January 26, 2020

3418 words 17 mins read

Paper Group ANR 1551

Examining Gender Bias in Languages with Grammatical Gender. Towards a Rigorous Evaluation of XAI Methods on Time Series. Transaction Confirmation Time Prediction in Ethereum Blockchain Using Machine Learning. Periocular Recognition in the Wild with Orthogonal Combination of Local Binary Coded Pattern in Dual-stream Convolutional Neural Network. A R …

Examining Gender Bias in Languages with Grammatical Gender


Title	Examining Gender Bias in Languages with Grammatical Gender
Authors	Pei Zhou, Weijia Shi, Jieyu Zhao, Kuan-Hao Huang, Muhao Chen, Ryan Cotterell, Kai-Wei Chang
Abstract	Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be directly extended to languages that exhibit morphological agreement on gender, such as Spanish and French. In this paper, we propose new metrics for evaluating gender bias in word embeddings of these languages and further demonstrate evidence of gender bias in bilingual embeddings which align these languages with English. Finally, we extend an existing approach to mitigate gender bias in word embeddings under both monolingual and bilingual settings. Experiments on modified Word Embedding Association Test, word similarity, word translation, and word pair translation tasks show that the proposed approaches effectively reduce the gender bias while preserving the utility of the embeddings.
Tasks	Word Embeddings
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02224v2
PDF	https://arxiv.org/pdf/1909.02224v2.pdf
PWC	https://paperswithcode.com/paper/examining-gender-bias-in-languages-with
Repo
Framework

Towards a Rigorous Evaluation of XAI Methods on Time Series


Title	Towards a Rigorous Evaluation of XAI Methods on Time Series
Authors	Udo Schlegel, Hiba Arnout, Mennatallah El-Assady, Daniela Oelke, Daniel A. Keim
Abstract	Explainable Artificial Intelligence (XAI) methods are typically deployed to explain and debug black-box machine learning models. However, most proposed XAI methods are black-boxes themselves and designed for images. Thus, they rely on visual interpretability to evaluate and prove explanations. In this work, we apply XAI methods previously used in the image and text-domain on time series. We present a methodology to test and evaluate various XAI methods on time series by introducing new verification techniques to incorporate the temporal dimension. We further conduct preliminary experiments to assess the quality of selected XAI method explanations with various verification methods on a range of datasets and inspecting quality metrics on it. We demonstrate that in our initial experiments, SHAP works robust for all models, but others like DeepLIFT, LRP, and Saliency Maps work better with specific architectures.
Tasks	Time Series
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07082v2
PDF	https://arxiv.org/pdf/1909.07082v2.pdf
PWC	https://paperswithcode.com/paper/towards-a-rigorous-evaluation-of-xai-methods
Repo
Framework

Transaction Confirmation Time Prediction in Ethereum Blockchain Using Machine Learning


Title	Transaction Confirmation Time Prediction in Ethereum Blockchain Using Machine Learning
Authors	Harsh Jot Singh, Abdelhakim Senhaji Hafid
Abstract	Blockchain offers a decentralized, immutable, transparent system of records. It offers a peer-to-peer network of nodes with no centralised governing entity making it unhackable and therefore, more secure than the traditional paper-based or centralised system of records like banks etc. While there are certain advantages to the paper-based recording approach, it does not work well with digital relationships where the data is in constant flux. Unlike traditional channels, governed by centralized entities, blockchain offers its users a certain level of anonymity by providing capabilities to interact without disclosing their personal identities and allows them to build trust without a third-party governing entity. Due to the aforementioned characteristics of blockchain, more and more users around the globe are inclined towards making a digital transaction via blockchain than via rudimentary channels. Therefore, there is a dire need for us to gain insight on how these transactions are processed by the blockchain and how much time it may take for a peer to confirm a transaction and add it to the blockchain network. This paper presents a novel approach that would allow one to estimate the time, in block time or otherwise, it would take for a mining node to accept and confirm a transaction to a block using machine learning. The paper also aims to compare the predictive accuracy of two machine learning regression models- Random Forest Regressor and Multilayer Perceptron against previously proposed statistical regression model under a set evaluation criterion. The objective is to determine whether machine learning offers a more accurate predictive model than conventional statistical models. The proposed model results in improved accuracy in prediction.
Tasks
Published	2019-11-25
URL	https://arxiv.org/abs/1911.11592v1
PDF	https://arxiv.org/pdf/1911.11592v1.pdf
PWC	https://paperswithcode.com/paper/transaction-confirmation-time-prediction-in
Repo
Framework

Periocular Recognition in the Wild with Orthogonal Combination of Local Binary Coded Pattern in Dual-stream Convolutional Neural Network


Title	Periocular Recognition in the Wild with Orthogonal Combination of Local Binary Coded Pattern in Dual-stream Convolutional Neural Network
Authors	Leslie Ching Ow Tiong, Andrew Beng Jin Teoh, Yunli Lee
Abstract	In spite of the advancements made in the periocular recognition, the dataset and periocular recognition in the wild remains a challenge. In this paper, we propose a multilayer fusion approach by means of a pair of shared parameters (dual-stream) convolutional neural network where each network accepts RGB data and a novel colour-based texture descriptor, namely Orthogonal Combination-Local Binary Coded Pattern (OC-LBCP) for periocular recognition in the wild. Specifically, two distinct late-fusion layers are introduced in the dual-stream network to aggregate the RGB data and OC-LBCP. Thus, the network beneficial from this new feature of the late-fusion layers for accuracy performance gain. We also introduce and share a new dataset for periocular in the wild, namely Ethnic-ocular dataset for benchmarking. The proposed network has also been assessed on one publicly available dataset, namely UBIPr. The proposed network outperforms several competing approaches on these datasets.
Tasks
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06383v2
PDF	http://arxiv.org/pdf/1902.06383v2.pdf
PWC	https://paperswithcode.com/paper/periocular-recognition-in-the-wild-with
Repo
Framework

A Random Matrix Perspective on Mixtures of Nonlinearities for Deep Learning


Title	A Random Matrix Perspective on Mixtures of Nonlinearities for Deep Learning
Authors	Ben Adlam, Jake Levinson, Jeffrey Pennington
Abstract	One of the distinguishing characteristics of modern deep learning systems is that they typically employ neural network architectures that utilize enormous numbers of parameters, often in the millions and sometimes even in the billions. While this paradigm has inspired significant research on the properties of large networks, relatively little work has been devoted to the fact that these networks are often used to model large complex datasets, which may themselves contain millions or even billions of constraints. In this work, we focus on this high-dimensional regime in which both the dataset size and the number of features tend to infinity. We analyze the performance of a simple regression model trained on the random features $F=f(WX+B)$ for a random weight matrix $W$ and random bias vector $B$, obtaining an exact formula for the asymptotic training error on a noisy autoencoding task. The role of the bias can be understood as parameterizing a distribution over activation functions, and our analysis directly generalizes to such distributions, even those not expressible with a traditional additive bias. Intriguingly, we find that a mixture of nonlinearities can outperform the best single nonlinearity on the noisy autoecndoing task, suggesting that mixtures of nonlinearities might be useful for approximate kernel methods or neural network architecture design.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00827v1
PDF	https://arxiv.org/pdf/1912.00827v1.pdf
PWC	https://paperswithcode.com/paper/a-random-matrix-perspective-on-mixtures-of-1
Repo
Framework

Learning Accurate, Comfortable and Human-like Driving


Title	Learning Accurate, Comfortable and Human-like Driving
Authors	Simon Hecker, Dengxin Dai, Luc Van Gool
Abstract	Autonomous vehicles are more likely to be accepted if they drive accurately, comfortably, but also similar to how human drivers would. This is especially true when autonomous and human-driven vehicles need to share the same road. The main research focus thus far, however, is still on improving driving accuracy only. This paper formalizes the three concerns with the aim of accurate, comfortable and human-like driving. Three contributions are made in this paper. First, numerical map data from HERE Technologies are employed for more accurate driving; a set of map features which are believed to be relevant to driving are engineered to navigate better. Second, the learning procedure is improved from a pointwise prediction to a sequence-based prediction and passengers’ comfort measures are embedded into the learning algorithm. Finally, we take advantage of the advances in adversary learning to learn human-like driving; specifically, the standard L1 or L2 loss is augmented by an adversary loss which is based on a discriminator trained to distinguish between human driving and machine driving. Our model is trained and evaluated on the Drive360 dataset, which features 60 hours and 3000 km of real-world driving data. Extensive experiments show that our driving model is more accurate, more comfortable and behaves more like a human driver than previous methods. The resources of this work will be released on the project page.
Tasks	Autonomous Vehicles
Published	2019-03-26
URL	http://arxiv.org/abs/1903.10995v1
PDF	http://arxiv.org/pdf/1903.10995v1.pdf
PWC	https://paperswithcode.com/paper/learning-accurate-comfortable-and-human-like
Repo
Framework

A new asymmetric $ε$-insensitive pinball loss function based support vector quantile regression model


Title	A new asymmetric $ε$-insensitive pinball loss function based support vector quantile regression model
Authors	Pritam Anand, Reshma Rastogi, Suresh Chandra
Abstract	In this paper, we propose a novel asymmetric $\epsilon$-insensitive pinball loss function for quantile estimation. There exists some pinball loss functions which attempt to incorporate the $\epsilon$-insensitive zone approach in it but, they fail to extend the $\epsilon$-insensitive approach for quantile estimation in true sense. The proposed asymmetric $\epsilon$-insensitive pinball loss function can make an asymmetric $\epsilon$- insensitive zone of fixed width around the data and divide it using $\tau$ value for the estimation of the $\tau$th quantile. The use of the proposed asymmetric $\epsilon$-insensitive pinball loss function in Support Vector Quantile Regression (SVQR) model improves its prediction ability significantly. It also brings the sparsity back in SVQR model. Further, the numerical results obtained by several experiments carried on artificial and real world datasets empirically show the efficacy of the proposed `$\epsilon$-Support Vector Quantile Regression’ ($\epsilon$-SVQR) model over other existing SVQR models. \|
Tasks
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06923v1
PDF	https://arxiv.org/pdf/1908.06923v1.pdf
PWC	https://paperswithcode.com/paper/a-new-asymmetric-insensitive-pinball-loss
Repo
Framework

Optimized Compilation of Aggregated Instructions for Realistic Quantum Computers


Title	Optimized Compilation of Aggregated Instructions for Realistic Quantum Computers
Authors	Yunong Shi, Nelson Leung, Pranav Gokhale, Zane Rossi, David I. Schuster, Henry Hoffman, Fred T. Chong
Abstract	Recent developments in engineering and algorithms have made real-world applications in quantum computing possible in the near future. Existing quantum programming languages and compilers use a quantum assembly language composed of 1- and 2-qubit (quantum bit) gates. Quantum compiler frameworks translate this quantum assembly to electric signals (called control pulses) that implement the specified computation on specific physical devices. However, there is a mismatch between the operations defined by the 1- and 2-qubit logical ISA and their underlying physical implementation, so the current practice of directly translating logical instructions into control pulses results in inefficient, high-latency programs. To address this inefficiency, we propose a universal quantum compilation methodology that aggregates multiple logical operations into larger units that manipulate up to 10 qubits at a time. Our methodology then optimizes these aggregates by (1) finding commutative intermediate operations that result in more efficient schedules and (2) creating custom control pulses optimized for the aggregate (instead of individual 1- and 2-qubit operations). Compared to the standard gate-based compilation, the proposed approach realizes a deeper vertical integration of high-level quantum software and low-level, physical quantum hardware. We evaluate our approach on important near-term quantum applications on simulations of superconducting quantum architectures. Our proposed approach provides a mean speedup of $5\times$, with a maximum of $10\times$. Because latency directly affects the feasibility of quantum computation, our results not only improve performance but also have the potential to enable quantum computation sooner than otherwise possible.
Tasks
Published	2019-02-04
URL	http://arxiv.org/abs/1902.01474v2
PDF	http://arxiv.org/pdf/1902.01474v2.pdf
PWC	https://paperswithcode.com/paper/optimized-compilation-of-aggregated
Repo
Framework

Do NLP Models Know Numbers? Probing Numeracy in Embeddings


Title	Do NLP Models Know Numbers? Probing Numeracy in Embeddings
Authors	Eric Wallace, Yizhong Wang, Sujian Li, Sameer Singh, Matt Gardner
Abstract	The ability to understand and work with numbers (numeracy) is critical for many complex reasoning tasks. Currently, most NLP models treat numbers in text in the same way as other tokens—they embed them as distributed vectors. Is this enough to capture numeracy? We begin by investigating the numerical reasoning capabilities of a state-of-the-art question answering model on the DROP dataset. We find this model excels on questions that require numerical reasoning, i.e., it already captures numeracy. To understand how this capability emerges, we probe token embedding methods (e.g., BERT, GloVe) on synthetic list maximum, number decoding, and addition tasks. A surprising degree of numeracy is naturally present in standard embeddings. For example, GloVe and word2vec accurately encode magnitude for numbers up to 1,000. Furthermore, character-level embeddings are even more precise—ELMo captures numeracy the best for all pre-trained methods—but BERT, which uses sub-word units, is less exact.
Tasks	Question Answering
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07940v2
PDF	https://arxiv.org/pdf/1909.07940v2.pdf
PWC	https://paperswithcode.com/paper/do-nlp-models-know-numbers-probing-numeracy
Repo
Framework

Quantifying the pathways to life using assembly spaces


Title	Quantifying the pathways to life using assembly spaces
Authors	Stuart M. Marshall, Douglas Moore, Alastair R. G. Murray, Sara I. Walker, Leroy Cronin
Abstract	We have developed the concept of pathway assembly to explore the amount of extrinsic information required to build an object. To quantify this information in an agnostic way, we present a method to determine the amount of pathway assembly information contained within such an object by deconstructing the object into its irreducible parts, and then evaluating the minimum number of steps to reconstruct the object along any pathway. The mathematical formalisation of this approach uses an assembly space. By finding the minimal number of steps contained in the route by which the objects can be assembled within that space, we can compare how much information (I) is gained from knowing this pathway assembly index (PA) according to I_PA=log (N)/(N_PA ) where, for an end product with PA=x, N is the set of objects possible that can be created from the same irreducible parts within x steps regardless of PA, and NPA is the subset of those objects with the precise pathway assembly index PA=x. Applying this formalism to objects formed in 1D, 2D and 3D space allows us to identify objects in the world or wider Universe that have high assembly numbers. We propose that objects with PA greater than a threshold are important because these are uniquely identifiable as those that must have been produced by biological or technological processes, rather than the assembly occurring via unbiased random processes alone. We think this approach is needed to help identify the new physical and chemical laws needed to understand what life is, by quantifying what life does.
Tasks
Published	2019-07-06
URL	https://arxiv.org/abs/1907.04649v2
PDF	https://arxiv.org/pdf/1907.04649v2.pdf
PWC	https://paperswithcode.com/paper/quantifying-the-pathways-to-life-using
Repo
Framework

Gaussian-Spherical Restricted Boltzmann Machines


Title	Gaussian-Spherical Restricted Boltzmann Machines
Authors	Aurélien Decelle, Cyril Furtlehner
Abstract	We consider a special type of Restricted Boltzmann machine (RBM), namely a Gaussian-spherical RBM where the visible units have Gaussian priors while the vector of hidden variables is constrained to stay on an ${\mathbbm L}_2$ sphere. The spherical constraint having the advantage to admit exact asymptotic treatments, various scaling regimes are explicitly identified based solely on the spectral properties of the coupling matrix (also called weight matrix of the RBM). Incidentally these happen to be formally related to similar scaling behaviours obtained in a different context dealing with spatial condensation of zero range processes. More specifically, when the spectrum of the coupling matrix is doubly degenerated an exact treatment can be proposed to deal with finite size effects. Interestingly the known parallel between the ferromagnetic transition of the spherical model and the Bose-Einstein condensation can be made explicit in that case. More importantly this gives us the ability to extract all needed response functions with arbitrary precision for the training algorithm of the RBM. This allows us then to numerically integrate the dynamics of the spectrum of the weight matrix during learning in a precise way. This dynamics reveals in particular a sequential emergence of modes from the Marchenko-Pastur bulk of singular vectors of the coupling matrix.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14544v1
PDF	https://arxiv.org/pdf/1910.14544v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-spherical-restricted-boltzmann
Repo
Framework

BLOCCS: Block Sparse Canonical Correlation Analysis With Application To Interpretable Omics Integration


Title	BLOCCS: Block Sparse Canonical Correlation Analysis With Application To Interpretable Omics Integration
Authors	Omid Shams Solari, Rojin Safavi, James B. Brown
Abstract	We introduce Block Sparse Canonical Correlation Analysis which estimates multiple pairs of canonical directions (together a “block”) at once, resulting in significantly improved orthogonality of the sparse directions which, we demonstrate, translates to more interpretable solutions. Our approach builds on the sparse CCA method of (Solari, Brown, and Bickel 2019) in that we also express the bi-convex objective of our block formulation as a concave minimization problem over an orthogonal k-frame in a unit Euclidean ball, which in turn, due to concavity of the objective, is shrunk to a Stiefel manifold, which is optimized via gradient descent algorithm. Our simulations show that our method outperforms existing sCCA algorithms and implementations in terms of computational cost and stability, mainly due to the drastic shrinkage of our search space, and the correlation within and orthogonality between pairs of estimated canonical covariates. Finally, we apply our method, available as an R-package called BLOCCS, to multi-omic data on Lung Squamous Cell Carcinoma(LUSC) obtained via The Cancer Genome Atlas, and demonstrate its capability in capturing meaningful biological associations relevant to the hypothesis under study rather than spurious dominant variations.
Tasks
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07944v2
PDF	https://arxiv.org/pdf/1909.07944v2.pdf
PWC	https://paperswithcode.com/paper/bloccs-block-sparse-canonical-correlation
Repo
Framework

Robust Principal Component Analysis Based On Maximum Correntropy Power Iterations


Title	Robust Principal Component Analysis Based On Maximum Correntropy Power Iterations
Authors	Jean P. Chereau, Bruno Scalzo Dees, Danilo P. Mandic
Abstract	Principal component analysis (PCA) is recognised as a quintessential data analysis technique when it comes to describing linear relationships between the features of a dataset. However, the well-known sensitivity of PCA to non-Gaussian samples and/or outliers often makes it unreliable in practice. To this end, a robust formulation of PCA is derived based on the maximum correntropy criterion (MCC) so as to maximise the expected likelihood of Gaussian distributed reconstruction errors. In this way, the proposed solution reduces to a generalised power iteration, whereby: (i) robust estimates of the principal components are obtained even in the presence of outliers; (ii) the number of principal components need not be specified in advance; and (iii) the entire set of principal components can be obtained, unlike existing approaches. The advantages of the proposed maximum correntropy power iteration (MCPI) are demonstrated through an intuitive numerical example.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11374v1
PDF	https://arxiv.org/pdf/1910.11374v1.pdf
PWC	https://paperswithcode.com/paper/robust-principal-component-analysis-based-on
Repo
Framework

Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation


Title	Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation
Authors	Aparna Balagopalan, Jekaterina Novikova, Matthew B. A. McDermott, Bret Nestor, Tristan Naumann, Marzyeh Ghassemi
Abstract	Multi-language speech datasets are scarce and often have small sample sizes in the medical domain. Robust transfer of linguistic features across languages could improve rates of early diagnosis and therapy for speakers of low-resource languages when detecting health conditions from speech. We utilize out-of-domain, unpaired, single-speaker, healthy speech data for training multiple Optimal Transport (OT) domain adaptation systems. We learn mappings from other languages to English and detect aphasia from linguistic characteristics of speech, and show that OT domain adaptation improves aphasia detection over unilingual baselines for French (6% increased F1) and Mandarin (5% increased F1). Further, we show that adding aphasic data to the domain adaptation system significantly increases performance for both French and Mandarin, increasing the F1 scores further (10% and 8% increase in F1 scores for French and Mandarin, respectively, over unilingual baselines).
Tasks	Domain Adaptation
Published	2019-12-04
URL	https://arxiv.org/abs/1912.04370v1
PDF	https://arxiv.org/pdf/1912.04370v1.pdf
PWC	https://paperswithcode.com/paper/191204370
Repo
Framework

A Novel Dual-Lidar Calibration Algorithm Using Planar Surfaces


Title	A Novel Dual-Lidar Calibration Algorithm Using Planar Surfaces
Authors	Jianhao Jiao, Qinghai Liao, Yilong Zhu, Tianyu Liu, Yang Yu, Rui Fan, Lujia Wang, Ming Liu
Abstract	Multiple lidars are prevalently used on mobile vehicles for rendering a broad view to enhance the performance of localization and perception systems. However, precise calibration of multiple lidars is challenging since the feature correspondences in scan points cannot always provide enough constraints. To address this problem, the existing methods require fixed calibration targets in scenes or rely exclusively on additional sensors. In this paper, we present a novel method that enables automatic lidar calibration without these restrictions. Three linearly independent planar surfaces appearing in surroundings is utilized to find correspondences. Two components are developed to ensure the extrinsic parameters to be found: a closed-form solver for initialization and an optimizer for refinement by minimizing a nonlinear cost function. Simulation and experimental results demonstrate the high accuracy of our calibration approach with the rotation and translation errors smaller than 0.05rad and 0.1m respectively.
Tasks	Calibration
Published	2019-04-27
URL	http://arxiv.org/abs/1904.12116v1
PDF	http://arxiv.org/pdf/1904.12116v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-dual-lidar-calibration-algorithm
Repo
Framework