October 16, 2019

3112 words 15 mins read

Paper Group ANR 1025

Request-and-Reverify: Hierarchical Hypothesis Testing for Concept Drift Detection with Expensive Labels. MetaBags: Bagged Meta-Decision Trees for Regression. Hierarchical Clustering with Structural Constraints. Weighted Tanimoto Coefficient for 3D Molecule Structure Similarity Measurement. More Knowledge is Better: Cross-Modality Volume Completion …

Request-and-Reverify: Hierarchical Hypothesis Testing for Concept Drift Detection with Expensive Labels


Title	Request-and-Reverify: Hierarchical Hypothesis Testing for Concept Drift Detection with Expensive Labels
Authors	Shujian Yu, Xiaoyang Wang, Jose C. Principe
Abstract	One important assumption underlying common classification models is the stationarity of the data. However, in real-world streaming applications, the data concept indicated by the joint distribution of feature and label is not stationary but drifting over time. Concept drift detection aims to detect such drifts and adapt the model so as to mitigate any deterioration in the model’s predictive performance. Unfortunately, most existing concept drift detection methods rely on a strong and over-optimistic condition that the true labels are available immediately for all already classified instances. In this paper, a novel Hierarchical Hypothesis Testing framework with Request-and-Reverify strategy is developed to detect concept drifts by requesting labels only when necessary. Two methods, namely Hierarchical Hypothesis Testing with Classification Uncertainty (HHT-CU) and Hierarchical Hypothesis Testing with Attribute-wise “Goodness-of-fit” (HHT-AG), are proposed respectively under the novel framework. In experiments with benchmark datasets, our methods demonstrate overwhelming advantages over state-of-the-art unsupervised drift detectors. More importantly, our methods even outperform DDM (the widely used supervised drift detector) when we use significantly fewer labels.
Tasks
Published	2018-06-25
URL	http://arxiv.org/abs/1806.10131v2
PDF	http://arxiv.org/pdf/1806.10131v2.pdf
PWC	https://paperswithcode.com/paper/request-and-reverify-hierarchical-hypothesis
Repo
Framework

MetaBags: Bagged Meta-Decision Trees for Regression


Title	MetaBags: Bagged Meta-Decision Trees for Regression
Authors	Jihed Khiari, Luis Moreira-Matias, Ammar Shaker, Bernard Zenko, Saso Dzeroski
Abstract	Ensembles are popular methods for solving practical supervised learning problems. They reduce the risk of having underperforming models in production-grade software. Although critical, methods for learning heterogeneous regression ensembles have not been proposed at large scale, whereas in classical ML literature, stacking, cascading and voting are mostly restricted to classification problems. Regression poses distinct learning challenges that may result in poor performance, even when using well established homogeneous ensemble schemas such as bagging or boosting. In this paper, we introduce MetaBags, a novel, practically useful stacking framework for regression. MetaBags is a meta-learning algorithm that learns a set of meta-decision trees designed to select one base model (i.e. expert) for each query, and focuses on inductive bias reduction. A set of meta-decision trees are learned using different types of meta-features, specially created for this purpose - to then be bagged at meta-level. This procedure is designed to learn a model with a fair bias-variance trade-off, and its improvement over base model performance is correlated with the prediction diversity of different experts on specific input space subregions. The proposed method and meta-features are designed in such a way that they enable good predictive performance even in subregions of space which are not adequately represented in the available training data. An exhaustive empirical testing of the method was performed, evaluating both generalization error and scalability of the approach on synthetic, open and real-world application datasets. The obtained results show that our method significantly outperforms existing state-of-the-art approaches.
Tasks	Meta-Learning
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06207v1
PDF	http://arxiv.org/pdf/1804.06207v1.pdf
PWC	https://paperswithcode.com/paper/metabags-bagged-meta-decision-trees-for
Repo
Framework

Hierarchical Clustering with Structural Constraints


Title	Hierarchical Clustering with Structural Constraints
Authors	Vaggos Chatziafratis, Rad Niazadeh, Moses Charikar
Abstract	Hierarchical clustering is a popular unsupervised data analysis method. For many real-world applications, we would like to exploit prior information about the data that imposes constraints on the clustering hierarchy, and is not captured by the set of features available to the algorithm. This gives rise to the problem of “hierarchical clustering with structural constraints”. Structural constraints pose major challenges for bottom-up approaches like average/single linkage and even though they can be naturally incorporated into top-down divisive algorithms, no formal guarantees exist on the quality of their output. In this paper, we provide provable approximation guarantees for two simple top-down algorithms, using a recently introduced optimization viewpoint of hierarchical clustering with pairwise similarity information [Dasgupta, 2016]. We show how to find good solutions even in the presence of conflicting prior information, by formulating a constraint-based regularization of the objective. We further explore a variation of this objective for dissimilarity information [Cohen-Addad et al., 2018] and improve upon current techniques. Finally, we demonstrate our approach on a real dataset for the taxonomy application.
Tasks
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09476v2
PDF	http://arxiv.org/pdf/1805.09476v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-clustering-with-structural
Repo
Framework

Weighted Tanimoto Coefficient for 3D Molecule Structure Similarity Measurement


Title	Weighted Tanimoto Coefficient for 3D Molecule Structure Similarity Measurement
Authors	Siti Asmah Bero, Azah Kamilah Muda, Yun-Huoy Choo, Noor Azilah Muda, Satrya Fajri Pratama
Abstract	Similarity searching of molecular structure has been an important application in the Chemoinformatics, especially in drug discovery. Similarity searching is a common method used for identification of molecular structure. It involve three main principal component of similarity searching: structure representation; weighting scheme; and similarity coefficient. In this paper, we introduces Weighted Tanimoto Coefficient based on weighted Euclidean distance in order to investigate the effect of weight function on the result for similarity searching. The Tanimoto coefficient is one of the popular similarity coefficients used to measure the similarity between pairs of the molecule. The most of research area found that the similarity searching is based on binary or fingerprint data. Meanwhile, we used non-binary data and was set amphetamine structure as a reference or targeted structure and the rest of the dataset becomes a database structure. Throughout this study, it showed that there is definitely gives a different result between a similarity searching with and without weight.
Tasks	Drug Discovery
Published	2018-06-10
URL	http://arxiv.org/abs/1806.05237v1
PDF	http://arxiv.org/pdf/1806.05237v1.pdf
PWC	https://paperswithcode.com/paper/weighted-tanimoto-coefficient-for-3d-molecule
Repo
Framework

More Knowledge is Better: Cross-Modality Volume Completion and 3D+2D Segmentation for Intracardiac Echocardiography Contouring


Title	More Knowledge is Better: Cross-Modality Volume Completion and 3D+2D Segmentation for Intracardiac Echocardiography Contouring
Authors	Haofu Liao, Yucheng Tang, Gareth Funka-Lea, Jiebo Luo, Shaohua Kevin Zhou
Abstract	Using catheter ablation to treat atrial fibrillation increasingly relies on intracardiac echocardiography (ICE) for an anatomical delineation of the left atrium and the pulmonary veins that enter the atrium. However, it is a challenge to build an automatic contouring algorithm because ICE is noisy and provides only a limited 2D view of the 3D anatomy. This work provides the first automatic solution to segment the left atrium and the pulmonary veins from ICE. In this solution, we demonstrate the benefit of building a cross-modality framework that can leverage a database of diagnostic images to supplement the less available interventional images. To this end, we develop a novel deep neural network approach that uses the (i) 3D geometrical information provided by a position sensor embedded in the ICE catheter and the (ii) 3D image appearance information from a set of computed tomography cardiac volumes. We evaluate the proposed approach over 11,000 ICE images collected from 150 clinical patients. Experimental results show that our model is significantly better than a direct 2D image-to-image deep neural network segmentation, especially for less-observed structures.
Tasks
Published	2018-12-09
URL	https://arxiv.org/abs/1812.03507v2
PDF	https://arxiv.org/pdf/1812.03507v2.pdf
PWC	https://paperswithcode.com/paper/more-knowledge-is-better-cross-modality
Repo
Framework

NengoDL: Combining deep learning and neuromorphic modelling methods


Title	NengoDL: Combining deep learning and neuromorphic modelling methods
Authors	Daniel Rasmussen
Abstract	NengoDL is a software framework designed to combine the strengths of neuromorphic modelling and deep learning. NengoDL allows users to construct biologically detailed neural models, intermix those models with deep learning elements (such as convolutional networks), and then efficiently simulate those models in an easy-to-use, unified framework. In addition, NengoDL allows users to apply deep learning training methods to optimize the parameters of biological neural models. In this paper we present basic usage examples, benchmarking, and details on the key implementation elements of NengoDL. More details can be found at https://www.nengo.ai/nengo-dl .
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.11144v3
PDF	http://arxiv.org/pdf/1805.11144v3.pdf
PWC	https://paperswithcode.com/paper/nengodl-combining-deep-learning-and
Repo
Framework

Optimal Transport for Multi-source Domain Adaptation under Target Shift


Title	Optimal Transport for Multi-source Domain Adaptation under Target Shift
Authors	Ievgen Redko, Nicolas Courty, Rémi Flamary, Devis Tuia
Abstract	In this paper, we propose to tackle the problem of reducing discrepancies between multiple domains referred to as multi-source domain adaptation and consider it under the target shift assumption: in all domains we aim to solve a classification problem with the same output classes, but with labels’ proportions differing across them. This problem, generally ignored in the vast majority papers on domain adaptation papers, is nevertheless critical in real-world applications, and we theoretically show its impact on the adaptation success. To address this issue, we design a method based on optimal transport, a theory that has been successfully used to tackle adaptation problems in machine learning. Our method performs multi-source adaptation and target shift correction simultaneously by learning the class probabilities of the unlabeled target sample and the coupling allowing to align two (or more) probability distributions. Experiments on both synthetic and real-world data related to satellite image segmentation task show the superiority of the proposed method over the state-of-the-art.
Tasks	Domain Adaptation, Semantic Segmentation
Published	2018-03-13
URL	http://arxiv.org/abs/1803.04899v3
PDF	http://arxiv.org/pdf/1803.04899v3.pdf
PWC	https://paperswithcode.com/paper/optimal-transport-for-multi-source-domain
Repo
Framework

Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization


Title	Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization
Authors	Bryan Wilder, Bistra Dilkina, Milind Tambe
Abstract	Creating impact in real-world settings requires artificial intelligence techniques to span the full pipeline from data, to predictive models, to decisions. These components are typically approached separately: a machine learning model is first trained via a measure of predictive accuracy, and then its predictions are used as input into an optimization algorithm which produces a decision. However, the loss function used to train the model may easily be misaligned with the end goal, which is to make the best decisions possible. Hand-tuning the loss function to align with optimization is a difficult and error-prone process (which is often skipped entirely). We focus on combinatorial optimization problems and introduce a general framework for decision-focused learning, where the machine learning model is directly trained in conjunction with the optimization algorithm to produce high-quality decisions. Technically, our contribution is a means of integrating common classes of discrete optimization problems into deep learning or other predictive models, which are typically trained via gradient descent. The main idea is to use a continuous relaxation of the discrete problem to propagate gradients through the optimization procedure. We instantiate this framework for two broad classes of combinatorial problems: linear programs and submodular maximization. Experimental results across a variety of domains show that decision-focused learning often leads to improved optimization performance compared to traditional methods. We find that standard measures of accuracy are not a reliable proxy for a predictive model’s utility in optimization, and our method’s ability to specify the true goal as the model’s training objective yields substantial dividends across a range of decision problems.
Tasks	Combinatorial Optimization
Published	2018-09-14
URL	http://arxiv.org/abs/1809.05504v2
PDF	http://arxiv.org/pdf/1809.05504v2.pdf
PWC	https://paperswithcode.com/paper/melding-the-data-decisions-pipeline-decision
Repo
Framework

Learning to Segment Corneal Tissue Interfaces in OCT Images


Title	Learning to Segment Corneal Tissue Interfaces in OCT Images
Authors	Tejas Sudharshan Mathai, Kira Lathrop, John Galeotti
Abstract	Accurate and repeatable delineation of corneal tissue interfaces is necessary for surgical planning during anterior segment interventions, such as Keratoplasty. Designing an approach to identify interfaces, which generalizes to datasets acquired from different Optical Coherence Tomographic (OCT) scanners, is paramount. In this paper, we present a Convolutional Neural Network (CNN) based framework called CorNet that can accurately segment three corneal interfaces across datasets obtained with different scan settings from different OCT scanners. Extensive validation of the approach was conducted across all imaged datasets. To the best of our knowledge, this is the first deep learning based approach to segment both anterior and posterior corneal tissue interfaces. Our errors are 2x lower than non-proprietary state-of-the-art corneal tissue interface segmentation algorithms, which include image analysis-based and deep learning approaches.
Tasks
Published	2018-10-15
URL	http://arxiv.org/abs/1810.06612v4
PDF	http://arxiv.org/pdf/1810.06612v4.pdf
PWC	https://paperswithcode.com/paper/learning-to-segment-corneal-tissue-interfaces
Repo
Framework

Chemi-net: a graph convolutional network for accurate drug property prediction


Title	Chemi-net: a graph convolutional network for accurate drug property prediction
Authors	Ke Liu, Xiangyan Sun, Lei Jia, Jun Ma, Haoming Xing, Junqiu Wu, Hua Gao, Yax Sun, Florian Boulnois, Jie Fan
Abstract	Absorption, distribution, metabolism, and excretion (ADME) studies are critical for drug discovery. Conventionally, these tasks, together with other chemical property predictions, rely on domain-specific feature descriptors, or fingerprints. Following the recent success of neural networks, we developed Chemi-Net, a completely data-driven, domain knowledge-free, deep learning method for ADME property prediction. To compare the relative performance of Chemi-Net with Cubist, one of the popular machine learning programs used by Amgen, a large-scale ADME property prediction study was performed on-site at Amgen. The results showed that our deep neural network method improved current methods by a large margin. We foresee that the significantly increased accuracy of ADME prediction seen with Chemi-Net over Cubist will greatly accelerate drug discovery.
Tasks	Drug Discovery
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06236v2
PDF	http://arxiv.org/pdf/1803.06236v2.pdf
PWC	https://paperswithcode.com/paper/chemi-net-a-graph-convolutional-network-for
Repo
Framework

Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner


Title	Aiming to Know You Better Perhaps Makes Me a More Engaging Dialogue Partner
Authors	Yury Zemlyanskiy, Fei Sha
Abstract	There have been several attempts to define a plausible motivation for a chit-chat dialogue agent that can lead to engaging conversations. In this work, we explore a new direction where the agent specifically focuses on discovering information about its interlocutor. We formalize this approach by defining a quantitative metric. We propose an algorithm for the agent to maximize it. We validate the idea with human evaluation where our system outperforms various baselines. We demonstrate that the metric indeed correlates with the human judgments of engagingness.
Tasks
Published	2018-08-21
URL	http://arxiv.org/abs/1808.07104v1
PDF	http://arxiv.org/pdf/1808.07104v1.pdf
PWC	https://paperswithcode.com/paper/aiming-to-know-you-better-perhaps-makes-me-a
Repo
Framework

Towards a Deep Unified Framework for Nuclear Reactor Perturbation Analysis


Title	Towards a Deep Unified Framework for Nuclear Reactor Perturbation Analysis
Authors	Fabio De Sousa Ribeiro, Francesco Caliva, Dionysios Chionis, Abdelhamid Dokhane, Antonios Mylonakis, Christophe Demaziere, Georgios Leontidis, Stefanos Kollias
Abstract	In this paper, we take the first steps towards a novel unified framework for the analysis of perturbations in both the Time and Frequency domains. The identification of type and source of such perturbations is fundamental for monitoring reactor cores and guarantee safety while running at nominal conditions. A 3D Convolutional Neural Network (3D-CNN) was employed to analyse perturbations happening in the frequency domain, such as an absorber of variable strength or propagating perturbation. Recurrent neural networks (RNN), specifically Long Short-Term Memory (LSTM) networks were used to study signal sequences related to perturbations induced in the time domain, including the vibrations of fuel assemblies and the fluctuations of thermal-hydraulic parameters at the inlet of the reactor coolant loops. 512 dimensional representations were extracted from the 3D-CNN and LSTM architectures, and used as input to a fused multi-sigmoid classification layer to recognise the perturbation type. If the perturbation is in the frequency domain, a separate fully-connected layer utilises said representations to regress the coordinates of its source. The results showed that the perturbation type can be recognised with high accuracy in all cases, and frequency domain scenario sources can be localised with high precision.
Tasks
Published	2018-07-26
URL	http://arxiv.org/abs/1807.10096v2
PDF	http://arxiv.org/pdf/1807.10096v2.pdf
PWC	https://paperswithcode.com/paper/towards-a-deep-unified-framework-for-nuclear
Repo
Framework

Deep Clustering Based on a Mixture of Autoencoders


Title	Deep Clustering Based on a Mixture of Autoencoders
Authors	Shlomo E. Chazan, Sharon Gannot, Jacob Goldberger
Abstract	In this paper we propose a Deep Autoencoder MIxture Clustering (DAMIC) algorithm based on a mixture of deep autoencoders where each cluster is represented by an autoencoder. A clustering network transforms the data into another space and then selects one of the clusters. Next, the autoencoder associated with this cluster is used to reconstruct the data-point. The clustering algorithm jointly learns the nonlinear data representation and the set of autoencoders. The optimal clustering is found by minimizing the reconstruction loss of the mixture of autoencoder network. Unlike other deep clustering algorithms, no regularization term is needed to avoid data collapsing to a single point. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods.
Tasks
Published	2018-12-16
URL	http://arxiv.org/abs/1812.06535v2
PDF	http://arxiv.org/pdf/1812.06535v2.pdf
PWC	https://paperswithcode.com/paper/deep-clustering-based-on-a-mixture-of
Repo
Framework

Fast and Accurate Recognition of Chinese Clinical Named Entities with Residual Dilated Convolutions


Title	Fast and Accurate Recognition of Chinese Clinical Named Entities with Residual Dilated Convolutions
Authors	Jiahui Qiu, Qi Wang, Yangming Zhou, Tong Ruan, Ju Gao
Abstract	Clinical Named Entity Recognition (CNER) aims to identify and classify clinical terms such as diseases, symptoms, treatments, exams, and body parts in electronic health records, which is a fundamental and crucial task for clinical and translation research. In recent years, deep learning methods have achieved significant success in CNER tasks. However, these methods depend greatly on Recurrent Neural Networks (RNNs), which maintain a vector of hidden activations that are propagated through time, thus causing too much time to train models. In this paper, we propose a Residual Dilated Convolutional Neural Network with Conditional Random Field (RD-CNN-CRF) to solve it. Specifically, Chinese characters and dictionary features are first projected into dense vector representations, then they are fed into the residual dilated convolutional neural network to capture contextual features. Finally, a conditional random field is employed to capture dependencies between neighboring tags. Computational results on the CCKS-2017 Task 2 benchmark dataset show that our proposed RD-CNN-CRF method competes favorably with state-of-the-art RNN-based methods both in terms of computational performance and training time.
Tasks	Named Entity Recognition
Published	2018-08-27
URL	http://arxiv.org/abs/1808.08669v3
PDF	http://arxiv.org/pdf/1808.08669v3.pdf
PWC	https://paperswithcode.com/paper/fast-and-accurate-recognition-of-chinese
Repo
Framework

Correction by Projection: Denoising Images with Generative Adversarial Networks


Title	Correction by Projection: Denoising Images with Generative Adversarial Networks
Authors	Subarna Tripathi, Zachary C. Lipton, Truong Q. Nguyen
Abstract	Generative adversarial networks (GANs) transform low-dimensional latent vectors into visually plausible images. If the real dataset contains only clean images, then ostensibly, the manifold learned by the GAN should contain only clean images. In this paper, we propose to denoise corrupted images by finding the nearest point on the GAN manifold, recovering latent vectors by minimizing distances in image space. We first demonstrate that given a corrupted version of an image that truly lies on the GAN manifold, we can approximately recover the latent vector and denoise the image, obtaining significantly higher quality, comparing with BM3D. Next, we demonstrate that latent vectors recovered from noisy images exhibit a consistent bias. By subtracting this bias before projecting back to image space, we improve denoising results even further. Finally, even for unseen images, our method performs better at denoising better than BM3D. Notably, the basic version of our method (without bias correction) requires no prior knowledge on the noise variance. To achieve the highest possible denoising quality, the best performing signal processing based methods, such as BM3D, require an estimate of the blur kernel.
Tasks	Denoising
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04477v1
PDF	http://arxiv.org/pdf/1803.04477v1.pdf
PWC	https://paperswithcode.com/paper/correction-by-projection-denoising-images
Repo
Framework