July 27, 2019

3140 words 15 mins read

Paper Group ANR 488

Matching Code and Law: Achieving Algorithmic Fairness with Optimal Transport. Accelerating CS in Parallel Imaging Reconstructions Using an Efficient and Effective Circulant Preconditioner. Depression Severity Estimation from Multiple Modalities. Tuning Over-Relaxed ADMM. Spontaneous Symmetry Breaking in Neural Networks. Cardinal Virtues: Extracting …

Matching Code and Law: Achieving Algorithmic Fairness with Optimal Transport


Title	Matching Code and Law: Achieving Algorithmic Fairness with Optimal Transport
Authors	Meike Zehlike, Philipp Hacker, Emil Wiedemann
Abstract	Increasingly, discrimination by algorithms is perceived as a societal and legal problem. As a response, a number of criteria for implementing algorithmic fairness in machine learning have been developed in the literature. This paper proposes the Continuous Fairness Algorithm (CFA$\theta$) which enables a continuous interpolation between different fairness definitions. More specifically, we make three main contributions to the existing literature. First, our approach allows the decision maker to continuously vary between specific concepts of individual and group fairness. As a consequence, the algorithm enables the decision maker to adopt intermediate `worldviews'' on the degree of discrimination encoded in algorithmic processes, adding nuance to the extreme cases of` we’re all equal’’ (WAE) and ``what you see is what you get’’ (WYSIWYG) proposed so far in the literature. Second, we use optimal transport theory, and specifically the concept of the barycenter, to maximize decision maker utility under the chosen fairness constraints. Third, the algorithm is able to handle cases of intersectionality, i.e., of multi-dimensional discrimination of certain groups on grounds of several criteria. We discuss three main examples (credit applications; college admissions; insurance contracts) and map out the legal and policy implications of our approach. The explicit formalization of the trade-off between individual and group fairness allows this post-processing approach to be tailored to different situational contexts in which one or the other fairness criterion may take precedence. Finally, we evaluate our model experimentally. \|
Tasks
Published	2017-12-21
URL	https://arxiv.org/abs/1712.07924v2
PDF	https://arxiv.org/pdf/1712.07924v2.pdf
PWC	https://paperswithcode.com/paper/a-continuous-framework-for-fairness
Repo
Framework

Accelerating CS in Parallel Imaging Reconstructions Using an Efficient and Effective Circulant Preconditioner


Title	Accelerating CS in Parallel Imaging Reconstructions Using an Efficient and Effective Circulant Preconditioner
Authors	Kirsten Koolstra, Jeroen van Gemert, Peter Börnert, Andrew Webb, Rob Remis
Abstract	Purpose: Design of a preconditioner for fast and efficient parallel imaging and compressed sensing reconstructions. Theory: Parallel imaging and compressed sensing reconstructions become time consuming when the problem size or the number of coils is large, due to the large linear system of equations that has to be solved in l_1 and l_2-norm based reconstruction algorithms. Such linear systems can be solved efficiently using effective preconditioning techniques. Methods: In this paper we construct such a preconditioner by approximating the system matrix of the linear system, which comprises the data fidelity and includes total variation and wavelet regularization, by a matrix with the assumption that is a block circulant matrix with circulant blocks. Due to its circulant structure, the preconditioner can be constructed quickly and its inverse can be evaluated fast using only two fast Fourier transformations. We test the performance of the preconditioner for the conjugate gradient method as the linear solver, integrated into the Split Bregman algorithm. Results: The designed circulant preconditioner reduces the number of iterations required in the conjugate gradient method by almost a factor of~5. The speed up results in a total acceleration factor of approximately 2.5 for the entire reconstruction algorithm when implemented in MATLAB, while the initialization time of the preconditioner is negligible. Conclusion: The proposed preconditioner reduces the reconstruction time for parallel imaging and compressed sensing in a Split Bregman implementation and can easily handle large systems since it is Fourier-based, allowing for efficient computations. Key words: preconditioning; compressed sensing; Split Bregman; parallel imaging
Tasks
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01758v1
PDF	http://arxiv.org/pdf/1710.01758v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-cs-in-parallel-imaging
Repo
Framework

Depression Severity Estimation from Multiple Modalities


Title	Depression Severity Estimation from Multiple Modalities
Authors	Evgeny Stepanov, Stephane Lathuiliere, Shammur Absar Chowdhury, Arindam Ghosh, Radu-Laurentiu Vieriu, Nicu Sebe, Giuseppe Riccardi
Abstract	Depression is a major debilitating disorder which can affect people from all ages. With a continuous increase in the number of annual cases of depression, there is a need to develop automatic techniques for the detection of the presence and extent of depression. In this AVEC challenge we explore different modalities (speech, language and visual features extracted from face) to design and develop automatic methods for the detection of depression. In psychology literature, the PHQ-8 questionnaire is well established as a tool for measuring the severity of depression. In this paper we aim to automatically predict the PHQ-8 scores from features extracted from the different modalities. We show that visual features extracted from facial landmarks obtain the best performance in terms of estimating the PHQ-8 results with a mean absolute error (MAE) of 4.66 on the development set. Behavioral characteristics from speech provide an MAE of 4.73. Language features yield a slightly higher MAE of 5.17. When switching to the test set, our Turn Features derived from audio transcriptions achieve the best performance, scoring an MAE of 4.11 (corresponding to an RMSE of 4.94), which makes our system the winner of the AVEC 2017 depression sub-challenge.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.06095v1
PDF	http://arxiv.org/pdf/1711.06095v1.pdf
PWC	https://paperswithcode.com/paper/depression-severity-estimation-from-multiple
Repo
Framework

Tuning Over-Relaxed ADMM


Title	Tuning Over-Relaxed ADMM
Authors	Guilherme França, José Bento
Abstract	The framework of Integral Quadratic Constraints (IQC) reduces the computation of upper bounds on the convergence rate of several optimization algorithms to a semi-definite program (SDP). In the case of over-relaxed Alternating Direction Method of Multipliers (ADMM), an explicit and closed form solution to this SDP was derived in our recent work [1]. The purpose of this paper is twofold. First, we summarize these results. Second, we explore one of its consequences which allows us to obtain general and simple formulas for optimal parameter selection. These results are valid for arbitrary strongly convex objective functions.
Tasks
Published	2017-03-10
URL	http://arxiv.org/abs/1703.03863v2
PDF	http://arxiv.org/pdf/1703.03863v2.pdf
PWC	https://paperswithcode.com/paper/tuning-over-relaxed-admm
Repo
Framework

Spontaneous Symmetry Breaking in Neural Networks


Title	Spontaneous Symmetry Breaking in Neural Networks
Authors	Ricky Fok, Aijun An, Xiaogang Wang
Abstract	We propose a framework to understand the unprecedented performance and robustness of deep neural networks using field theory. Correlations between the weights within the same layer can be described by symmetries in that layer, and networks generalize better if such symmetries are broken to reduce the redundancies of the weights. Using a two parameter field theory, we find that the network can break such symmetries itself towards the end of training in a process commonly known in physics as spontaneous symmetry breaking. This corresponds to a network generalizing itself without any user input layers to break the symmetry, but by communication with adjacent layers. In the layer decoupling limit applicable to residual networks (He et al., 2015), we show that the remnant symmetries that survive the non-linear layers are spontaneously broken. The Lagrangian for the non-linear and weight layers together has striking similarities with the one in quantum field theory of a scalar. Using results from quantum field theory we show that our framework is able to explain many experimentally observed phenomena,such as training on random labels with zero error (Zhang et al., 2017), the information bottleneck, the phase transition out of it and gradient variance explosion (Shwartz-Ziv & Tishby, 2017), shattered gradients (Balduzzi et al., 2017), and many more.
Tasks
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06096v1
PDF	http://arxiv.org/pdf/1710.06096v1.pdf
PWC	https://paperswithcode.com/paper/spontaneous-symmetry-breaking-in-neural
Repo
Framework

Cardinal Virtues: Extracting Relation Cardinalities from Text


Title	Cardinal Virtues: Extracting Relation Cardinalities from Text
Authors	Paramita Mirza, Simon Razniewski, Fariz Darari, Gerhard Weikum
Abstract	Information extraction (IE) from text has largely focused on relations between individual entities, such as who has won which award. However, some facts are never fully mentioned, and no IE method has perfect recall. Thus, it is beneficial to also tap contents about the cardinalities of these relations, for example, how many awards someone has won. We introduce this novel problem of extracting cardinalities and discusses the specific challenges that set it apart from standard IE. We present a distant supervision method using conditional random fields. A preliminary evaluation results in precision between 3% and 55%, depending on the difficulty of relations.
Tasks
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04455v2
PDF	http://arxiv.org/pdf/1704.04455v2.pdf
PWC	https://paperswithcode.com/paper/cardinal-virtues-extracting-relation
Repo
Framework

Evolving soft locomotion in aquatic and terrestrial environments: effects of material properties and environmental transitions


Title	Evolving soft locomotion in aquatic and terrestrial environments: effects of material properties and environmental transitions
Authors	Francesco Corucci, Nick Cheney, Francesco Giorgio-Serchi, Josh Bongard, Cecilia Laschi
Abstract	Designing soft robots poses considerable challenges: automated design approaches may be particularly appealing in this field, as they promise to optimize complex multi-material machines with very little or no human intervention. Evolutionary soft robotics is concerned with the application of optimization algorithms inspired by natural evolution in order to let soft robots (both morphologies and controllers) spontaneously evolve within physically-realistic simulated environments, figuring out how to satisfy a set of objectives defined by human designers. In this paper a powerful evolutionary system is put in place in order to perform a broad investigation on the free-form evolution of walking and swimming soft robots in different environments. Three sets of experiments are reported, tackling different aspects of the evolution of soft locomotion. The first two sets explore the effects of different material properties on the evolution of terrestrial and aquatic soft locomotion: particularly, we show how different materials lead to the evolution of different morphologies, behaviors, and energy-performance tradeoffs. It is found that within our simplified physics world stiffer robots evolve more sophisticated and effective gaits and morphologies on land, while softer ones tend to perform better in water. The third set of experiments starts investigating the effect and potential benefits of major environmental transitions (land - water) during evolution. Results provide interesting morphological exaptation phenomena, and point out a potential asymmetry between land-water and water-land transitions: while the first type of transition appears to be detrimental, the second one seems to have some beneficial effects.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06605v1
PDF	http://arxiv.org/pdf/1711.06605v1.pdf
PWC	https://paperswithcode.com/paper/evolving-soft-locomotion-in-aquatic-and
Repo
Framework

Image Restoration using Autoencoding Priors


Title	Image Restoration using Autoencoding Priors
Authors	Siavash Arjomand Bigdeli, Matthias Zwicker
Abstract	We propose to leverage denoising autoencoder networks as priors to address image restoration problems. We build on the key observation that the output of an optimal denoising autoencoder is a local mean of the true data density, and the autoencoder error (the difference between the output and input of the trained autoencoder) is a mean shift vector. We use the magnitude of this mean shift vector, that is, the distance to the local mean, as the negative log likelihood of our natural image prior. For image restoration, we maximize the likelihood using gradient descent by backpropagating the autoencoder error. A key advantage of our approach is that we do not need to train separate networks for different image restoration tasks, such as non-blind deconvolution with different kernels, or super-resolution at different magnification factors. We demonstrate state of the art results for non-blind deconvolution and super-resolution using the same autoencoding prior.
Tasks	Denoising, Image Restoration, Super-Resolution
Published	2017-03-29
URL	http://arxiv.org/abs/1703.09964v1
PDF	http://arxiv.org/pdf/1703.09964v1.pdf
PWC	https://paperswithcode.com/paper/image-restoration-using-autoencoding-priors
Repo
Framework

ADaPTION: Toolbox and Benchmark for Training Convolutional Neural Networks with Reduced Numerical Precision Weights and Activation


Title	ADaPTION: Toolbox and Benchmark for Training Convolutional Neural Networks with Reduced Numerical Precision Weights and Activation
Authors	Moritz B. Milde, Daniel Neil, Alessandro Aimar, Tobi Delbruck, Giacomo Indiveri
Abstract	Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functions within the deep network are typically stored with high-precision formats, e.g. 32 bit floating point. However, since storage capacity is limited and each memory access consumes power, both storage capacity and memory access are two crucial factors in these networks. Here we present a method and present the ADaPTION toolbox to extend the popular deep learning library Caffe to support training of deep CNNs with reduced numerical precision of weights and activations using fixed point notation. ADaPTION includes tools to measure the dynamic range of weights and activations. Using the ADaPTION tools, we quantized several CNNs including VGG16 down to 16-bit weights and activations with only 0.8% drop in Top-1 accuracy. The quantization, especially of the activations, leads to increase of up to 50% of sparsity especially in early and intermediate layers, which we exploit to skip multiplications with zero, thus performing faster and computationally cheaper inference.
Tasks	Quantization
Published	2017-11-13
URL	http://arxiv.org/abs/1711.04713v1
PDF	http://arxiv.org/pdf/1711.04713v1.pdf
PWC	https://paperswithcode.com/paper/adaption-toolbox-and-benchmark-for-training
Repo
Framework

On Multilingual Training of Neural Dependency Parsers


Title	On Multilingual Training of Neural Dependency Parsers
Authors	Michał Zapotoczny, Paweł Rychlikowski, Jan Chorowski
Abstract	We show that a recently proposed neural dependency parser can be improved by joint training on multiple languages from the same family. The parser is implemented as a deep neural network whose only input is orthographic representations of words. In order to successfully parse, the network has to discover how linguistically relevant concepts can be inferred from word spellings. We analyze the representations of characters and words that are learned by the network to establish which properties of languages were accounted for. In particular we show that the parser has approximately learned to associate Latin characters with their Cyrillic counterparts and that it can group Polish and Russian words that have a similar grammatical function. Finally, we evaluate the parser on selected languages from the Universal Dependencies dataset and show that it is competitive with other recently proposed state-of-the art methods, while having a simple structure.
Tasks
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10209v1
PDF	http://arxiv.org/pdf/1705.10209v1.pdf
PWC	https://paperswithcode.com/paper/on-multilingual-training-of-neural-dependency
Repo
Framework

Iterative Object and Part Transfer for Fine-Grained Recognition


Title	Iterative Object and Part Transfer for Fine-Grained Recognition
Authors	Zhiqiang Shen, Yu-Gang Jiang, Dequan Wang, Xiangyang Xue
Abstract	The aim of fine-grained recognition is to identify sub-ordinate categories in images like different species of birds. Existing works have confirmed that, in order to capture the subtle differences across the categories, automatic localization of objects and parts is critical. Most approaches for object and part localization relied on the bottom-up pipeline, where thousands of region proposals are generated and then filtered by pre-trained object/part models. This is computationally expensive and not scalable once the number of objects/parts becomes large. In this paper, we propose a nonparametric data-driven method for object and part localization. Given an unlabeled test image, our approach transfers annotations from a few similar images retrieved in the training set. In particular, we propose an iterative transfer strategy that gradually refine the predicted bounding boxes. Based on the located objects and parts, deep convolutional features are extracted for recognition. We evaluate our approach on the widely-used CUB200-2011 dataset and a new and large dataset called Birdsnap. On both datasets, we achieve better results than many state-of-the-art approaches, including a few using oracle (manually annotated) bounding boxes in the test images.
Tasks
Published	2017-03-29
URL	http://arxiv.org/abs/1703.09983v1
PDF	http://arxiv.org/pdf/1703.09983v1.pdf
PWC	https://paperswithcode.com/paper/iterative-object-and-part-transfer-for-fine
Repo
Framework

BodyDigitizer: An Open Source Photogrammetry-based 3D Body Scanner


Title	BodyDigitizer: An Open Source Photogrammetry-based 3D Body Scanner
Authors	Travis Gesslein, Daniel Scherer, Jens Grubert
Abstract	With the rising popularity of Augmented and Virtual Reality, there is a need for representing humans as virtual avatars in various application domains ranging from remote telepresence, games to medical applications. Besides explicitly modelling 3D avatars, sensing approaches that create person-specific avatars are becoming popular. However, affordable solutions typically suffer from a low visual quality and professional solution are often too expensive to be deployed in nonprofit projects. We present an open-source project, BodyDigitizer, which aims at providing both build instructions and configuration software for a high-resolution photogrammetry-based 3D body scanner. Our system encompasses up to 96 Rasperry PI cameras, active LED lighting, a sturdy frame construction and open-source configuration software. %We demonstrate the applicability of the body scanner in a nonprofit Mixed Reality health project. The detailed build instruction and software are available at http://www.bodydigitizer.org.
Tasks
Published	2017-10-03
URL	http://arxiv.org/abs/1710.01370v2
PDF	http://arxiv.org/pdf/1710.01370v2.pdf
PWC	https://paperswithcode.com/paper/bodydigitizer-an-open-source-photogrammetry
Repo
Framework

An Attention-based Collaboration Framework for Multi-View Network Representation Learning


Title	An Attention-based Collaboration Framework for Multi-View Network Representation Learning
Authors	Meng Qu, Jian Tang, Jingbo Shang, Xiang Ren, Ming Zhang, Jiawei Han
Abstract	Learning distributed node representations in networks has been attracting increasing attention recently due to its effectiveness in a variety of applications. Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network. However, in reality there usually exists multiple types of proximities between nodes, yielding networks with multiple views. This paper studies learning node representations for networks with multiple views, which aims to infer robust node representations across different views. We propose a multi-view representation learning approach, which promotes the collaboration of different views and lets them vote for the robust representations. During the voting process, an attention mechanism is introduced, which enables each node to focus on the most informative views. Experimental results on real-world networks show that the proposed approach outperforms existing state-of-the-art approaches for network representation learning with a single view and other competitive approaches with multiple views.
Tasks	Representation Learning
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06636v1
PDF	http://arxiv.org/pdf/1709.06636v1.pdf
PWC	https://paperswithcode.com/paper/an-attention-based-collaboration-framework
Repo
Framework

Learnable Explicit Density for Continuous Latent Space and Variational Inference


Title	Learnable Explicit Density for Continuous Latent Space and Variational Inference
Authors	Chin-Wei Huang, Ahmed Touati, Laurent Dinh, Michal Drozdzal, Mohammad Havaei, Laurent Charlin, Aaron Courville
Abstract	In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior. First, we decompose the learning of VAEs into layerwise density estimation, and argue that having a flexible prior is beneficial to both sample generation and inference. Second, we analyze the family of inverse autoregressive flows (inverse AF) and show that with further improvement, inverse AF could be used as universal approximation to any complicated posterior. Our analysis results in a unified approach to parameterizing a VAE, without the need to restrict ourselves to use factorial Gaussians in the latent real space.
Tasks	Density Estimation
Published	2017-10-06
URL	http://arxiv.org/abs/1710.02248v1
PDF	http://arxiv.org/pdf/1710.02248v1.pdf
PWC	https://paperswithcode.com/paper/learnable-explicit-density-for-continuous
Repo
Framework

Person Re-identification Using Visual Attention


Title	Person Re-identification Using Visual Attention
Authors	Alireza Rahimpour, Liu Liu, Ali Taalimi, Yang Song, Hairong Qi
Abstract	Despite recent attempts for solving the person re-identification problem, it remains a challenging task since a person’s appearance can vary significantly when large variations in view angle, human pose, and illumination are involved. In this paper, we propose a novel approach based on using a gradient-based attention mechanism in deep convolution neural network for solving the person re-identification problem. Our model learns to focus selectively on parts of the input image for which the networks’ output is most sensitive to and processes them with high resolution while perceiving the surrounding image in low resolution. Extensive comparative evaluations demonstrate that the proposed method outperforms state-of-the-art approaches on the challenging CUHK01, CUHK03, and Market 1501 datasets.
Tasks	Person Re-Identification
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07336v7
PDF	http://arxiv.org/pdf/1707.07336v7.pdf
PWC	https://paperswithcode.com/paper/person-re-identification-using-visual
Repo
Framework