January 26, 2020

3032 words 15 mins read

Paper Group ANR 1594

Higher-order Weighted Graph Convolutional Networks. Progressive VAE Training on Highly Sparse and Imbalanced Data. IAN: Combining Generative Adversarial Networks for Imaginative Face Generation. Spatially regularized active diffusion learning for high-dimensional images. An Overview of Open-Ended Evolution: Editorial Introduction to the Open-Ended …

Higher-order Weighted Graph Convolutional Networks


Title	Higher-order Weighted Graph Convolutional Networks
Authors	Songtao Liu, Lingwei Chen, Hanze Dong, Zihao Wang, Dinghao Wu, Zengfeng Huang
Abstract	Graph Convolution Network (GCN) has been recognized as one of the most effective graph models for semi-supervised learning, but it extracts merely the first-order or few-order neighborhood information through information propagation, which suffers performance drop-off for deeper structure. Existing approaches that deal with the higher-order neighbors tend to take advantage of adjacency matrix power. In this paper, we assume a seemly trivial condition that the higher-order neighborhood information may be similar to that of the first-order neighbors. Accordingly, we present an unsupervised approach to describe such similarities and learn the weight matrices of higher-order neighbors automatically through Lasso that minimizes the feature loss between the first-order and higher-order neighbors, based on which we formulate the new convolutional filter for GCN to learn the better node representations. Our model, called higher-order weighted GCN(HWGCN), has achieved the state-of-the-art results on a number of node classification tasks over Cora, Citeseer and Pubmed datasets.
Tasks	Node Classification
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04129v2
PDF	https://arxiv.org/pdf/1911.04129v2.pdf
PWC	https://paperswithcode.com/paper/higher-order-weighted-graph-convolutional
Repo
Framework

Progressive VAE Training on Highly Sparse and Imbalanced Data


Title	Progressive VAE Training on Highly Sparse and Imbalanced Data
Authors	Dmitry Utyamishev, Inna Partin-Vaisband
Abstract	In this paper, we present a novel approach for training a Variational Autoencoder (VAE) on a highly imbalanced data set. The proposed training of a high-resolution VAE model begins with the training of a low-resolution core model, which can be successfully trained on imbalanced data set. In subsequent training steps, new convolutional, upsampling, deconvolutional, and downsampling layers are iteratively attached to the model. In each iteration, the additional layers are trained based on the intermediate pretrained model - a result of previous training iterations. Thus, the resolution of the model is progressively increased up to the required resolution level. In this paper, the progressive VAE training is exploited for learning a latent representation with imbalanced, highly sparse data sets and, consequently, generating routes in a constrained 2D space. Routing problems (e.g., vehicle routing problem, travelling salesman problem, and arc routing) are of special significance in many modern applications (e.g., route planning, network maintenance, developing high-performance nanoelectronic systems, and others) and typically associated with sparse imbalanced data. In this paper, the critical problem of routing billions of components in nanoelectronic devices is considered. The proposed approach exhibits a significant training speedup as compared with state-of-the-art existing VAE training methods, while generating expected image outputs from unseen input data. Furthermore, the final progressive VAE models exhibit much more precise output representation, than the Generative Adversarial Network (GAN) models trained with comparable training time. The proposed method is expected to be applicable to a wide range of applications, including but not limited image impainting, sentence interpolation, and semi-supervised learning.
Tasks
Published	2019-12-17
URL	https://arxiv.org/abs/1912.08283v1
PDF	https://arxiv.org/pdf/1912.08283v1.pdf
PWC	https://paperswithcode.com/paper/progressive-vae-training-on-highly-sparse-and
Repo
Framework

IAN: Combining Generative Adversarial Networks for Imaginative Face Generation


Title	IAN: Combining Generative Adversarial Networks for Imaginative Face Generation
Authors	Abdullah Hamdi, Bernard Ghanem
Abstract	Generative Adversarial Networks (GANs) have gained momentum for their ability to model image distributions. They learn to emulate the training set and that enables sampling from that domain and using the knowledge learned for useful applications. Several methods proposed enhancing GANs, including regularizing the loss with some feature matching. We seek to push GANs beyond the data in the training and try to explore unseen territory in the image manifold. We first propose a new regularizer for GAN based on K-nearest neighbor (K-NN) selective feature matching to a target set Y in high-level feature space, during the adversarial training of GAN on the base set X, and we call this novel model K-GAN. We show that minimizing the added term follows from cross-entropy minimization between the distributions of GAN and the set Y. Then, We introduce a cascaded framework for GANs that try to address the task of imagining a new distribution that combines the base set X and target set Y by cascading sampling GANs with translation GANs, and we dub the cascade of such GANs as the Imaginative Adversarial Network (IAN). We conduct an objective and subjective evaluation for different IAN setups in the addressed task and show some useful applications for these IANs, like manifold traversing and creative face generation for characters’ design in movies or video games.
Tasks	Face Generation
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07916v1
PDF	http://arxiv.org/pdf/1904.07916v1.pdf
PWC	https://paperswithcode.com/paper/ian-combining-generative-adversarial-networks
Repo
Framework

Spatially regularized active diffusion learning for high-dimensional images


Title	Spatially regularized active diffusion learning for high-dimensional images
Authors	James M. Murphy
Abstract	An active learning algorithm for the classification of high-dimensional images is proposed in which spatially-regularized nonlinear diffusion geometry is used to characterize cluster cores. The proposed method samples from estimated cluster cores in order to generate a small but potent set of training labels which propagate to the remainder of the dataset via the underlying diffusion process. By spatially regularizing the rich, high-dimensional spectral information of the image to efficiently estimate the most significant and influential points in the data, our approach avoids redundancy in the training dataset. This allows it to produce high-accuracy labelings with a very small number of training labels. The proposed algorithm admits an efficient numerical implementation that scales essentially linearly in the number of data points under a suitable data model and enjoys state-of-the-art performance on real hyperspectral images.
Tasks	Active Learning
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02155v1
PDF	https://arxiv.org/pdf/1911.02155v1.pdf
PWC	https://paperswithcode.com/paper/spatially-regularized-active-diffusion
Repo
Framework

An Overview of Open-Ended Evolution: Editorial Introduction to the Open-Ended Evolution II Special Issue


Title	An Overview of Open-Ended Evolution: Editorial Introduction to the Open-Ended Evolution II Special Issue
Authors	Norman Packard, Mark A. Bedau, Alastair Channon, Takashi Ikegami, Steen Rasmussen, Kenneth O. Stanley, Tim Taylor
Abstract	Nature’s spectacular inventiveness, reflected in the enormous diversity of form and function displayed by the biosphere, is a feature of life that distinguishes living most strongly from nonliving. It is, therefore, not surprising that this aspect of life should become a central focus of artificial life. We have known since Darwin that the diversity is produced dynamically, through the process of evolution; this has led life’s creative productivity to be called Open-Ended Evolution (OEE) in the field. This article introduces the second of two special issues on current research in OEE and provides an overview of the contents of both special issues. Most of the work was presented at a workshop on open-ended evolution that was held as a part of the 2018 Conference on Artificial Life in Tokyo, and much of it had antecedents in two previous workshops on open-ended evolution at artificial life conferences in Cancun and York. We present a simplified categorization of OEE and summarize progress in the field as represented by the articles in this special issue.
Tasks	Artificial Life
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04430v1
PDF	https://arxiv.org/pdf/1909.04430v1.pdf
PWC	https://paperswithcode.com/paper/an-overview-of-open-ended-evolution-editorial
Repo
Framework

Do we still need fuzzy classifiers for Small Data in the Era of Big Data?


Title	Do we still need fuzzy classifiers for Small Data in the Era of Big Data?
Authors	Mikel Elkano, Humberto Bustince, Mikel Galar
Abstract	The Era of Big Data has forced researchers to explore new distributed solutions for building fuzzy classifiers, which often introduce approximation errors or make strong assumptions to reduce computational and memory requirements. As a result, Big Data classifiers might be expected to be inferior to those designed for standard classification tasks (Small Data) in terms of accuracy and model complexity. To our knowledge, however, there is no empirical evidence to confirm such a conjecture yet. Here, we investigate the extent to which state-of-the-art fuzzy classifiers for Big Data sacrifice performance in favor of scalability. To this end, we carry out an empirical study that compares these classifiers with some of the best performing algorithms for Small Data. Assuming the latter were generally designed for maximizing performance without considering scalability issues, the results of this study provide some intuition around the tradeoff between performance and scalability achieved by current Big Data solutions. Our findings show that, although slightly inferior, Big Data classifiers are gradually catching up with state-of-the-art classifiers for Small data, suggesting that a unified learning algorithm for Big and Small Data might be possible.
Tasks
Published	2019-03-08
URL	http://arxiv.org/abs/1903.03324v1
PDF	http://arxiv.org/pdf/1903.03324v1.pdf
PWC	https://paperswithcode.com/paper/do-we-still-need-fuzzy-classifiers-for-small
Repo
Framework

Disentangling and Learning Robust Representations with Natural Clustering


Title	Disentangling and Learning Robust Representations with Natural Clustering
Authors	Javier Antoran, Antonio Miguel
Abstract	Learning representations that disentangle the underlying factors of variability in data is an intuitive way to achieve generalization in deep models. In this work, we address the scenario where generative factors present a multimodal distribution due to the existence of class distinction in the data. We propose N-VAE, a model which is capable of separating factors of variation which are exclusive to certain classes from factors that are shared among classes. This model implements an explicitly compositional latent variable structure by defining a class-conditioned latent space and a shared latent space. We show its usefulness for detecting and disentangling class-dependent generative factors as well as its capacity to generate artificial samples which contain characteristics unseen in the training data.
Tasks
Published	2019-01-27
URL	https://arxiv.org/abs/1901.09415v3
PDF	https://arxiv.org/pdf/1901.09415v3.pdf
PWC	https://paperswithcode.com/paper/disentangling-in-variational-autoencoders
Repo
Framework

Unsupervised Keyword Extraction for Full-sentence VQA


Title	Unsupervised Keyword Extraction for Full-sentence VQA
Authors	Kohei Uehara, Tatsuya Harada
Abstract	In most of the existing Visual Question Answering (VQA) methods, the answers consist of short, almost single words, due to the instructions to the annotators when constructing the dataset. In this study, we envision a new VQA task in natural situations, where the answers would more likely to be sentences, rather than single words. To bridge the gap between the natural VQA and the existing VQA studies, we proposed a novel unsupervised keyword extraction method for VQA. Our key insight is that the full-sentence answer can be decomposed into two parts: one that contains new information for the question (i.e. keyword) and one that contains information already included in the question. We designed discriminative decoders to ensure such decomposition. We conducted experiments on VQA datasets that contain full-sentence answers, and show that our proposed model can correctly extract the keyword without explicit annotations of what the keyword is.
Tasks	Keyword Extraction, Question Answering, Visual Question Answering
Published	2019-11-23
URL	https://arxiv.org/abs/1911.10354v2
PDF	https://arxiv.org/pdf/1911.10354v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-keyword-extraction-for-full
Repo
Framework

Smaller Text Classifiers with Discriminative Cluster Embeddings


Title	Smaller Text Classifiers with Discriminative Cluster Embeddings
Authors	Mingda Chen, Kevin Gimpel
Abstract	Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a hard word clustering in an end-to-end manner. We use the Gumbel-Softmax distribution to maximize over the latent clustering while minimizing the task loss. We propose variations that selectively assign additional parameters to words, which further improves accuracy while still remaining parameter-efficient.
Tasks
Published	2019-06-23
URL	https://arxiv.org/abs/1906.09532v1
PDF	https://arxiv.org/pdf/1906.09532v1.pdf
PWC	https://paperswithcode.com/paper/smaller-text-classifiers-with-discriminative-1
Repo
Framework

Logical Classification of Partially Ordered Data


Title	Logical Classification of Partially Ordered Data
Authors	Elena V. Djukova, Gleb O. Masliakov, Petr A. Prokofyev
Abstract	Issues concerning intelligent data analysis occurring in machine learning are investigated. A scheme for synthesizing correct supervised classification procedures is proposed. These procedures are focused on specifying partial order relations on sets of feature values; they are based on a generalization of the classical concepts of logical classification. It is shown that learning the correct logical classifier requires an intractable discrete problem to be solved. This is the dualization problem over products of partially ordered sets. The matrix formulation of this problem is given. The effectiveness of the proposed approach to the supervised classification problem is illustrated on model and real-life data.
Tasks
Published	2019-07-21
URL	https://arxiv.org/abs/1907.08962v1
PDF	https://arxiv.org/pdf/1907.08962v1.pdf
PWC	https://paperswithcode.com/paper/logical-classification-of-partially-ordered
Repo
Framework

Survey of Bayesian Networks Applications to Intelligent Autonomous Vehicles


Title	Survey of Bayesian Networks Applications to Intelligent Autonomous Vehicles
Authors	Rocío Díaz de León Torres, Martín Molina, Pascual Campoy
Abstract	This article reviews the applications of Bayesian Networks to Intelligent Autonomous Vehicles (IAV) from the decision making point of view, which represents the final step for fully Autonomous Vehicles (currently under discussion). Until now, when it comes making high level decisions for Autonomous Vehicles (AVs), humans have the last word. Based on the works cited in this article and analysis done here, the modules of a general decision making framework and its variables are inferred. Many efforts have been made in the labs showing Bayesian Networks as a promising computer model for decision making. Further research should go into the direction of testing Bayesian Network models in real situations. In addition to the applications, Bayesian Network fundamentals are introduced as elements to consider when developing IAVs with the potential of making high level judgement calls.
Tasks	Autonomous Vehicles, Decision Making
Published	2019-01-16
URL	http://arxiv.org/abs/1901.05517v2
PDF	http://arxiv.org/pdf/1901.05517v2.pdf
PWC	https://paperswithcode.com/paper/survey-of-bayesian-networks-applications-to
Repo
Framework

“My Way of Telling a Story”: Persona based Grounded Story Generation


Title	“My Way of Telling a Story”: Persona based Grounded Story Generation
Authors	Shrimai Prabhumoye, Khyathi Raghavi Chandu, Ruslan Salakhutdinov, Alan W Black
Abstract	Visual storytelling is the task of generating stories based on a sequence of images. Inspired by the recent works in neural generation focusing on controlling the form of text, this paper explores the idea of generating these stories in different personas. However, one of the main challenges of performing this task is the lack of a dataset of visual stories in different personas. Having said that, there are independent datasets for both visual storytelling and annotated sentences for various persona. In this paper we describe an approach to overcome this by getting labelled persona data from a different task and leveraging those annotations to perform persona based story generation. We inspect various ways of incorporating personality in both the encoder and the decoder representations to steer the generation in the target direction. To this end, we propose five models which are incremental extensions to the baseline model to perform the task at hand. In our experiments we use five different personas to guide the generation process. We find that the models based on our hypotheses perform better at capturing words while generating stories in the target persona.
Tasks	Visual Storytelling
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06401v1
PDF	https://arxiv.org/pdf/1906.06401v1.pdf
PWC	https://paperswithcode.com/paper/my-way-of-telling-a-story-persona-based
Repo
Framework

Modelling EHR timeseries by restricting feature interaction


Title	Modelling EHR timeseries by restricting feature interaction
Authors	Kun Zhang, Yuan Xue, Gerardo Flores, Alvin Rajkomar, Claire Cui, Andrew M. Dai
Abstract	Time series data are prevalent in electronic health records, mostly in the form of physiological parameters such as vital signs and lab tests. The patterns of these values may be significant indicators of patients’ clinical states and there might be patterns that are unknown to clinicians but are highly predictive of some outcomes. Many of these values are also missing which makes it difficult to apply existing methods like decision trees. We propose a recurrent neural network model that reduces overfitting to noisy observations by limiting interactions between features. We analyze its performance on mortality, ICD-9 and AKI prediction from observational values on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset. Our models result in an improvement of 1.1% [p<0.01] in AU-ROC for mortality prediction under the MetaVision subset and 1.0% and 2.2% [p<0.01] respectively for mortality and AKI under the full MIMIC-III dataset compared to existing state-of-the-art interpolation, embedding and decay-based recurrent models.
Tasks	Mortality Prediction, Time Series
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06410v1
PDF	https://arxiv.org/pdf/1911.06410v1.pdf
PWC	https://paperswithcode.com/paper/modelling-ehr-timeseries-by-restricting
Repo
Framework

Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations


Title	Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations
Authors	Sangwoo Cho, Chen Li, Dong Yu, Hassan Foroosh, Fei Liu
Abstract	Emerged as one of the best performing techniques for extractive summarization, determinantal point processes select the most probable set of sentences to form a summary according to a probability measure defined by modeling sentence prominence and pairwise repulsion. Traditionally, these aspects are modelled using shallow and linguistically informed features, but the rise of deep contextualized representations raises an interesting question of whether, and to what extent, contextualized representations can be used to improve DPP modeling. Our findings suggest that, despite the success of deep representations, it remains necessary to combine them with surface indicators for effective identification of summary sentences.
Tasks	Document Summarization, Multi-Document Summarization, Point Processes
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11411v1
PDF	https://arxiv.org/pdf/1910.11411v1.pdf
PWC	https://paperswithcode.com/paper/multi-document-summarization-with
Repo
Framework

Automated crater shape retrieval using weakly-supervised deep learning


Title	Automated crater shape retrieval using weakly-supervised deep learning
Authors	Mohamad Ali-Dib, Kristen Menou, Alan P. Jackson, Chenchong Zhu, Noah Hammond
Abstract	Crater ellipticity determination is a complex and time consuming task that so far has evaded successful automation. We train a state of the art computer vision algorithm to identify craters in Lunar digital elevation maps and retrieve their sizes and 2D shapes. The computational backbone of the model is MaskRCNN, an “instance segmentation” general framework that detects craters in an image while simultaneously producing a mask for each crater that traces its outer rim. Our post-processing pipeline then finds the closest fitting ellipse to these masks, allowing us to retrieve the crater ellipticities. Our model is able to correctly identify 87% of known craters in the longitude range we hid from the network during training and validation (test set), while predicting thousands of additional craters not present in our training data. Manual validation of a subset of these “new” craters indicates that a majority of them are real, which we take as an indicator of the strength of our model in learning to identify craters, despite incomplete training data. The crater size, ellipticity, and depth distributions predicted by our model are consistent with human-generated results. The model allows us to perform a large scale search for differences in crater diameter and shape distributions between the lunar highlands and maria, and we exclude any such differences with a high statistical significance. The predicted test set catalogue and trained model are available here: https://github.com/malidib/Craters_MaskRCNN/.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08826v3
PDF	https://arxiv.org/pdf/1906.08826v3.pdf
PWC	https://paperswithcode.com/paper/automated-crater-shape-retrieval-using-weakly
Repo
Framework