July 27, 2019

3058 words 15 mins read

Paper Group ANR 701

Hybrid Clustering based on Content and Connection Structure using Joint Nonnegative Matrix Factorization. Learning hard quantum distributions with variational autoencoders. A Line-Point Unified Solution to Relative Camera Pose Estimation. The Pragmatics of Indirect Commands in Collaborative Discourse. Markov Decision Processes with Continuous Side …

Hybrid Clustering based on Content and Connection Structure using Joint Nonnegative Matrix Factorization


Title	Hybrid Clustering based on Content and Connection Structure using Joint Nonnegative Matrix Factorization
Authors	Rundong Du, Barry Drake, Haesun Park
Abstract	We present a hybrid method for latent information discovery on the data sets containing both text content and connection structure based on constrained low rank approximation. The new method jointly optimizes the Nonnegative Matrix Factorization (NMF) objective function for text clustering and the Symmetric NMF (SymNMF) objective function for graph clustering. We propose an effective algorithm for the joint NMF objective function, based on a block coordinate descent (BCD) framework. The proposed hybrid method discovers content associations via latent connections found using SymNMF. The method can also be applied with a natural conversion of the problem when a hypergraph formulation is used or the content is associated with hypergraph edges. Experimental results show that by simultaneously utilizing both content and connection structure, our hybrid method produces higher quality clustering results compared to the other NMF clustering methods that uses content alone (standard NMF) or connection structure alone (SymNMF). We also present some interesting applications to several types of real world data such as citation recommendations of papers. The hybrid method proposed in this paper can also be applied to general data expressed with both feature space vectors and pairwise similarities and can be extended to the case with multiple feature spaces or multiple similarity measures.
Tasks	Graph Clustering, Text Clustering
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09646v1
PDF	http://arxiv.org/pdf/1703.09646v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-clustering-based-on-content-and
Repo
Framework

Learning hard quantum distributions with variational autoencoders


Title	Learning hard quantum distributions with variational autoencoders
Authors	Andrea Rocchetto, Edward Grant, Sergii Strelchuk, Giuseppe Carleo, Simone Severini
Abstract	Studying general quantum many-body systems is one of the major challenges in modern physics because it requires an amount of computational resources that scales exponentially with the size of the system.Simulating the evolution of a state, or even storing its description, rapidly becomes intractable for exact classical algorithms. Recently, machine learning techniques, in the form of restricted Boltzmann machines, have been proposed as a way to efficiently represent certain quantum states with applications in state tomography and ground state estimation. Here, we introduce a new representation of states based on variational autoencoders. Variational autoencoders are a type of generative model in the form of a neural network. We probe the power of this representation by encoding probability distributions associated with states from different classes. Our simulations show that deep networks give a better representation for states that are hard to sample from, while providing no benefit for random states. This suggests that the probability distributions associated to hard quantum states might have a compositional structure that can be exploited by layered neural networks. Specifically, we consider the learnability of a class of quantum states introduced by Fefferman and Umans. Such states are provably hard to sample for classical computers, but not for quantum ones, under plausible computational complexity assumptions. The good level of compression achieved for hard states suggests these methods can be suitable for characterising states of the size expected in first generation quantum hardware.
Tasks
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00725v2
PDF	http://arxiv.org/pdf/1710.00725v2.pdf
PWC	https://paperswithcode.com/paper/learning-hard-quantum-distributions-with
Repo
Framework

A Line-Point Unified Solution to Relative Camera Pose Estimation


Title	A Line-Point Unified Solution to Relative Camera Pose Estimation
Authors	Ashraf Qadir, Jeremiah Neubert
Abstract	In this work we present a unified method of relative camera pose estimation from points and lines correspondences. Given a set of 2D points and lines correspondences in three views, of which two are known, a method has been developed for estimating the camera pose of the third view. Novelty of this algorithm is to combine both points and lines correspondences in the camera pose estimation which enables us to compute relative camera pose with a small number of feature correspondences. Our central idea is to exploit the tri-linear relationship between three views and generate a set of linear equations from the points and lines correspondences in the three views. The desired solution to the system of equations are expressed as a linear combination of the singular vectors and the coefficients are computed by solving a small set of quadratic equations generated by imposing orthonormality constraints for general camera motion. The advantages of the proposed method are demonstrated by experimenting on publicly available data set. Results show the robustness and efficiency of the method in relative camera pose estimation for both small and large camera motion with a small set of points and line features.
Tasks	Pose Estimation
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06495v1
PDF	http://arxiv.org/pdf/1710.06495v1.pdf
PWC	https://paperswithcode.com/paper/a-line-point-unified-solution-to-relative
Repo
Framework

The Pragmatics of Indirect Commands in Collaborative Discourse


Title	The Pragmatics of Indirect Commands in Collaborative Discourse
Authors	Matthew Lamm, Mihail Eric
Abstract	Today’s artificial assistants are typically prompted to perform tasks through direct, imperative commands such as \emph{Set a timer} or \emph{Pick up the box}. However, to progress toward more natural exchanges between humans and these assistants, it is important to understand the way non-imperative utterances can indirectly elicit action of an addressee. In this paper, we investigate command types in the setting of a grounded, collaborative game. We focus on a less understood family of utterances for eliciting agent action, locatives like \emph{The chair is in the other room}, and demonstrate how these utterances indirectly command in specific game state contexts. Our work shows that models with domain-specific grounding can effectively realize the pragmatic reasoning that is necessary for more robust natural language interaction.
Tasks
Published	2017-05-08
URL	http://arxiv.org/abs/1705.03454v2
PDF	http://arxiv.org/pdf/1705.03454v2.pdf
PWC	https://paperswithcode.com/paper/the-pragmatics-of-indirect-commands-in
Repo
Framework

Markov Decision Processes with Continuous Side Information


Title	Markov Decision Processes with Continuous Side Information
Authors	Aditya Modi, Nan Jiang, Satinder Singh, Ambuj Tewari
Abstract	We consider a reinforcement learning (RL) setting in which the agent interacts with a sequence of episodic MDPs. At the start of each episode the agent has access to some side-information or context that determines the dynamics of the MDP for that episode. Our setting is motivated by applications in healthcare where baseline measurements of a patient at the start of a treatment episode form the context that may provide information about how the patient might respond to treatment decisions. We propose algorithms for learning in such Contextual Markov Decision Processes (CMDPs) under an assumption that the unobserved MDP parameters vary smoothly with the observed context. We also give lower and upper PAC bounds under the smoothness assumption. Because our lower bound has an exponential dependence on the dimension, we consider a tractable linear setting where the context is used to create linear combinations of a finite set of MDPs. For the linear setting, we give a PAC learning algorithm based on KWIK learning techniques.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05726v1
PDF	http://arxiv.org/pdf/1711.05726v1.pdf
PWC	https://paperswithcode.com/paper/markov-decision-processes-with-continuous
Repo
Framework

Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting


Title	Max-Pooling Loss Training of Long Short-Term Memory Networks for Small-Footprint Keyword Spotting
Authors	Ming Sun, Anirudh Raju, George Tucker, Sankaran Panchapagesan, Gengshen Fu, Arindam Mandal, Spyros Matsoukas, Nikko Strom, Shiv Vitaladevuni
Abstract	We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothing based evaluation approach is employed to measure keyword spotting performance. Our experimental results show that LSTM models trained using cross-entropy loss or max-pooling loss outperform a cross-entropy loss trained baseline feed-forward Deep Neural Network (DNN). In addition, max-pooling loss trained LSTM with randomly initialized network performs better compared to cross-entropy loss trained LSTM. Finally, the max-pooling loss trained LSTM initialized with a cross-entropy pre-trained network shows the best performance, which yields $67.6%$ relative reduction compared to baseline feed-forward DNN in Area Under the Curve (AUC) measure.
Tasks	Keyword Spotting, Small-Footprint Keyword Spotting
Published	2017-05-05
URL	http://arxiv.org/abs/1705.02411v1
PDF	http://arxiv.org/pdf/1705.02411v1.pdf
PWC	https://paperswithcode.com/paper/max-pooling-loss-training-of-long-short-term
Repo
Framework

Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation


Title	Conditional Random Field and Deep Feature Learning for Hyperspectral Image Segmentation
Authors	Fahim Irfan Alam, Jun Zhou, Alan Wee-Chung Liew, Xiuping Jia, Jocelyn Chanussot, Yongsheng Gao
Abstract	Image segmentation is considered to be one of the critical tasks in hyperspectral remote sensing image processing. Recently, convolutional neural network (CNN) has established itself as a powerful model in segmentation and classification by demonstrating excellent performances. The use of a graphical model such as a conditional random field (CRF) contributes further in capturing contextual information and thus improving the segmentation performance. In this paper, we propose a method to segment hyperspectral images by considering both spectral and spatial information via a combined framework consisting of CNN and CRF. We use multiple spectral cubes to learn deep features using CNN, and then formulate deep CRF with CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between patches consisting of three-dimensional data cubes. Effective piecewise training is applied in order to avoid the computationally expensive iterative CRF inference. Furthermore, we introduce a deep deconvolution network that improves the segmentation masks. We also introduce a new dataset and experimented our proposed method on it along with several widely adopted benchmark datasets to evaluate the effectiveness of our method. By comparing our results with those from several state-of-the-art models, we show the promising potential of our method.
Tasks	Hyperspectral Image Segmentation, Semantic Segmentation
Published	2017-11-13
URL	http://arxiv.org/abs/1711.04483v2
PDF	http://arxiv.org/pdf/1711.04483v2.pdf
PWC	https://paperswithcode.com/paper/conditional-random-field-and-deep-feature
Repo
Framework

Memory Enriched Big Bang Big Crunch Optimization Algorithm for Data Clustering


Title	Memory Enriched Big Bang Big Crunch Optimization Algorithm for Data Clustering
Authors	Kayvan Bijari, Hadi Zare, Hadi Veisi, Hossein Bobarshad
Abstract	Cluster analysis plays an important role in decision making process for many knowledge-based systems. There exist a wide variety of different approaches for clustering applications including the heuristic techniques, probabilistic models, and traditional hierarchical algorithms. In this paper, a novel heuristic approach based on big bang-big crunch algorithm is proposed for clustering problems. The proposed method not only takes advantage of heuristic nature to alleviate typical clustering algorithms such as k-means, but it also benefits from the memory based scheme as compared to its similar heuristic techniques. Furthermore, the performance of the proposed algorithm is investigated based on several benchmark test functions as well as on the well-known datasets. The experimental results show the significant superiority of the proposed method over the similar algorithms.
Tasks	Decision Making
Published	2017-03-08
URL	http://arxiv.org/abs/1703.02883v1
PDF	http://arxiv.org/pdf/1703.02883v1.pdf
PWC	https://paperswithcode.com/paper/memory-enriched-big-bang-big-crunch
Repo
Framework

Neural Paraphrase Identification of Questions with Noisy Pretraining


Title	Neural Paraphrase Identification of Questions with Noisy Pretraining
Authors	Gaurav Singh Tomar, Thyago Duque, Oscar Täckström, Jakob Uszkoreit, Dipanjan Das
Abstract	We present a solution to the problem of paraphrase identification of questions. We focus on a recent dataset of question pairs annotated with binary paraphrase labels and show that a variant of the decomposable attention model (Parikh et al., 2016) results in accurate performance on this task, while being far simpler than many competing neural architectures. Furthermore, when the model is pretrained on a noisy dataset of automatically collected question paraphrases, it obtains the best reported performance on the dataset.
Tasks	Paraphrase Identification
Published	2017-04-15
URL	http://arxiv.org/abs/1704.04565v2
PDF	http://arxiv.org/pdf/1704.04565v2.pdf
PWC	https://paperswithcode.com/paper/neural-paraphrase-identification-of-questions
Repo
Framework

A quantum dynamic belief model to explain the interference effects of categorization on decision making


Title	A quantum dynamic belief model to explain the interference effects of categorization on decision making
Authors	Zichang He, Wen Jiang
Abstract	Categorization is necessary for many decision making tasks. However, the categorization process may interfere the decision making result and the law of total probability can be violated in some situations. To predict the interference effect of categorization, some model based on quantum probability has been proposed. In this paper, a new quantum dynamic belief (QDB) model is proposed. Considering the precise decision may not be made during the process, the concept of uncertainty is introduced in our model to simulate real human thinking process. Then the interference effect categorization can be predicted by handling the uncertain information. The proposed model is applied to a categorization decision-making experiment to explain the interference effect of categorization. Compared with other models, our model is relatively more succinct and the result shows the correctness and effectiveness of our model.
Tasks	Decision Making
Published	2017-03-06
URL	http://arxiv.org/abs/1703.02894v1
PDF	http://arxiv.org/pdf/1703.02894v1.pdf
PWC	https://paperswithcode.com/paper/a-quantum-dynamic-belief-model-to-explain-the
Repo
Framework

A simple data discretizer


Title	A simple data discretizer
Authors	Gourab Mitra, Shashidhar Sundareisan, Bikash Kanti Sarkar
Abstract	Data discretization is an important step in the process of machine learning, since it is easier for classifiers to deal with discrete attributes rather than continuous attributes. Over the years, several methods of performing discretization such as Boolean Reasoning, Equal Frequency Binning, Entropy have been proposed, explored, and implemented. In this article, a simple supervised discretization approach is introduced. The prime goal of MIL is to maximize classification accuracy of classifier, minimizing loss of information while discretization of continuous attributes. The performance of the suggested approach is compared with the supervised discretization algorithm Minimum Information Loss (MIL), using the state-of-the-art rule inductive algorithms- J48 (Java implementation of C4.5 classifier). The presented approach is, indeed, the modified version of MIL. The empirical results show that the modified approach performs better in several cases in comparison to the original MIL algorithm and Minimum Description Length Principle (MDLP) .
Tasks
Published	2017-10-13
URL	http://arxiv.org/abs/1710.05091v1
PDF	http://arxiv.org/pdf/1710.05091v1.pdf
PWC	https://paperswithcode.com/paper/a-simple-data-discretizer
Repo
Framework

Comparison of Different Methods for Tissue Segmentation in Histopathological Whole-Slide Images


Title	Comparison of Different Methods for Tissue Segmentation in Histopathological Whole-Slide Images
Authors	Péter Bándi, Rob van de Loo, Milad Intezar, Daan Geijs, Francesco Ciompi, Bram van Ginneken, Jeroen van der Laak, Geert Litjens
Abstract	Tissue segmentation is an important pre-requisite for efficient and accurate diagnostics in digital pathology. However, it is well known that whole-slide scanners can fail in detecting all tissue regions, for example due to the tissue type, or due to weak staining because their tissue detection algorithms are not robust enough. In this paper, we introduce two different convolutional neural network architectures for whole slide image segmentation to accurately identify the tissue sections. We also compare the algorithms to a published traditional method. We collected 54 whole slide images with differing stains and tissue types from three laboratories to validate our algorithms. We show that while the two methods do not differ significantly they outperform their traditional counterpart (Jaccard index of 0.937 and 0.929 vs. 0.870, p < 0.01).
Tasks	Semantic Segmentation
Published	2017-03-17
URL	http://arxiv.org/abs/1703.05990v2
PDF	http://arxiv.org/pdf/1703.05990v2.pdf
PWC	https://paperswithcode.com/paper/comparison-of-different-methods-for-tissue
Repo
Framework

A multi-agent reinforcement learning model of common-pool resource appropriation


Title	A multi-agent reinforcement learning model of common-pool resource appropriation
Authors	Julien Perolat, Joel Z. Leibo, Vinicius Zambaldi, Charles Beattie, Karl Tuyls, Thore Graepel
Abstract	Humanity faces numerous problems of common-pool resource appropriation. This class of multi-agent social dilemma includes the problems of ensuring sustainable use of fresh water, common fisheries, grazing pastures, and irrigation systems. Abstract models of common-pool resource appropriation based on non-cooperative game theory predict that self-interested agents will generally fail to find socially positive equilibria—a phenomenon called the tragedy of the commons. However, in reality, human societies are sometimes able to discover and implement stable cooperative solutions. Decades of behavioral game theory research have sought to uncover aspects of human behavior that make this possible. Most of that work was based on laboratory experiments where participants only make a single choice: how much to appropriate. Recognizing the importance of spatial and temporal resource dynamics, a recent trend has been toward experiments in more complex real-time video game-like environments. However, standard methods of non-cooperative game theory can no longer be used to generate predictions for this case. Here we show that deep reinforcement learning can be used instead. To that end, we study the emergent behavior of groups of independently learning agents in a partially observed Markov game modeling common-pool resource appropriation. Our experiments highlight the importance of trial-and-error learning in common-pool resource appropriation and shed light on the relationship between exclusion, sustainability, and inequality.
Tasks	Multi-agent Reinforcement Learning
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06600v2
PDF	http://arxiv.org/pdf/1707.06600v2.pdf
PWC	https://paperswithcode.com/paper/a-multi-agent-reinforcement-learning-model-of
Repo
Framework

Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments


Title	Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments
Authors	Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens
Abstract	Implicit semantic role labeling (iSRL) is the task of predicting the semantic roles of a predicate that do not appear as explicit arguments, but rather regard common sense knowledge or are mentioned earlier in the discourse. We introduce an approach to iSRL based on a predictive recurrent neural semantic frame model (PRNSFM) that uses a large unannotated corpus to learn the probability of a sequence of semantic arguments given a predicate. We leverage the sequence probabilities predicted by the PRNSFM to estimate selectional preferences for predicates and their arguments. On the NomBank iSRL test set, our approach improves state-of-the-art performance on implicit semantic role labeling with less reliance than prior work on manually constructed language resources.
Tasks	Common Sense Reasoning, Semantic Role Labeling
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02709v2
PDF	http://arxiv.org/pdf/1704.02709v2.pdf
PWC	https://paperswithcode.com/paper/improving-implicit-semantic-role-labeling-by
Repo
Framework

GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks


Title	GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks
Authors	Alessandro Bay, Biswa Sengupta
Abstract	The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution. Recurrent neural networks such as the Sequence-to-Sequence (Seq2Seq) networks that have lately been used to yield state-of-the-art performance on speech translation or image captioning have so far ignored the geometry of the latent embedding, that they iteratively learn. We propose the information geometric Seq2Seq (GeoSeq2Seq) network which abridges the gap between deep recurrent neural networks and information geometry. Specifically, the latent embedding offered by a recurrent network is encoded as a Fisher kernel of a parametric Gaussian Mixture Model, a formalism common in computer vision. We utilise such a network to predict the shortest routes between two nodes of a graph by learning the adjacency matrix using the GeoSeq2Seq formalism; our results show that for such a problem the probabilistic representation of the latent embedding supersedes the non-probabilistic embedding by 10-15%.
Tasks	Image Captioning
Published	2017-10-25
URL	http://arxiv.org/abs/1710.09363v2
PDF	http://arxiv.org/pdf/1710.09363v2.pdf
PWC	https://paperswithcode.com/paper/geoseq2seq-information-geometric-sequence-to
Repo
Framework