Paper Group ANR 246
Causal Inference with Noisy and Missing Covariates via Matrix Factorization. Combinatorial framework for planning in geological exploration. CNN-based Landmark Detection in Cardiac CTA Scans. LSD$_2$ - Joint Denoising and Deblurring of Short and Long Exposure Images with Convolutional Neural Networks. Entity-aware Image Caption Generation. Explicit …
Causal Inference with Noisy and Missing Covariates via Matrix Factorization
| Title | Causal Inference with Noisy and Missing Covariates via Matrix Factorization |
| Authors | Nathan Kallus, Xiaojie Mao, Madeleine Udell |
| Abstract | Valid causal inference in observational studies often requires controlling for confounders. However, in practice measurements of confounders may be noisy, and can lead to biased estimates of causal effects. We show that we can reduce the bias caused by measurement noise using a large number of noisy measurements of the underlying confounders. We propose the use of matrix factorization to infer the confounders from noisy covariates, a flexible and principled framework that adapts to missing values, accommodates a wide variety of data types, and can augment many causal inference methods. We bound the error for the induced average treatment effect estimator and show it is consistent in a linear regression setting, using Exponential Family Matrix Completion preprocessing. We demonstrate the effectiveness of the proposed procedure in numerical experiments with both synthetic data and real clinical data. |
| Tasks | Causal Inference, Matrix Completion |
| Published | 2018-06-03 |
| URL | http://arxiv.org/abs/1806.00811v1 |
| http://arxiv.org/pdf/1806.00811v1.pdf | |
| PWC | https://paperswithcode.com/paper/causal-inference-with-noisy-and-missing |
| Repo | |
| Framework | |
Combinatorial framework for planning in geological exploration
| Title | Combinatorial framework for planning in geological exploration |
| Authors | Mark Sh. Levin |
| Abstract | The paper describes combinatorial framework for planning of geological exploration for oil-gas fields. The suggested scheme of the geological exploration involves the following stages: (1) building of special 4-layer tree-like model (layer of geological exploration): productive layer, group of productive layers, oil-gas field, oil-gas region (or group of the fields); (2) generations of local design (exploration) alternatives for each low-layer geological objects: conservation, additional search, independent utilization, joint utilization; (3) multicriteria (i.e., multi-attribute) assessment of the design (exploration) alternatives and their interrelation (compatibility) and mapping if the obtained vector estimates into integrated ordinal scale; (4) hierarchical design (‘bottom-up’) of composite exploration plans for each oil-gas field; (5) integration of the plans into region plans and (6) aggregation of the region plans into a general exploration plan. Stages 2, 3, 4, and 5 are based on hierarchical multicriteria morphological design (HMMD) method (assessment of ranking of alternatives, selection and composition of alternatives into composite alternatives). The composition problem is based on morphological clique model. Aggregation of the obtained modular alternatives (stage 6) is based on detection of a alternatives ‘kernel’ and its extension by addition of elements (multiple choice model). In addition, the usage of multiset estimates for alternatives is described as well. The alternative estimates are based on expert judgment. The suggested combinatorial planning methodology is illustrated by numerical examples for geological exploration of Yamal peninsula. |
| Tasks | |
| Published | 2018-01-22 |
| URL | http://arxiv.org/abs/1801.07229v1 |
| http://arxiv.org/pdf/1801.07229v1.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-framework-for-planning-in |
| Repo | |
| Framework | |
CNN-based Landmark Detection in Cardiac CTA Scans
| Title | CNN-based Landmark Detection in Cardiac CTA Scans |
| Authors | Julia M. H. Noothout, Bob D. de Vos, Jelmer M. Wolterink, Tim Leiner, Ivana Išgum |
| Abstract | Fast and accurate anatomical landmark detection can benefit many medical image analysis methods. Here, we propose a method to automatically detect anatomical landmarks in medical images. Automatic landmark detection is performed with a patch-based fully convolutional neural network (FCNN) that combines regression and classification. For any given image patch, regression is used to predict the 3D displacement vector from the image patch to the landmark. Simultaneously, classification is used to identify patches that contain the landmark. Under the assumption that patches close to a landmark can determine the landmark location more precisely than patches farther from it, only those patches that contain the landmark according to classification are used to determine the landmark location. The landmark location is obtained by calculating the average landmark location using the computed 3D displacement vectors. The method is evaluated using detection of six clinically relevant landmarks in coronary CT angiography (CCTA) scans: the right and left ostium, the bifurcation of the left main coronary artery (LM) into the left anterior descending and the left circumflex artery, and the origin of the right, non-coronary, and left aortic valve commissure. The proposed method achieved an average Euclidean distance error of 2.19 mm and 2.88 mm for the right and left ostium respectively, 3.78 mm for the bifurcation of the LM, and 1.82 mm, 2.10 mm and 1.89 mm for the origin of the right, non-coronary, and left aortic valve commissure respectively, demonstrating accurate performance. The proposed combination of regression and classification can be used to accurately detect landmarks in CCTA scans. |
| Tasks | |
| Published | 2018-04-13 |
| URL | http://arxiv.org/abs/1804.04963v1 |
| http://arxiv.org/pdf/1804.04963v1.pdf | |
| PWC | https://paperswithcode.com/paper/cnn-based-landmark-detection-in-cardiac-cta |
| Repo | |
| Framework | |
LSD$_2$ - Joint Denoising and Deblurring of Short and Long Exposure Images with Convolutional Neural Networks
| Title | LSD$_2$ - Joint Denoising and Deblurring of Short and Long Exposure Images with Convolutional Neural Networks |
| Authors | Janne Mustaniemi, Juho Kannala, Jiri Matas, Simo Särkkä, Janne Heikkilä |
| Abstract | The paper addresses the problem of acquiring highquality photographs with handheld smartphone cameras in low-light imaging conditions. We propose an approach based on capturing pairs of short and long exposure images in rapid succession and fusing them into a single highquality photograph. Unlike existing methods, we take advantage of both images simultaneously and perform a joint denoising and deblurring using a convolutional neural network. The network is trained using a combination of real and simulated data. To that end, we introduce a novel approach for generating realistic short-long exposure image pairs. The evaluation shows that the method produces good images in extremely challenging conditions and outperforms existing denoising and deblurring methods. Furthermore, it enables exposure fusion even in the presence of motion blur. |
| Tasks | Deblurring, Denoising |
| Published | 2018-11-23 |
| URL | http://arxiv.org/abs/1811.09485v2 |
| http://arxiv.org/pdf/1811.09485v2.pdf | |
| PWC | https://paperswithcode.com/paper/lsd_2-joint-denoising-and-deblurring-of-short |
| Repo | |
| Framework | |
Entity-aware Image Caption Generation
| Title | Entity-aware Image Caption Generation |
| Authors | Di Lu, Spencer Whitehead, Lifu Huang, Heng Ji, Shih-Fu Chang |
| Abstract | Current image captioning approaches generate descriptions which lack specific information, such as named entities that are involved in the images. In this paper we propose a new task which aims to generate informative image captions, given images and hashtags as input. We propose a simple but effective approach to tackle this problem. We first train a convolutional neural networks - long short term memory networks (CNN-LSTM) model to generate a template caption based on the input image. Then we use a knowledge graph based collective inference algorithm to fill in the template with specific named entities retrieved via the hashtags. Experiments on a new benchmark dataset collected from Flickr show that our model generates news-style image descriptions with much richer information. Our model outperforms unimodal baselines significantly with various evaluation metrics. |
| Tasks | Image Captioning |
| Published | 2018-04-21 |
| URL | http://arxiv.org/abs/1804.07889v2 |
| http://arxiv.org/pdf/1804.07889v2.pdf | |
| PWC | https://paperswithcode.com/paper/entity-aware-image-caption-generation |
| Repo | |
| Framework | |
Explicit Inductive Bias for Transfer Learning with Convolutional Networks
| Title | Explicit Inductive Bias for Transfer Learning with Convolutional Networks |
| Authors | Xuhong Li, Yves Grandvalet, Franck Davoine |
| Abstract | In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which are at least partially relevant for solving the target task, but would be difficult to extract from the limited amount of data available on the target task. However, besides the initialization with the pre-trained model and the early stopping, there is no mechanism in fine-tuning for retaining the features learned on the source task. In this paper, we investigate several regularization schemes that explicitly promote the similarity of the final solution with the initial model. We show the benefit of having an explicit inductive bias towards the initial model, and we eventually recommend a simple $L^2$ penalty with the pre-trained model being a reference as the baseline of penalty for transfer learning tasks. |
| Tasks | Transfer Learning |
| Published | 2018-02-05 |
| URL | http://arxiv.org/abs/1802.01483v2 |
| http://arxiv.org/pdf/1802.01483v2.pdf | |
| PWC | https://paperswithcode.com/paper/explicit-inductive-bias-for-transfer-learning |
| Repo | |
| Framework | |
Efficient Gauss-Newton-Krylov momentum conservation constrained PDE-LDDMM using the band-limited vector field parameterization
| Title | Efficient Gauss-Newton-Krylov momentum conservation constrained PDE-LDDMM using the band-limited vector field parameterization |
| Authors | Monica Hernandez |
| Abstract | The class of non-rigid registration methods proposed in the framework of PDE-constrained Large Deformation Diffeomorphic Metric Mapping is a particularly interesting family of physically meaningful diffeomorphic registration methods. PDE-constrained LDDMM methods are formulated as constrained variational problems, where the different physical models are imposed using the associated partial differential equations as hard constraints. Inexact Newton-Krylov optimization has shown an excellent numerical accuracy and an extraordinarily fast convergence rate in this framework. However, the Galerkin representation of the non-stationary velocity fields does not provide proper geodesic paths. In a previous work, we proposed a method for PDE-constrained LDDMM parameterized in the space of initial velocity fields under the EPDiff equation. The proposed method provided geodesics in the framework of PDE-constrained LDDMM, and it showed performance competitive to benchmark PDE-constrained LDDMM and EPDiff-LDDMM methods. However, the major drawback of this method was the large memory load inherent to PDE-constrained LDDMM methods and the increased computational time with respect to the benchmark methods. In this work we optimize the computational complexity of the method using the band-limited vector field parameterization closing the loop with our previous works. |
| Tasks | |
| Published | 2018-07-27 |
| URL | http://arxiv.org/abs/1807.11560v1 |
| http://arxiv.org/pdf/1807.11560v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-gauss-newton-krylov-momentum |
| Repo | |
| Framework | |
LearningWord Embeddings for Low-resource Languages by PU Learning
| Title | LearningWord Embeddings for Low-resource Languages by PU Learning |
| Authors | Chao Jiang, Hsiang-Fu Yu, Cho-Jui Hsieh, Kai-Wei Chang |
| Abstract | Word embedding is a key component in many downstream applications in processing natural languages. Existing approaches often assume the existence of a large collection of text for learning effective word embedding. However, such a corpus may not be available for some low-resource languages. In this paper, we study how to effectively learn a word embedding model on a corpus with only a few million tokens. In such a situation, the co-occurrence matrix is sparse as the co-occurrences of many word pairs are unobserved. In contrast to existing approaches often only sample a few unobserved word pairs as negative samples, we argue that the zero entries in the co-occurrence matrix also provide valuable information. We then design a Positive-Unlabeled Learning (PU-Learning) approach to factorize the co-occurrence matrix and validate the proposed approaches in four different languages. |
| Tasks | |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03366v1 |
| http://arxiv.org/pdf/1805.03366v1.pdf | |
| PWC | https://paperswithcode.com/paper/learningword-embeddings-for-low-resource |
| Repo | |
| Framework | |
Multi Layered-Parallel Graph Convolutional Network (ML-PGCN) for Disease Prediction
| Title | Multi Layered-Parallel Graph Convolutional Network (ML-PGCN) for Disease Prediction |
| Authors | Anees Kazi, Shadi Albarqouni, Karsten Kortuem, Nassir Navab |
| Abstract | Structural data from Electronic Health Records as complementary information to imaging data for disease prediction. We incorporate novel weighting layer into the Graph Convolutional Networks, which weights every element of structural data by exploring its relation to the underlying disease. We demonstrate the superiority of our developed technique in terms of computational speed and obtained encouraging results where our method outperforms the state-of-the-art methods when applied to two publicly available datasets ABIDE and Chest X-ray in terms of relative performance for the accuracy of prediction by 5.31 % and 8.15 % and for the area under the ROC curve by 4.96 % and 10.36 % respectively. Additionally, the model is lightweight, fast and easily trainable. |
| Tasks | Disease Prediction |
| Published | 2018-04-28 |
| URL | http://arxiv.org/abs/1804.10776v1 |
| http://arxiv.org/pdf/1804.10776v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-layered-parallel-graph-convolutional |
| Repo | |
| Framework | |
Machine learning for accelerating effective property prediction for poroelasticity problem in stochastic media
| Title | Machine learning for accelerating effective property prediction for poroelasticity problem in stochastic media |
| Authors | Maria Vasilyeva, Aleksey Tyrylgin |
| Abstract | In this paper, we consider a numerical homogenization of the poroelasticity problem with stochastic properties. The proposed method based on the construction of the deep neural network (DNN) for fast calculation of the effective properties for a coarse grid approximation of the problem. We train neural networks on the set of the selected realizations of the local microscale stochastic fields and macroscale characteristics (permeability and elasticity tensors). We construct a deep learning method through convolutional neural network (CNN) to learn a map between stochastic fields and effective properties. Numerical results are presented for two and three-dimensional model problems and show that proposed method provide fast and accurate effective property predictions. |
| Tasks | |
| Published | 2018-10-03 |
| URL | http://arxiv.org/abs/1810.01586v1 |
| http://arxiv.org/pdf/1810.01586v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-accelerating-effective |
| Repo | |
| Framework | |
Goal-Oriented Chatbot Dialog Management Bootstrapping with Transfer Learning
| Title | Goal-Oriented Chatbot Dialog Management Bootstrapping with Transfer Learning |
| Authors | Vladimir Ilievski, Claudiu Musat, Andreea Hossmann, Michael Baeriswyl |
| Abstract | Goal-Oriented (GO) Dialogue Systems, colloquially known as goal oriented chatbots, help users achieve a predefined goal (e.g. book a movie ticket) within a closed domain. A first step is to understand the user’s goal by using natural language understanding techniques. Once the goal is known, the bot must manage a dialogue to achieve that goal, which is conducted with respect to a learnt policy. The success of the dialogue system depends on the quality of the policy, which is in turn reliant on the availability of high-quality training data for the policy learning method, for instance Deep Reinforcement Learning. Due to the domain specificity, the amount of available data is typically too low to allow the training of good dialogue policies. In this paper we introduce a transfer learning method to mitigate the effects of the low in-domain data availability. Our transfer learning based approach improves the bot’s success rate by 20% in relative terms for distant domains and we more than double it for close domains, compared to the model without transfer learning. Moreover, the transfer learning chatbots learn the policy up to 5 to 10 times faster. Finally, as the transfer learning approach is complementary to additional processing such as warm-starting, we show that their joint application gives the best outcomes. |
| Tasks | Chatbot, Transfer Learning |
| Published | 2018-02-01 |
| URL | http://arxiv.org/abs/1802.00500v2 |
| http://arxiv.org/pdf/1802.00500v2.pdf | |
| PWC | https://paperswithcode.com/paper/goal-oriented-chatbot-dialog-management |
| Repo | |
| Framework | |
A conjugate prior for the Dirichlet distribution
| Title | A conjugate prior for the Dirichlet distribution |
| Authors | Jean-Marc Andreoli |
| Abstract | This note investigates a conjugate class for the Dirichlet distribution class in the exponential family. |
| Tasks | |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05266v1 |
| http://arxiv.org/pdf/1811.05266v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-conjugate-prior-for-the-dirichlet |
| Repo | |
| Framework | |
Combining Symbolic Expressions and Black-box Function Evaluations in Neural Programs
| Title | Combining Symbolic Expressions and Black-box Function Evaluations in Neural Programs |
| Authors | Forough Arabshahi, Sameer Singh, Animashree Anandkumar |
| Abstract | Neural programming involves training neural networks to learn programs, mathematics, or logic from data. Previous works have failed to achieve good generalization performance, especially on problems and programs with high complexity or on large domains. This is because they mostly rely either on black-box function evaluations that do not capture the structure of the program, or on detailed execution traces that are expensive to obtain, and hence the training data has poor coverage of the domain under consideration. We present a novel framework that utilizes black-box function evaluations, in conjunction with symbolic expressions that define relationships between the given functions. We employ tree LSTMs to incorporate the structure of the symbolic expression trees. We use tree encoding for numbers present in function evaluation data, based on their decimal representation. We present an evaluation benchmark for this task to demonstrate our proposed model combines symbolic reasoning and function evaluation in a fruitful manner, obtaining high accuracies in our experiments. Our framework generalizes significantly better to expressions of higher depth and is able to fill partial equations with valid completions. |
| Tasks | |
| Published | 2018-01-12 |
| URL | http://arxiv.org/abs/1801.04342v3 |
| http://arxiv.org/pdf/1801.04342v3.pdf | |
| PWC | https://paperswithcode.com/paper/combining-symbolic-expressions-and-black-box |
| Repo | |
| Framework | |
Graph Node-Feature Convolution for Representation Learning
| Title | Graph Node-Feature Convolution for Representation Learning |
| Authors | Li Zhang, Heda Song, Haiping Lu |
| Abstract | Graph convolutional network (GCN) is an emerging neural network approach. It learns new representation of a node by aggregating feature vectors of all neighbors in the aggregation process without considering whether the neighbors or features are useful or not. Recent methods have improved solutions by sampling a fixed size set of neighbors, or assigning different weights to different neighbors in the aggregation process, but features within a feature vector are still treated equally in the aggregation process. In this paper, we introduce a new convolution operation on regular size feature maps constructed from features of a fixed node bandwidth via sampling to get the first-level node representation, which is then passed to a standard GCN to learn the second-level node representation. Experiments show that our method outperforms competing methods in semi-supervised node classification tasks. Furthermore, our method opens new doors for exploring new GCN architectures, particularly deeper GCN models. |
| Tasks | Node Classification, Representation Learning |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1812.00086v1 |
| http://arxiv.org/pdf/1812.00086v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-node-feature-convolution-for |
| Repo | |
| Framework | |
Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images using Bayesian Deep Learning
| Title | Joint Segmentation and Uncertainty Visualization of Retinal Layers in Optical Coherence Tomography Images using Bayesian Deep Learning |
| Authors | Suman Sedai, Bhavna Antony, Dwarikanath Mahapatra, Rahil Garnavi |
| Abstract | Optical coherence tomography (OCT) is commonly used to analyze retinal layers for assessment of ocular diseases. In this paper, we propose a method for retinal layer segmentation and quantification of uncertainty based on Bayesian deep learning. Our method not only performs end-to-end segmentation of retinal layers, but also gives the pixel wise uncertainty measure of the segmentation output. The generated uncertainty map can be used to identify erroneously segmented image regions which is useful in downstream analysis. We have validated our method on a dataset of 1487 images obtained from 15 subjects (OCT volumes) and compared it against the state-of-the-art segmentation algorithms that does not take uncertainty into account. The proposed uncertainty based segmentation method results in comparable or improved performance, and most importantly is more robust against noise. |
| Tasks | |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04282v1 |
| http://arxiv.org/pdf/1809.04282v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-segmentation-and-uncertainty |
| Repo | |
| Framework | |
