues for different learning tasks including image classification and annotation. As the performances of these tasks are currently reaching a plateau, any extra knowledge, including context, should be leveraged in order to seek significant leaps in these performances. In the particular scenario of kernel machines, context-aware kernel design aims at learning positive semi-definite similarity functions which return high values not only when data share similar contents, but also similar structures (a.k.a contexts). However, the use of context in kernel design has not been fully explored; indeed, context in these solutions is handcrafted instead of being learned. In this paper, we introduce a novel deep network architecture that learns context in kernel design. This architecture is fully determined by the solution of an objective function mixing a content term that captures the intrinsic similarity between data, a context criterion which models their structure and a regularization term that helps designing smooth kernel network representations. The solution of this objective function defines a particular deep network architecture whose parameters correspond to different variants of learned contexts including layerwise, stationary and classwise; larger values of these parameters correspond to the most influencing contextual relationships between data. Extensive experiments conducted on the challenging ImageCLEF Photo Annotation and Corel5k benchmarks show that our deep context networks are highly effective for image classification and the learned contexts further enhance the performance of image annotation.
Tasks	Image Classification
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12735v1
PDF	https://arxiv.org/pdf/1912.12735v1.pdf
PWC	https://paperswithcode.com/paper/deep-context-aware-kernel-networks
Repo
Framework

Explainable Failure Predictions with RNN Classifiers based on Time Series Data


Title	Explainable Failure Predictions with RNN Classifiers based on Time Series Data
Authors	Ioana Giurgiu, Anika Schumann
Abstract	Given key performance indicators collected with fine granularity as time series, our aim is to predict and explain failures in storage environments. Although explainable predictive modeling based on spiky telemetry data is key in many domains, current approaches cannot tackle this problem. Deep learning methods suitable for sequence modeling and learning temporal dependencies, such as RNNs, are effective, but opaque from an explainability perspective. Our approach first extracts the anomalous spikes from time series as events and then builds an RNN classifier with attention mechanisms to embed the irregularity and frequency of these events. A preliminary evaluation on real world storage environments shows that our approach can predict failures within a 3-day prediction window with comparable accuracy as traditional RNN-based classifiers. At the same time it can explain the predictions by returning the key anomalous events which led to those failure predictions.
Tasks	Time Series
Published	2019-01-20
URL	http://arxiv.org/abs/1901.08554v1
PDF	http://arxiv.org/pdf/1901.08554v1.pdf
PWC	https://paperswithcode.com/paper/explainable-failure-predictions-with-rnn
Repo
Framework

Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent Surfaces


Title	Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent Surfaces
Authors	Chongwen Huang, George C. Alexandropoulos, Chau Yuen, Mérouane Debbah
Abstract	Reconfigurable Intelligent Surfaces (RISs) comprised of tunable unit elements have been recently considered in indoor communication environments for focusing signal reflections to intended user locations. However, the current proofs of concept require complex operations for the RIS configuration, which are mainly realized via wired control connections. In this paper, we present a deep learning method for efficient online wireless configuration of RISs when deployed in indoor communication environments. According to the proposed method, a database of coordinate fingerprints is implemented during an offline training phase. This fingerprinting database is used to train the weights and bias of a properly designed Deep Neural Network (DNN), whose role is to unveil the mapping between the measured coordinate information at a user location and the configuration of the RIS’s unit cells that maximizes this user’s received signal strength. During the online phase of the presented method, the trained DNN is fed with the measured position information at the target user to output the optimal phase configurations of the RIS for signal power focusing on this intended location. Our realistic simulation results using ray tracing on a three dimensional indoor environment demonstrate that the proposed DNN-based configuration method exhibits its merits for all considered cases, and effectively increases the achievable throughput at the target user location.
Tasks
Published	2019-05-19
URL	https://arxiv.org/abs/1905.07726v1
PDF	https://arxiv.org/pdf/1905.07726v1.pdf
PWC	https://paperswithcode.com/paper/indoor-signal-focusing-with-deep-learning
Repo
Framework

Efron-Stein PAC-Bayesian Inequalities


Title	Efron-Stein PAC-Bayesian Inequalities
Authors	Ilja Kuzborskij, Csaba Szepesvári
Abstract	We prove semi-empirical concentration inequalities for random variables which are given as possibly nonlinear functions of independent random variables. These inequalities describe concentration of random variable in terms of the data/distribution-dependent Efron-Stein (ES) estimate of its variance and they do not require any additional assumptions on the moments. In particular, this allows us to state semi-empirical Bernstein type inequalities for general functions of unbounded random variables, which gives user-friendly concentration bounds for cases where related methods (e.g. bounded differences) might be more challenging to apply. We extend these results to Efron-Stein PAC-Bayesian inequalities which hold for arbitrary probability kernels that define a random, data-dependent choice of the function of interest. Finally, we demonstrate a number of applications, including PAC-Bayesian generalization bounds for unbounded loss functions, empirical Bernstein type generalization bounds, new truncation-free bounds for off-policy evaluation with Weighted Importance Sampling (WIS), and off-policy PAC-Bayesian learning with WIS.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01931v2
PDF	https://arxiv.org/pdf/1909.01931v2.pdf
PWC	https://paperswithcode.com/paper/efron-stein-pac-bayesian-inequalities
Repo
Framework

Privacy-preserving Federated Bayesian Learning of a Generative Model for Imbalanced Classification of Clinical Data


Title	Privacy-preserving Federated Bayesian Learning of a Generative Model for Imbalanced Classification of Clinical Data
Authors	Seok-Ju Hahn, Junghye Lee
Abstract	In clinical research, the lack of events of interest often necessitates imbalanced learning. One approach to resolve this obstacle is data integration or sharing, but due to privacy concerns neither is practical. Therefore, there is an increasing demand for a platform on which an analysis can be performed in a federated environment while maintaining privacy. However, it is quite challenging to develop a federated learning algorithm that can address both privacy-preserving and class imbalanced issues. In this study, we introduce a federated generative model learning platform for generating samples in a data-distributed environment while preserving privacy. We specifically propose approximate Bayesian computation-based Gaussian Mixture Model called ‘Federated ABC-GMM’, which can oversample data in a minor class by estimating the posterior distribution of model parameters across institutions in a privacy-preserving manner. PhysioNet2012, a dataset for prediction of mortality of patients in an Intensive Care Unit (ICU), was used to verify the performance of the proposed method. Experimental results show that our method boosts classification performance in terms of F1 score up to nearly an ideal situation. It is believed that the proposed method can be a novel alternative to solving class imbalance problems.
Tasks
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08489v1
PDF	https://arxiv.org/pdf/1910.08489v1.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-federated-bayesian
Repo
Framework

A Closer Look at Data Bias in Neural Extractive Summarization Models


Title	A Closer Look at Data Bias in Neural Extractive Summarization Models
Authors	Ming Zhong, Danqing Wang, Pengfei Liu, Xipeng Qiu, Xuanjing Huang
Abstract	In this paper, we take stock of the current state of summarization datasets and explore how different factors of datasets influence the generalization behaviour of neural extractive summarization models. Specifically, we first propose several properties of datasets, which matter for the generalization of summarization models. Then we build the connection between priors residing in datasets and model designs, analyzing how different properties of datasets influence the choices of model structure design and training methods. Finally, by taking a typical dataset as an example, we rethink the process of the model design based on the experience of the above analysis. We demonstrate that when we have a deep understanding of the characteristics of datasets, a simple approach can bring significant improvements to the existing state-of-the-art model.A
Tasks
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13705v1
PDF	https://arxiv.org/pdf/1909.13705v1.pdf
PWC	https://paperswithcode.com/paper/a-closer-look-at-data-bias-in-neural
Repo
Framework

Machine learning accelerates parameter optimization and uncertainty assessment of a land surface model


Title	Machine learning accelerates parameter optimization and uncertainty assessment of a land surface model
Authors	Yohei Sawada
Abstract	The performance of land surface models (LSMs) significantly affects the understanding of atmospheric and related processes. Many of the LSMs’ soil and vegetation parameters were unknown so that it is crucially important to efficiently optimize them. Here I present a globally applicable and computationally efficient method for parameter optimization and uncertainty assessment of the LSM by combining Markov Chain Monte Carlo (MCMC) with machine learning. First, I performed the long-term (decadal scales) ensemble simulation of the LSM, in which each ensemble member has different parameters’ values, and calculated the gap between simulation and observation, or the cost function, for each ensemble member. Second, I developed the statistical machine learning based surrogate model, which is computationally cheap but accurately mimics the relationship between parameters and the cost function, by applying the Gaussian process regression to learn the model simulation. Third, we applied MCMC by repeatedly driving the surrogate model to get the posterior probabilistic distribution of parameters. Using satellite passive microwave brightness temperature observations, both synthetic and real-data experiments in the Sahel region of west Africa were performed to optimize unknown soil and vegetation parameters of the LSM. The primary findings are (1) the proposed method is 50,000 times as fast as the direct application of MCMC to the full LSM; (2) the skill of the LSM to simulate both soil moisture and vegetation dynamics can be improved; (3) I successfully quantify the characteristics of equifinality by obtaining the full non-parametric probabilistic distribution of parameters.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.04196v2
PDF	https://arxiv.org/pdf/1909.04196v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-accelerates-parameter
Repo
Framework

Towards a Metric for Automated Conversational Dialogue System Evaluation and Improvement


Title	Towards a Metric for Automated Conversational Dialogue System Evaluation and Improvement
Authors	Jan Deriu, Mark Cieliebak
Abstract	We present “AutoJudge”, an automated evaluation method for conversational dialogue systems. The method works by first generating dialogues based on self-talk, i.e. dialogue systems talking to itself. Then, it uses human ratings on these dialogues to train an automated judgement model. Our experiments show that AutoJudge correlates well with the human ratings and can be used to automatically evaluate dialogue systems, even in deployed systems. In a second part, we attempt to apply AutoJudge to improve existing systems. This works well for re-ranking a set of candidate utterances. However, our experiments show that AutoJudge cannot be applied as reward for reinforcement learning, although the metric can distinguish good from bad dialogues. We discuss potential reasons, but state here already that this is still an open question for further research.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12066v1
PDF	https://arxiv.org/pdf/1909.12066v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-metric-for-automated-conversational
Repo
Framework

Regularized Diffusion Adaptation via Conjugate Smoothing


Title	Regularized Diffusion Adaptation via Conjugate Smoothing
Authors	Stefan Vlaski, Lieven Vandenberghe, Ali H. Sayed
Abstract	The purpose of this work is to develop and study a distributed strategy for Pareto optimization of an aggregate cost consisting of regularized risks. Each risk is modeled as the expectation of some loss function with unknown probability distribution while the regularizers are assumed deterministic, but are not required to be differentiable or even continuous. The individual, regularized, cost functions are distributed across a strongly-connected network of agents and the Pareto optimal solution is sought by appealing to a multi-agent diffusion strategy. To this end, the regularizers are smoothed by means of infimal convolution and it is shown that the Pareto solution of the approximate, smooth problem can be made arbitrarily close to the solution of the original, non-smooth problem. Performance bounds are established under conditions that are weaker than assumed before in the literature, and hence applicable to a broader class of adaptation and learning problems.
Tasks
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09417v1
PDF	https://arxiv.org/pdf/1909.09417v1.pdf
PWC	https://paperswithcode.com/paper/regularized-diffusion-adaptation-via
Repo
Framework

Empirical study towards understanding line search approximations for training neural networks


Title	Empirical study towards understanding line search approximations for training neural networks
Authors	Younghwan Chae, Daniel N. Wilke
Abstract	Choosing appropriate step sizes is critical for reducing the computational cost of training large-scale neural network models. Mini-batch sub-sampling (MBSS) is often employed for computational tractability. However, MBSS introduces a sampling error, that can manifest as a bias or variance in a line search. This is because MBSS can be performed statically, where the mini-batch is updated only when the search direction changes, or dynamically, where the mini-batch is updated every-time the function is evaluated. Static MBSS results in a smooth loss function along a search direction, reflecting low variance but large bias in the estimated “true” (or full batch) minimum. Conversely, dynamic MBSS results in a point-wise discontinuous function, with computable gradients using backpropagation, along a search direction, reflecting high variance but lower bias in the estimated “true” (or full batch) minimum. In this study, quadratic line search approximations are considered to study the quality of function and derivative information to construct approximations for dynamic MBSS loss functions. An empirical study is conducted where function and derivative information are enforced in various ways for the quadratic approximations. The results for various neural network problems show that being selective on what information is enforced helps to reduce the variance of predicted step sizes.
Tasks
Published	2019-09-15
URL	https://arxiv.org/abs/1909.06893v1
PDF	https://arxiv.org/pdf/1909.06893v1.pdf
PWC	https://paperswithcode.com/paper/empirical-study-towards-understanding-line
Repo
Framework

Adversarial Examples Versus Cloud-based Detectors: A Black-box Empirical Study


Title	Adversarial Examples Versus Cloud-based Detectors: A Black-box Empirical Study
Authors	Xurong Li, Shouling Ji, Meng Han, Juntao Ji, Zhenyu Ren, Yushan Liu, Chunming Wu
Abstract	Deep learning has been broadly leveraged by major cloud providers, such as Google, AWS and Baidu, to offer various computer vision related services including image classification, object identification, illegal image detection, etc. While recent works extensively demonstrated that deep learning classification models are vulnerable to adversarial examples, cloud-based image detection models, which are more complicated than classifiers, may also have similar security concern but not get enough attention yet. In this paper, we mainly focus on the security issues of real-world cloud-based image detectors. Specifically, (1) based on effective semantic segmentation, we propose four attacks to generate semantics-aware adversarial examples via only interacting with black-box APIs; and (2) we make the first attempt to conduct an extensive empirical study of black-box attacks against real-world cloud-based image detectors. Through the comprehensive evaluations on five major cloud platforms: AWS, Azure, Google Cloud, Baidu Cloud, and Alibaba Cloud, we demonstrate that our image processing based attacks can reach a success rate of approximately 100%, and the semantic segmentation based attacks have a success rate over 90% among different detection services, such as violence, politician, and pornography detection. We also proposed several possible defense strategies for these security challenges in the real-life situation.
Tasks	Image Classification, Pornography Detection, Semantic Segmentation
Published	2019-01-04
URL	https://arxiv.org/abs/1901.01223v4
PDF	https://arxiv.org/pdf/1901.01223v4.pdf
PWC	https://paperswithcode.com/paper/adversarial-examples-versus-cloud-based
Repo
Framework

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation


Title	Bayesian Uncertainty Matching for Unsupervised Domain Adaptation
Authors	Jun Wen, Nenggan Zheng, Junsong Yuan, Zhefeng Gong, Changyou Chen
Abstract	Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by matching marginal feature distributions through deep transformations on the input features, due to the unavailability of target domain labels. We show that domain shift may still exist via label distribution shift at the classifier, thus deteriorating model performances. To alleviate this issue, we propose an approximate joint distribution matching scheme by exploiting prediction uncertainty. Specifically, we use a Bayesian neural network to quantify prediction uncertainty of a classifier. By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains. We also propose a few techniques to improve our method by adaptively reweighting domain adaptation loss to achieve nontrivial distribution matching and stable training. Comparisons with state of the art unsupervised domain adaptation methods on three popular benchmark datasets demonstrate the superiority of our approach, especially on the effectiveness of alleviating negative transfer.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09693v1
PDF	https://arxiv.org/pdf/1906.09693v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-uncertainty-matching-for
Repo
Framework