July 27, 2019

2945 words 14 mins read

Paper Group ANR 535

Learning Invariant Riemannian Geometric Representations Using Deep Nets. Distributed Constraint Problems for Utilitarian Agents with Privacy Concerns, Recast as POMDPs. Towards CT-quality Ultrasound Imaging using Deep Learning. A relevance-scalability-interpretability tradeoff with temporally evolving user personas. Deep Learning Microscopy. Multi- …

Learning Invariant Riemannian Geometric Representations Using Deep Nets


Title	Learning Invariant Riemannian Geometric Representations Using Deep Nets
Authors	Suhas Lohit, Pavan Turaga
Abstract	Non-Euclidean constraints are inherent in many kinds of data in computer vision and machine learning, typically as a result of specific invariance requirements that need to be respected during high-level inference. Often, these geometric constraints can be expressed in the language of Riemannian geometry, where conventional vector space machine learning does not apply directly. The central question this paper deals with is: How does one train deep neural nets whose final outputs are elements on a Riemannian manifold? To answer this, we propose a general framework for manifold-aware training of deep neural networks – we utilize tangent spaces and exponential maps in order to convert the proposed problem into a form that allows us to bring current advances in deep learning to bear upon this problem. We describe two specific applications to demonstrate this approach: prediction of probability distributions for multi-class image classification, and prediction of illumination-invariant subspaces from a single face-image via regression on the Grassmannian. These applications show the generality of the proposed framework, and result in improved performance over baselines that ignore the geometry of the output space. In addition to solving this specific problem, we believe this paper opens new lines of enquiry centered on the implications of Riemannian geometry on deep architectures.
Tasks	Image Classification
Published	2017-08-30
URL	http://arxiv.org/abs/1708.09485v2
PDF	http://arxiv.org/pdf/1708.09485v2.pdf
PWC	https://paperswithcode.com/paper/learning-invariant-riemannian-geometric
Repo
Framework

Distributed Constraint Problems for Utilitarian Agents with Privacy Concerns, Recast as POMDPs


Title	Distributed Constraint Problems for Utilitarian Agents with Privacy Concerns, Recast as POMDPs
Authors	Julien Savaux, Julien Vion, Sylvain Piechowiak, René Mandiau, Toshihiro Matsui, Katsutoshi Hirayama, Makoto Yokoo, Shakre Elmane, Marius Silaghi
Abstract	Privacy has traditionally been a major motivation for distributed problem solving. Distributed Constraint Satisfaction Problem (DisCSP) as well as Distributed Constraint Optimization Problem (DCOP) are fundamental models used to solve various families of distributed problems. Even though several approaches have been proposed to quantify and preserve privacy in such problems, none of them is exempt from limitations. Here we approach the problem by assuming that computation is performed among utilitarian agents. We introduce a utilitarian approach where the utility of each state is estimated as the difference between the reward for reaching an agreement on assignments of shared variables and the cost of privacy loss. We investigate extensions to solvers where agents integrate the utility function to guide their search and decide which action to perform, defining thereby their policy. We show that these extended solvers succeed in significantly reducing privacy loss without significant degradation of the solution quality.
Tasks
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06939v1
PDF	http://arxiv.org/pdf/1703.06939v1.pdf
PWC	https://paperswithcode.com/paper/distributed-constraint-problems-for
Repo
Framework

Towards CT-quality Ultrasound Imaging using Deep Learning


Title	Towards CT-quality Ultrasound Imaging using Deep Learning
Authors	Sanketh Vedula, Ortal Senouf, Alex M. Bronstein, Oleg V. Michailovich, Michael Zibulevsky
Abstract	The cost-effectiveness and practical harmlessness of ultrasound imaging have made it one of the most widespread tools for medical diagnosis. Unfortunately, the beam-forming based image formation produces granular speckle noise, blurring, shading and other artifacts. To overcome these effects, the ultimate goal would be to reconstruct the tissue acoustic properties by solving a full wave propagation inverse problem. In this work, we make a step towards this goal, using Multi-Resolution Convolutional Neural Networks (CNN). As a result, we are able to reconstruct CT-quality images from the reflected ultrasound radio-frequency(RF) data obtained by simulation from real CT scans of a human body. We also show that CNN is able to imitate existing computationally heavy despeckling methods, thereby saving orders of magnitude in computations and making them amenable to real-time applications.
Tasks	Medical Diagnosis
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06304v1
PDF	http://arxiv.org/pdf/1710.06304v1.pdf
PWC	https://paperswithcode.com/paper/towards-ct-quality-ultrasound-imaging-using
Repo
Framework

A relevance-scalability-interpretability tradeoff with temporally evolving user personas


Title	A relevance-scalability-interpretability tradeoff with temporally evolving user personas
Authors	Snigdha Panigrahi, Nadia Fawaz
Abstract	The current work characterizes the users of a VoD streaming space through user-personas based on a tenure timeline and temporal behavioral features in the absence of explicit user profiles. A combination of tenure timeline and temporal characteristics caters to business needs of understanding the evolution and phases of user behavior as their accounts age. The personas constructed in this work successfully represent both dominant and niche characterizations while providing insightful maturation of user behavior in the system. The two major highlights of our personas are demonstration of stability along tenure timelines on a population level, while exhibiting interesting migrations between labels on an individual granularity and clear interpretability of user labels. Finally, we show a trade-off between an indispensable trio of guarantees, relevance-scalability-interpretability by using summary information from personas in a CTR (Click through rate) predictive model. The proposed method of uncovering latent personas, consequent insights from these and application of information from personas to predictive models are broadly applicable to other streaming based products.
Tasks
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07554v2
PDF	http://arxiv.org/pdf/1704.07554v2.pdf
PWC	https://paperswithcode.com/paper/a-relevance-scalability-interpretability
Repo
Framework

Deep Learning Microscopy


Title	Deep Learning Microscopy
Authors	Yair Rivenson, Zoltan Gorocs, Harun Gunaydin, Yibo Zhang, Hongda Wang, Aydogan Ozcan
Abstract	We demonstrate that a deep neural network can significantly improve optical microscopy, enhancing its spatial resolution over a large field-of-view and depth-of-field. After its training, the only input to this network is an image acquired using a regular optical microscope, without any changes to its design. We blindly tested this deep learning approach using various tissue samples that are imaged with low-resolution and wide-field systems, where the network rapidly outputs an image with remarkably better resolution, matching the performance of higher numerical aperture lenses, also significantly surpassing their limited field-of-view and depth-of-field. These results are transformative for various fields that use microscopy tools, including e.g., life sciences, where optical microscopy is considered as one of the most widely used and deployed techniques. Beyond such applications, our presented approach is broadly applicable to other imaging modalities, also spanning different parts of the electromagnetic spectrum, and can be used to design computational imagers that get better and better as they continue to image specimen and establish new transformations among different modes of imaging.
Tasks
Published	2017-05-12
URL	http://arxiv.org/abs/1705.04709v1
PDF	http://arxiv.org/pdf/1705.04709v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-microscopy
Repo
Framework

Multi-Value Rule Sets


Title	Multi-Value Rule Sets
Authors	Tong Wang
Abstract	We present the Multi-vAlue Rule Set (MARS) model for interpretable classification with feature efficient presentations. MARS introduces a more generalized form of association rules that allows multiple values in a condition. Rules of this form are more concise than traditional single-valued rules in capturing and describing patterns in data. MARS mitigates the problem of dealing with continuous features and high-cardinality categorical features faced by rule-based models. Our formulation also pursues a higher efficiency of feature utilization, which reduces the cognitive load to understand the decision process. We propose an efficient inference method for learning a maximum a posteriori model, incorporating theoretically grounded bounds to iteratively reduce the search space to improve search efficiency. Experiments with synthetic and real-world data demonstrate that MARS models have significantly smaller complexity and fewer features, providing better interpretability while being competitive in predictive accuracy. We conducted a usability study with human subjects and results show that MARS is the easiest to use compared with other competing rule-based models, in terms of the correct rate and response time. Overall, MARS introduces a new approach to rule-based models that balance accuracy and interpretability with feature-efficient representations.
Tasks
Published	2017-10-15
URL	http://arxiv.org/abs/1710.05257v1
PDF	http://arxiv.org/pdf/1710.05257v1.pdf
PWC	https://paperswithcode.com/paper/multi-value-rule-sets
Repo
Framework

Evolutionary Many-Objective Optimization Based on Adversarial Decomposition


Title	Evolutionary Many-Objective Optimization Based on Adversarial Decomposition
Authors	Mengyuan Wu, Ke Li, Sam Kwong, Qingfu Zhang
Abstract	The decomposition-based method has been recognized as a major approach for multi-objective optimization. It decomposes a multi-objective optimization problem into several single-objective optimization subproblems, each of which is usually defined as a scalarizing function using a weight vector. Due to the characteristics of the contour line of a particular scalarizing function, the performance of the decomposition-based method strongly depends on the Pareto front’s shape by merely using a single scalarizing function, especially when facing a large number of objectives. To improve the flexibility of the decomposition-based method, this paper develops an adversarial decomposition method that leverages the complementary characteristics of two different scalarizing functions within a single paradigm. More specifically, we maintain two co-evolving populations simultaneously by using different scalarizing functions. In order to avoid allocating redundant computational resources to the same region of the Pareto front, we stably match these two co-evolving populations into one-one solution pairs according to their working regions of the Pareto front. Then, each solution pair can at most contribute one mating parent during the mating selection process. Comparing with nine state-of-the-art many-objective optimizers, we have witnessed the competitive performance of our proposed algorithm on 130 many-objective test instances with various characteristics and Pareto front’s shapes.
Tasks
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02340v1
PDF	http://arxiv.org/pdf/1704.02340v1.pdf
PWC	https://paperswithcode.com/paper/evolutionary-many-objective-optimization
Repo
Framework

Point Neurons with Conductance-Based Synapses in the Neural Engineering Framework


Title	Point Neurons with Conductance-Based Synapses in the Neural Engineering Framework
Authors	Andreas Stöckel, Aaron R. Voelker, Chris Eliasmith
Abstract	The mathematical model underlying the Neural Engineering Framework (NEF) expresses neuronal input as a linear combination of synaptic currents. However, in biology, synapses are not perfect current sources and are thus nonlinear. Detailed synapse models are based on channel conductances instead of currents, which require independent handling of excitatory and inhibitory synapses. This, in particular, significantly affects the influence of inhibitory signals on the neuronal dynamics. In this technical report we first summarize the relevant portions of the NEF and conductance-based synapse models. We then discuss a na"ive translation between populations of LIF neurons with current- and conductance-based synapses based on an estimation of an average membrane potential. Experiments show that this simple approach works relatively well for feed-forward communication channels, yet performance degrades for NEF networks describing more complex dynamics, such as integration.
Tasks
Published	2017-10-20
URL	http://arxiv.org/abs/1710.07659v1
PDF	http://arxiv.org/pdf/1710.07659v1.pdf
PWC	https://paperswithcode.com/paper/point-neurons-with-conductance-based-synapses
Repo
Framework

On the Two-View Geometry of Unsynchronized Cameras


Title	On the Two-View Geometry of Unsynchronized Cameras
Authors	Cenek Albl, Zuzana Kukelova, Andrew Fitzgibbon, Jan Heller, Matej Smid, Tomas Pajdla
Abstract	We present new methods for simultaneously estimating camera geometry and time shift from video sequences from multiple unsynchronized cameras. Algorithms for simultaneous computation of a fundamental matrix or a homography with unknown time shift between images are developed. Our methods use minimal correspondence sets (eight for fundamental matrix and four and a half for homography) and therefore are suitable for robust estimation using RANSAC. Furthermore, we present an iterative algorithm that extends the applicability on sequences which are significantly unsynchronized, finding the correct time shift up to several seconds. We evaluated the methods on synthetic and wide range of real world datasets and the results show a broad applicability to the problem of camera synchronization.
Tasks
Published	2017-04-22
URL	http://arxiv.org/abs/1704.06843v1
PDF	http://arxiv.org/pdf/1704.06843v1.pdf
PWC	https://paperswithcode.com/paper/on-the-two-view-geometry-of-unsynchronized
Repo
Framework

Fast Linear Model for Knowledge Graph Embeddings


Title	Fast Linear Model for Knowledge Graph Embeddings
Authors	Armand Joulin, Edouard Grave, Piotr Bojanowski, Maximilian Nickel, Tomas Mikolov
Abstract	This paper shows that a simple baseline based on a Bag-of-Words (BoW) representation learns surprisingly good knowledge graph embeddings. By casting knowledge base completion and question answering as supervised classification problems, we observe that modeling co-occurences of entities and relations leads to state-of-the-art performance with a training time of a few minutes using the open sourced library fastText.
Tasks	Knowledge Base Completion, Knowledge Graph Embeddings, Question Answering
Published	2017-10-30
URL	http://arxiv.org/abs/1710.10881v1
PDF	http://arxiv.org/pdf/1710.10881v1.pdf
PWC	https://paperswithcode.com/paper/fast-linear-model-for-knowledge-graph
Repo
Framework

Deep Heterogeneous Feature Fusion for Template-Based Face Recognition


Title	Deep Heterogeneous Feature Fusion for Template-Based Face Recognition
Authors	Navaneeth Bodla, Jingxiao Zheng, Hongyu Xu, Jun-Cheng Chen, Carlos Castillo, Rama Chellappa
Abstract	Although deep learning has yielded impressive performance for face recognition, many studies have shown that different networks learn different feature maps: while some networks are more receptive to pose and illumination others appear to capture more local information. Thus, in this work, we propose a deep heterogeneous feature fusion network to exploit the complementary information present in features generated by different deep convolutional neural networks (DCNNs) for template-based face recognition, where a template refers to a set of still face images or video frames from different sources which introduces more blur, pose, illumination and other variations than traditional face datasets. The proposed approach efficiently fuses the discriminative information of different deep features by 1) jointly learning the non-linear high-dimensional projection of the deep features and 2) generating a more discriminative template representation which preserves the inherent geometry of the deep features in the feature space. Experimental results on the IARPA Janus Challenge Set 3 (Janus CS3) dataset demonstrate that the proposed method can effectively improve the recognition performance. In addition, we also present a series of covariate experiments on the face verification task for in-depth qualitative evaluations for the proposed approach.
Tasks	Face Recognition, Face Verification
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04471v1
PDF	http://arxiv.org/pdf/1702.04471v1.pdf
PWC	https://paperswithcode.com/paper/deep-heterogeneous-feature-fusion-for
Repo
Framework

Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings


Title	Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings
Authors	He He, Anusha Balakrishnan, Mihail Eric, Percy Liang
Abstract	We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We collected a dataset of 11K human-human dialogues, which exhibits interesting lexical, semantic, and strategic elements. To model both structured knowledge and unstructured language, we propose a neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses. Automatic and human evaluations show that our model is both more effective at achieving the goal and more human-like than baseline neural and rule-based models.
Tasks	Knowledge Graph Embeddings
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07130v1
PDF	http://arxiv.org/pdf/1704.07130v1.pdf
PWC	https://paperswithcode.com/paper/learning-symmetric-collaborative-dialogue
Repo
Framework

Kernel clustering: density biases and solutions


Title	Kernel clustering: density biases and solutions
Authors	Dmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov
Abstract	Kernel methods are popular in clustering due to their generality and discriminating power. However, we show that many kernel clustering criteria have density biases theoretically explaining some practically significant artifacts empirically observed in the past. For example, we provide conditions and formally prove the density mode isolation bias in kernel K-means for a common class of kernels. We call it Breiman’s bias due to its similarity to the histogram mode isolation previously discovered by Breiman in decision tree learning with Gini impurity. We also extend our analysis to other popular kernel clustering methods, e.g. average/normalized cut or dominant sets, where density biases can take different forms. For example, splitting isolated points by cut-based criteria is essentially the sparsest subset bias, which is the opposite of the density mode bias. Our findings suggest that a principled solution for density biases in kernel clustering should directly address data inhomogeneity. We show that density equalization can be implicitly achieved using either locally adaptive weights or locally adaptive kernels. Moreover, density equalization makes many popular kernel clustering objectives equivalent. Our synthetic and real data experiments illustrate density biases and proposed solutions. We anticipate that theoretical understanding of kernel clustering limitations and their principled solutions will be important for a broad spectrum of data analysis applications across the disciplines.
Tasks
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05950v5
PDF	http://arxiv.org/pdf/1705.05950v5.pdf
PWC	https://paperswithcode.com/paper/kernel-clustering-density-biases-and
Repo
Framework

Wireless Interference Identification with Convolutional Neural Networks


Title	Wireless Interference Identification with Convolutional Neural Networks
Authors	Malte Schmidt, Dimitri Block, Uwe Meier
Abstract	The steadily growing use of license-free frequency bands requires reliable coexistence management for deterministic medium utilization. For interference mitigation, proper wireless interference identification (WII) is essential. In this work we propose the first WII approach based upon deep convolutional neural networks (CNNs). The CNN naively learns its features through self-optimization during an extensive data-driven GPU-based training process. We propose a CNN example which is based upon sensing snapshots with a limited duration of 12.8 {\mu}s and an acquisition bandwidth of 10 MHz. The CNN differs between 15 classes. They represent packet transmissions of IEEE 802.11 b/g, IEEE 802.15.4 and IEEE 802.15.1 with overlapping frequency channels within the 2.4 GHz ISM band. We show that the CNN outperforms state-of-the-art WII approaches and has a classification accuracy greater than 95% for signal-to-noise ratio of at least -5 dB.
Tasks
Published	2017-03-02
URL	http://arxiv.org/abs/1703.00737v1
PDF	http://arxiv.org/pdf/1703.00737v1.pdf
PWC	https://paperswithcode.com/paper/wireless-interference-identification-with
Repo
Framework

Fast rates for online learning in Linearly Solvable Markov Decision Processes


Title	Fast rates for online learning in Linearly Solvable Markov Decision Processes
Authors	Gergely Neu, Vicenç Gómez
Abstract	We study the problem of online learning in a class of Markov decision processes known as linearly solvable MDPs. In the stationary version of this problem, a learner interacts with its environment by directly controlling the state transitions, attempting to balance a fixed state-dependent cost and a certain smooth cost penalizing extreme control inputs. In the current paper, we consider an online setting where the state costs may change arbitrarily between consecutive rounds, and the learner only observes the costs at the end of each respective round. We are interested in constructing algorithms for the learner that guarantee small regret against the best stationary control policy chosen in full knowledge of the cost sequence. Our main result is showing that the smoothness of the control cost enables the simple algorithm of following the leader to achieve a regret of order $\log^2 T$ after $T$ rounds, vastly improving on the best known regret bound of order $T^{3/4}$ for this setting.
Tasks
Published	2017-02-21
URL	http://arxiv.org/abs/1702.06341v2
PDF	http://arxiv.org/pdf/1702.06341v2.pdf
PWC	https://paperswithcode.com/paper/fast-rates-for-online-learning-in-linearly
Repo
Framework