January 27, 2020

3174 words 15 mins read

Paper Group ANR 1173

A global approach for learning sparse Ising models. Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel Survey. Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances. Enabling Multi-Shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE. Financial Event Extraction Using Wikip …

A global approach for learning sparse Ising models


Title	A global approach for learning sparse Ising models
Authors	Daniela De Canditiis
Abstract	We consider the problem of learning the link parameters as well as the structure of a binary-valued pairwise Markov model. Under sparsity assumption, we propose a method based on $l_1$- regularized logistic regression, which estimate globally the whole set of edges and link parameters. Unlike the more recent methods discussed in literature that learn the edges and the corresponding link parameters one node at a time, in this work we propose a method that learns all the edges and corresponding link parameters simultaneously for all nodes. The idea behind this proposal is to exploit the reciprocal information of the nodes between each other during the estimation process. Numerical experiments highlight the advantage of this technique and confirm the intuition behind it.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11641v2
PDF	https://arxiv.org/pdf/1906.11641v2.pdf
PWC	https://paperswithcode.com/paper/a-global-approach-for-learning-sparse-ising
Repo
Framework

Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel Survey


Title	Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel Survey
Authors	Ali Yazdizadeh, Zachary Patterson, Bilal Farooq
Abstract	We develop ensemble Convolutional Neural Networks (CNNs) to classify the transportation mode of trip data collected as part of a large-scale smartphone travel survey in Montreal, Canada. Our proposed ensemble library is composed of a series of CNN models with different hyper-parameter values and CNN architectures. In our final model, we combine the output of CNN models using “average voting”, “majority voting” and “optimal weights” methods. Furthermore, we exploit the ensemble library by deploying a Random Forest model as a meta-learner. The ensemble method with random forest as meta-learner shows an accuracy of 91.8% which surpasses the other three ensemble combination methods, as well as other comparable models reported in the literature. The “majority voting” and “optimal weights” combination methods result in prediction accuracy rates around 89%, while “average voting” is able to achieve an accuracy of only 85%.
Tasks
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08933v1
PDF	http://arxiv.org/pdf/1904.08933v1.pdf
PWC	https://paperswithcode.com/paper/ensemble-convolutional-neural-networks-for
Repo
Framework

Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances


Title	Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances
Authors	Vitor Guizilini, Jie Li, Rares Ambrus, Sudeep Pillai, Adrien Gaidon
Abstract	Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks. Initially viewed as a direct regression problem, requiring annotated labels as supervision at training time, in the past few years a substantial amount of work has been done in self-supervised depth training based on strong geometric cues, both from stereo cameras and more recently from monocular video sequences. In this paper we investigate how these two approaches (supervised & self-supervised) can be effectively combined, so that a depth model can learn to encode true scale from sparse supervision while achieving high fidelity local accuracy by leveraging geometric cues. To this end, we propose a novel supervised loss term that complements the widely used photometric loss, and show how it can be used to train robust semi-supervised monocular depth estimation models. Furthermore, we evaluate how much supervision is actually necessary to train accurate scale-aware monocular depth models, showing that with our proposed framework, very sparse LiDAR information, with as few as 4 beams (less than 100 valid depth values per image), is enough to achieve results competitive with the current state-of-the-art.
Tasks	Depth Estimation, Monocular Depth Estimation
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01765v3
PDF	https://arxiv.org/pdf/1910.01765v3.pdf
PWC	https://paperswithcode.com/paper/robust-semi-supervised-monocular-depth
Repo
Framework

Enabling Multi-Shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE


Title	Enabling Multi-Shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE
Authors	Vishwesh Nath, Ilwoo Lyu, Kurt G. Schilling, Prasanna Parvathaneni, Colin B. Hansen, Yucheng Tang, Yuankai Huo, Vaibhav A. Janve, Yurui Gao, Iwona Stepniewska, Adam W. Anderson, Bennett A. Landman
Abstract	Intra-voxel models of the diffusion signal are essential for interpreting organization of the tissue environment at micrometer level with data at millimeter resolution. Recent advances in data driven methods have enabled direct compari-son and optimization of methods for in-vivo data with externally validated histological sections with both 2-D and 3-D histology. Yet, all existing methods make limiting assumptions of either (1) model-based linkages between b-values or (2) limited associations with single shell data. We generalize prior deep learning models that used single shell spherical harmonic transforms to integrate the re-cently developed simple harmonic oscillator reconstruction (SHORE) basis. To enable learning on the SHORE manifold, we present an alternative formulation of the fiber orientation distribution (FOD) object using the SHORE basis while rep-resenting the observed diffusion weighted data in the SHORE basis. To ensure consistency of hyper-parameter optimization for SHORE, we present our Deep SHORE approach to learn on a data-optimized manifold. Deep SHORE is evalu-ated with eight-fold cross-validation of a preclinical MRI-histology data with four b-values. Generalizability of in-vivo human data is evaluated on two separate 3T MRI scanners. Specificity in terms of angular correlation (ACC) with the preclinical data improved on single shell: 0.78 relative to 0.73 and 0.73, multi-shell: 0.80 relative to 0.74 (p < 0.001). In the in-vivo human data, Deep SHORE was more consistent across scanners with 0.63 relative to other multi-shell methods 0.39, 0.52 and 0.57 in terms of ACC. In conclusion, Deep SHORE is a promising method to enable data driven learning with DW-MRI under conditions with varying b-values, number of diffusion shells, and gradient directions per shell.
Tasks
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06319v3
PDF	https://arxiv.org/pdf/1907.06319v3.pdf
PWC	https://paperswithcode.com/paper/enabling-multi-shell-b-value-generalizability
Repo
Framework

Financial Event Extraction Using Wikipedia-Based Weak Supervision


Title	Financial Event Extraction Using Wikipedia-Based Weak Supervision
Authors	Liat Ein-Dor, Ariel Gera, Orith Toledo-Ronen, Alon Halfon, Benjamin Sznajder
Abstract	Extraction of financial and economic events from text has previously been done mostly using rule-based methods, with more recent works employing machine learning techniques. This work is in line with this latter approach, leveraging relevant Wikipedia sections to extract weak labels for sentences describing economic events. Whereas previous weakly supervised approaches required a knowledge-base of such events, or corresponding financial figures, our approach requires no such additional data, and can be employed to extract economic events related to companies which are not even mentioned in the training data.
Tasks
Published	2019-11-25
URL	https://arxiv.org/abs/1911.10783v1
PDF	https://arxiv.org/pdf/1911.10783v1.pdf
PWC	https://paperswithcode.com/paper/financial-event-extraction-using-wikipedia-1
Repo
Framework

Learning Sparse Distributions using Iterative Hard Thresholding


Title	Learning Sparse Distributions using Iterative Hard Thresholding
Authors	Jacky Y. Zhang, Rajiv Khanna, Anastasios Kyrillidis, Oluwasanmi Koyejo
Abstract	Iterative hard thresholding (IHT) is a projected gradient descent algorithm, known to achieve state of the art performance for a wide range of structured estimation problems, such as sparse inference. In this work, we consider IHT as a solution to the problem of learning sparse discrete distributions. We study the hardness of using IHT on the space of measures. As a practical alternative, we propose a greedy approximate projection which simultaneously captures appropriate notions of sparsity in distributions, while satisfying the simplex constraint, and investigate the convergence behavior of the resulting procedure in various settings. Our results show, both in theory and practice, that IHT can achieve state of the art results for learning sparse distributions.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13389v3
PDF	https://arxiv.org/pdf/1910.13389v3.pdf
PWC	https://paperswithcode.com/paper/191013389
Repo
Framework

Machine learning and behavioral economics for personalized choice architecture


Title	Machine learning and behavioral economics for personalized choice architecture
Authors	Emir Hrnjic, Nikodem Tomczak
Abstract	Behavioral economics changed the way we think about market participants and revolutionized policy-making by introducing the concept of choice architecture. However, even though effective on the level of a population, interventions from behavioral economics, nudges, are often characterized by weak generalisation as they struggle on the level of individuals. Recent developments in data science, artificial intelligence (AI) and machine learning (ML) have shown ability to alleviate some of the problems of weak generalisation by providing tools and methods that result in models with stronger predictive power. This paper aims to describe how ML and AI can work with behavioral economics to support and augment decision-making and inform policy decisions by designing personalized interventions, assuming that enough personalized traits and psychological variables can be sampled.
Tasks	Decision Making
Published	2019-07-03
URL	https://arxiv.org/abs/1907.02100v1
PDF	https://arxiv.org/pdf/1907.02100v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-and-behavioral-economics-for
Repo
Framework

Efficient Multi-robot Exploration via Multi-head Attention-based Cooperation Strategy


Title	Efficient Multi-robot Exploration via Multi-head Attention-based Cooperation Strategy
Authors	Shuqi Liu, Zhaoxia Wu
Abstract	The goal of coordinated multi-robot exploration tasks is to employ a team of autonomous robots to explore an unknown environment as quickly as possible. Compared with human-designed methods, which began with heuristic and rule-based approaches, learning-based methods enable individual robots to learn sophisticated and hard-to-design cooperation strategies through deep reinforcement learning technologies. However, in decentralized multi-robot exploration tasks, learning-based algorithms are still far from being universally applicable to the continuous space due to the difficulties associated with area calculation and reward function designing; moreover, existing learning-based methods encounter problems when attempting to balance the historical trajectory issue and target area conflict problem. Furthermore, the scalability of these methods to a large number of agents is poor because of the exponential explosion problem of state space. Accordingly, this paper proposes a novel approach - Multi-head Attention-based Multi-robot Exploration in Continuous Space (MAMECS) - aimed at reducing the state space and automatically learning the cooperation strategies required for decentralized multi-robot exploration tasks in continuous space. Computational geometry knowledge is applied to describe the environment in continuous space and to design an improved reward function to ensure a superior exploration rate. Moreover, the multi-head attention mechanism employed helps to solve the historical trajectory issue in the decentralized multi-robot exploration task, as well as to reduce the quadratic increase of action space.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01774v1
PDF	https://arxiv.org/pdf/1911.01774v1.pdf
PWC	https://paperswithcode.com/paper/efficient-multi-robot-exploration-via-multi
Repo
Framework

Generalizing Deep Models for Overhead Image Segmentation Through Getis-Ord Gi* Pooling


Title	Generalizing Deep Models for Overhead Image Segmentation Through Getis-Ord Gi* Pooling
Authors	Xueqing Deng, Yi Zhu, Yuxin Tian, Shawn Newsam
Abstract	That most deep learning models are purely data driven is both a strength and a weakness. Given sufficient training data, the optimal model for a particular problem can be learned. However, this is usually not the case and so instead the model is either learned from scratch from a limited amount of training data or pre-trained on a different problem and then fine-tuned. Both of these situations are potentially suboptimal and limit the generalizability of the model. Inspired by this, we investigate methods to inform or guide deep learning models for geospatial image analysis to increase their performance when a limited amount of training data is available or when they are applied to scenarios other than which they were trained on. In particular, we exploit the fact that there are certain fundamental rules as to how things are distributed on the surface of the Earth and these rules do not vary substantially between locations. Based on this, we develop a novel feature pooling method for convolutional neural networks using Getis-Ord Gi* analysis from geostatistics. Experimental results show our proposed pooling function has significantly better generalization performance compared to a standard data-driven approach when applied to overhead image segmentation.
Tasks	Semantic Segmentation
Published	2019-12-23
URL	https://arxiv.org/abs/1912.10667v1
PDF	https://arxiv.org/pdf/1912.10667v1.pdf
PWC	https://paperswithcode.com/paper/generalizing-deep-models-for-overhead-image
Repo
Framework

Direct Classification of Type 2 Diabetes From Retinal Fundus Images in a Population-based Sample From The Maastricht Study


Title	Direct Classification of Type 2 Diabetes From Retinal Fundus Images in a Population-based Sample From The Maastricht Study
Authors	Friso G. Heslinga, Josien P. W. Pluim, A. J. H. M. Houben, Miranda T. Schram, Ronald M. A. Henry, Coen D. A. Stehouwer, Marleen J. van Greevenbroek, Tos T. J. M. Berendschot, Mitko Veta
Abstract	Type 2 Diabetes (T2D) is a chronic metabolic disorder that can lead to blindness and cardiovascular disease. Information about early stage T2D might be present in retinal fundus images, but to what extent these images can be used for a screening setting is still unknown. In this study, deep neural networks were employed to differentiate between fundus images from individuals with and without T2D. We investigated three methods to achieve high classification performance, measured by the area under the receiver operating curve (ROC-AUC). A multi-target learning approach to simultaneously output retinal biomarkers as well as T2D works best (AUC = 0.746 [$\pm$0.001]). Furthermore, the classification performance can be improved when images with high prediction uncertainty are referred to a specialist. We also show that the combination of images of the left and right eye per individual can further improve the classification performance (AUC = 0.758 [$\pm$0.003]), using a simple averaging approach. The results are promising, suggesting the feasibility of screening for T2D from retinal fundus images.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10022v1
PDF	https://arxiv.org/pdf/1911.10022v1.pdf
PWC	https://paperswithcode.com/paper/direct-classification-of-type-2-diabetes-from
Repo
Framework

Context-Integrated and Feature-Refined Network for Lightweight Object Parsing


Title	Context-Integrated and Feature-Refined Network for Lightweight Object Parsing
Authors	Bin Jiang, Wenxuan Tu, Chao Yang, Junsong Yuan
Abstract	Semantic segmentation for lightweight object parsing is a very challenging task, because both accuracy and efficiency (e.g., execution speed, memory footprint or computational complexity) should all be taken into account. However, most previous works pay too much attention to one-sided perspective, either accuracy or speed, and ignore others, which poses a great limitation to actual demands of intelligent devices. To tackle this dilemma, we propose a novel lightweight architecture named Context-Integrated and Feature-Refined Network (CIFReNet). The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Context Integration Module (MCIM). The LRM is designed to ease the propagation of spatial information between low-level and high-level stages. Furthermore, channel attention mechanism is introduced into the process of long-skip learning to boost the quality of low-level feature refinement. Meanwhile, the MCIM consists of three cascaded Dense Semantic Pyramid (DSP) blocks with image-level features, which is presented to encode multiple context information and enlarge the field of view. Specifically, the proposed DSP block exploits a dense feature sampling strategy to enhance the information representations without significantly increasing the computation cost. Comprehensive experiments are conducted on three benchmark datasets for object parsing including Cityscapes, CamVid, and Helen. As indicated, the proposed method reaches a better trade-off between accuracy and efficiency compared with the other state-of-the-art methods.
Tasks	Scene Parsing, Semantic Segmentation
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11474v3
PDF	https://arxiv.org/pdf/1907.11474v3.pdf
PWC	https://paperswithcode.com/paper/context-integrated-and-feature-refined
Repo
Framework

Tensor Entropy for Uniform Hypergraphs


Title	Tensor Entropy for Uniform Hypergraphs
Authors	Can Chen, Indika Rajapakse
Abstract	In this paper, we develop the notion of entropy for uniform hypergraphs via tensor theory. We employ the probability distribution of the generalized singular values, calculated from the higher-order singular value decomposition of the Laplacian tensors, to fit into the Shannon entropy formula. We show that this tensor entropy is an extension of von Neumann entropy for graphs. In addition, we establish results on the lower and upper bounds of the entropy and demonstrate that it is a measure of regularity for uniform hypergraphs in simulated and experimental data. We exploit the tensor train decomposition in computing the proposed tensor entropy efficiently. Finally, we introduce the notion of robustness for uniform hypergraphs.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09624v3
PDF	https://arxiv.org/pdf/1912.09624v3.pdf
PWC	https://paperswithcode.com/paper/tensor-entropy-for-uniform-hypergraphs
Repo
Framework

Molecular Generative Model Based On Adversarially Regularized Autoencoder


Title	Molecular Generative Model Based On Adversarially Regularized Autoencoder
Authors	Seung Hwan Hong, Jaechang Lim, Seongok Ryu, Woo Youn Kim
Abstract	Deep generative models are attracting great attention as a new promising approach for molecular design. All models reported so far are based on either variational autoencoder (VAE) or generative adversarial network (GAN). Here we propose a new type model based on an adversarially regularized autoencoder (ARAE). It basically uses latent variables like VAE, but the distribution of the latent variables is obtained by adversarial training like in GAN. The latter is intended to avoid both inappropriate approximation of posterior distribution in VAE and difficulty in handling discrete variables in GAN. Our benchmark study showed that ARAE indeed outperformed conventional models in terms of validity, uniqueness, and novelty per generated molecule. We also demonstrated successful conditional generation of drug-like molecules with ARAE for both cases of single and multiple properties control. As a potential real-world application, we could generate EGFR inhibitors sharing the scaffolds of known active molecules while satisfying drug-like conditions simultaneously.
Tasks
Published	2019-11-13
URL	https://arxiv.org/abs/1912.05617v1
PDF	https://arxiv.org/pdf/1912.05617v1.pdf
PWC	https://paperswithcode.com/paper/molecular-generative-model-based-on-1
Repo
Framework

Scalable Differentially Private Generative Student Model via PATE


Title	Scalable Differentially Private Generative Student Model via PATE
Authors	Yunhui Long, Suxin Lin, Zhuolin Yang, Carl A. Gunter, Bo Li
Abstract	Recent rapid development of machine learning is largely due to algorithmic breakthroughs, computation resource development, and especially the access to a large amount of training data. However, though data sharing has the great potential of improving machine learning models and enabling new applications, there have been increasing concerns about the privacy implications of data collection. In this work, we present a novel approach for training differentially private data generator G-PATE. The generator can be used to produce synthetic datasets with strong privacy guarantee while preserving high data utility. Our approach leverages generative adversarial nets (GAN) to generate data and protect data privacy based on the Private Aggregation of Teacher Ensembles (PATE) framework. Our approach improves the use of privacy budget by only ensuring differential privacy for the generator, which is the part of the model that actually needs to be published for private data generation. To achieve this, we connect a student generator with an ensemble of teacher discriminators. We also propose a private gradient aggregation mechanism to ensure differential privacy on all the information that flows from the teacher discriminators to the student generator. We empirically show that the G-PATE significantly outperforms prior work on both image and non-image datasets.
Tasks
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09338v1
PDF	https://arxiv.org/pdf/1906.09338v1.pdf
PWC	https://paperswithcode.com/paper/scalable-differentially-private-generative
Repo
Framework

Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network


Title	Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network
Authors	Feng Mao, Xiang Wu, Hui Xue, Rong Zhang
Abstract	High accuracy video label prediction (classification) models are attributed to large scale data. These data could be frame feature sequences extracted by a pre-trained convolutional-neural-network, which promote the efficiency for creating models. Unsupervised solutions such as feature average pooling, as a simple label-independent parameter-free based method, has limited ability to represent the video. While the supervised methods, like RNN, can greatly improve the recognition accuracy. However, the video length is usually long, and there are hierarchical relationships between frames across events in the video, the performance of RNN based models are decreased. In this paper, we proposes a novel video classification method based on a deep convolutional graph neural network(DCGN). The proposed method utilize the characteristics of the hierarchical structure of the video, and performed multi-level feature extraction on the video frame sequence through the graph network, obtained a video representation re ecting the event semantics hierarchically. We test our model on YouTube-8M Large-Scale Video Understanding dataset, and the result outperforms RNN based benchmarks.
Tasks	Video Classification, Video Understanding
Published	2019-06-02
URL	https://arxiv.org/abs/1906.00377v1
PDF	https://arxiv.org/pdf/1906.00377v1.pdf
PWC	https://paperswithcode.com/paper/190600377
Repo
Framework