April 2, 2020

3523 words 17 mins read

Paper Group ANR 155

Paper Group ANR 155

Foreground model recognition through Neural Networks for CMB B-mode observations. Exploring User Opinions of Fairness in Recommender Systems. Fair Correlation Clustering. Constrained Upper Confidence Reinforcement Learning. Learning Diverse Fashion Collocation by Neural Graph Filtering. Prior Knowledge Driven Label Embedding for Slot Filling in Nat …

Foreground model recognition through Neural Networks for CMB B-mode observations

Title Foreground model recognition through Neural Networks for CMB B-mode observations
Authors Farida Farsian, Nicoletta Krachmalnicoff, Carlo Baccigalupi
Abstract In this work we present a Neural Network (NN) algorithm for the identification of the appropriate parametrization of diffuse polarized Galactic emissions in the context of Cosmic Microwave Background (CMB) $B$-mode multi-frequency observations. In particular, we have focused our analysis on low frequency foregrounds relevant for polarization observation: namely Galactic Synchrotron and Anomalous Microwave Emission (AME). We have implemented and tested our approach on a set of simulated maps corresponding to the frequency coverage and sensitivity represented by future satellite and low frequency ground based probes. The NN efficiency in recognizing the right parametrization of foreground emission in different sky regions reaches an accuracy of about $90%$. We have compared this performance with the $\chi^{2}$ information following parametric foreground estimation using multi-frequency fitting, and quantify the gain provided by a NN approach. Our results show the relevance of model recognition in CMB $B$-mode observations, and highlight the exploitation of dedicated procedures to this purpose.
Published 2020-03-04
URL https://arxiv.org/abs/2003.02278v1
PDF https://arxiv.org/pdf/2003.02278v1.pdf
PWC https://paperswithcode.com/paper/foreground-model-recognition-through-neural

Exploring User Opinions of Fairness in Recommender Systems

Title Exploring User Opinions of Fairness in Recommender Systems
Authors Jessie Smith, Nasim Sonboli, Casey Fiesler, Robin Burke
Abstract Algorithmic fairness for artificial intelligence has become increasingly relevant as these systems become more pervasive in society. One realm of AI, recommender systems, presents unique challenges for fairness due to trade offs between optimizing accuracy for users and fairness to providers. But what is fair in the context of recommendation–particularly when there are multiple stakeholders? In an initial exploration of this problem, we ask users what their ideas of fair treatment in recommendation might be, and why. We analyze what might cause discrepancies or changes between user’s opinions towards fairness to eventually help inform the design of fairer and more transparent recommendation algorithms.
Tasks Recommendation Systems
Published 2020-03-13
URL https://arxiv.org/abs/2003.06461v1
PDF https://arxiv.org/pdf/2003.06461v1.pdf
PWC https://paperswithcode.com/paper/exploring-user-opinions-of-fairness-in

Fair Correlation Clustering

Title Fair Correlation Clustering
Authors Saba Ahmadi, Sainyam Galhotra, Barna Saha, Roy Schwartz
Abstract In this paper we study the problem of correlation clustering under fairness constraints. In the classic correlation clustering problem, we are given a complete graph where each edge is labeled positive or negative. The goal is to obtain a clustering of the vertices that minimizes disagreements – the number of negative edges trapped inside a cluster plus positive edges between different clusters. We consider two variations of fairness constraint for the problem of correlation clustering where each node has a color, and the goal is to form clusters that do not over-represent vertices of any color. The first variant aims to generate clusters with minimum disagreements, where the distribution of a feature (e.g. gender) in each cluster is same as the global distribution. For the case of two colors when the desired ratio of the number of colors in each cluster is $1:p$, we get $\mathcal{O}(p^2)$-approximation algorithm. Our algorithm could be extended to the case of multiple colors. We prove this problem is NP-hard. The second variant considers relative upper and lower bounds on the number of nodes of any color in a cluster. The goal is to avoid violating upper and lower bounds corresponding to each color in each cluster while minimizing the total number of disagreements. Along with our theoretical results, we show the effectiveness of our algorithm to generate fair clusters by empirical evaluation on real world data sets.
Published 2020-02-10
URL https://arxiv.org/abs/2002.03508v1
PDF https://arxiv.org/pdf/2002.03508v1.pdf
PWC https://paperswithcode.com/paper/fair-correlation-clustering-1

Constrained Upper Confidence Reinforcement Learning

Title Constrained Upper Confidence Reinforcement Learning
Authors Liyuan Zheng, Lillian J. Ratliff
Abstract Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints. This paper extends upper confidence reinforcement learning for settings in which the reward function and the constraints, described by cost functions, are unknown a priori but the transition kernel is known. Such a setting is well-motivated by a number of applications including exploration of unknown, potentially unsafe, environments. We present an algorithm C-UCRL and show that it achieves sub-linear regret ($ O(T^{\frac{3}{4}}\sqrt{\log(T/\delta)})$) with respect to the reward while satisfying the constraints even while learning with probability $1-\delta$. Illustrative examples are provided.
Published 2020-01-26
URL https://arxiv.org/abs/2001.09377v1
PDF https://arxiv.org/pdf/2001.09377v1.pdf
PWC https://paperswithcode.com/paper/constrained-upper-confidence-reinforcement

Learning Diverse Fashion Collocation by Neural Graph Filtering

Title Learning Diverse Fashion Collocation by Neural Graph Filtering
Authors Xin Liu, Yongbin Sun, Ziwei Liu, Dahua Lin
Abstract Fashion recommendation systems are highly desired by customers to find visually-collocated fashion items, such as clothes, shoes, bags, etc. While existing methods demonstrate promising results, they remain lacking in flexibility and diversity, e.g. assuming a fixed number of items or favoring safe but boring recommendations. In this paper, we propose a novel fashion collocation framework, Neural Graph Filtering, that models a flexible set of fashion items via a graph neural network. Specifically, we consider the visual embeddings of each garment as a node in the graph, and describe the inter-garment relationship as the edge between nodes. By applying symmetric operations on the edge vectors, this framework allows varying numbers of inputs/outputs and is invariant to their ordering. We further include a style classifier augmented with focal loss to enable the collocation of significantly diverse styles, which are inherently imbalanced in the training set. To facilitate a comprehensive study on diverse fashion collocation, we reorganize Amazon Fashion dataset with carefully designed evaluation protocols. We evaluate the proposed approach on three popular benchmarks, the Polyvore dataset, the Polyvore-D dataset, and our reorganized Amazon Fashion dataset. Extensive experimental results show that our approach significantly outperforms the state-of-the-art methods with over 10% improvements on the standard AUC metric on the established tasks. More importantly, 82.5% of the users prefer our diverse-style recommendations over other alternatives in a real-world perception study.
Tasks Recommendation Systems
Published 2020-03-11
URL https://arxiv.org/abs/2003.04888v1
PDF https://arxiv.org/pdf/2003.04888v1.pdf
PWC https://paperswithcode.com/paper/learning-diverse-fashion-collocation-by

Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding

Title Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
Authors Su Zhu, Zijian Zhao, Rao Ma, Kai Yu
Abstract Traditional slot filling in natural language understanding (NLU) predicts a one-hot vector for each word. This form of label representation lacks semantic correlation modelling, which leads to severe data sparsity problem, especially when adapting an NLU model to a new domain. To address this issue, a novel label embedding based slot filling framework is proposed in this paper. Here, distributed label embedding is constructed for each slot using prior knowledge. Three encoding methods are investigated to incorporate different kinds of prior knowledge about slots: atomic concepts, slot descriptions, and slot exemplars. The proposed label embeddings tend to share text patterns and reuses data with different slot labels. This makes it useful for adaptive NLU with limited data. Also, since label embedding is independent of NLU model, it is compatible with almost all deep learning based slot filling models. The proposed approaches are evaluated on three datasets. Experiments on single domain and domain adaptation tasks show that label embedding achieves significant performance improvement over traditional one-hot label representation as well as advanced zero-shot approaches.
Tasks Domain Adaptation, Slot Filling
Published 2020-03-22
URL https://arxiv.org/abs/2003.09831v1
PDF https://arxiv.org/pdf/2003.09831v1.pdf
PWC https://paperswithcode.com/paper/prior-knowledge-driven-label-embedding-for

Price-aware Recommendation with Graph Convolutional Networks

Title Price-aware Recommendation with Graph Convolutional Networks
Authors Yu Zheng, Chen Gao, Xiangnan He, Yong Li, Depeng Jin
Abstract In recent years, much research effort on recommendation has been devoted to mining user behaviors, i.e., collaborative filtering, along with the general information which describes users or items, e.g., textual attributes, categorical demographics, product images, and so on. Price, an important factor in marketing — which determines whether a user will make the final purchase decision on an item — surprisingly, has received relatively little scrutiny. In this work, we aim at developing an effective method to predict user purchase intention with the focus on the price factor in recommender systems. The main difficulties are two-fold: 1) the preference and sensitivity of a user on item price are unknown, which are only implicitly reflected in the items that the user has purchased, and 2) how the item price affects a user’s intention depends largely on the product category, that is, the perception and affordability of a user on item price could vary significantly across categories. Towards the first difficulty, we propose to model the transitive relationship between user-to-item and item-to-price, taking the inspiration from the recently developed Graph Convolution Networks (GCN). The key idea is to propagate the influence of price on users with items as the bridge, so as to make the learned user representations be price-aware. For the second difficulty, we further integrate item categories into the propagation progress and model the possible pairwise interactions for predicting user-item interactions. We conduct extensive experiments on two real-world datasets, demonstrating the effectiveness of our GCN-based method in learning the price-aware preference of users. Further analysis reveals that modeling the price awareness is particularly useful for predicting user preference on items of unexplored categories.
Tasks Recommendation Systems
Published 2020-03-09
URL https://arxiv.org/abs/2003.03975v1
PDF https://arxiv.org/pdf/2003.03975v1.pdf
PWC https://paperswithcode.com/paper/price-aware-recommendation-with-graph

Subsampling Winner Algorithm for Feature Selection in Large Regression Data

Title Subsampling Winner Algorithm for Feature Selection in Large Regression Data
Authors Yiying Fan, Jiayang Sun
Abstract Feature selection from a large number of covariates (aka features) in a regression analysis remains a challenge in data science, especially in terms of its potential of scaling to ever-enlarging data and finding a group of scientifically meaningful features. For example, to develop new, responsive drug targets for ovarian cancer, the actual false discovery rate (FDR) of a practical feature selection procedure must also match the target FDR. The popular approach to feature selection, when true features are sparse, is to use a penalized likelihood or a shrinkage estimation, such as a LASSO, SCAD, Elastic Net, or MCP procedure (call them benchmark procedures). We present a different approach using a new subsampling method, called the Subsampling Winner algorithm (SWA). The central idea of SWA is analogous to that used for the selection of US national merit scholars. SWA uses a “base procedure” to analyze each of the subsamples, computes the scores of all features according to the performance of each feature from all subsample analyses, obtains the “semifinalist” based on the resulting scores, and then determines the “finalists,” i.e., the most important features. Due to its subsampling nature, SWA can scale to data of any dimension in principle. The SWA also has the best-controlled actual FDR in comparison with the benchmark procedures and the randomForest, while having a competitive true-feature discovery rate. We also suggest practical add-on strategies to SWA with or without a penalized benchmark procedure to further assure the chance of “true” discovery. Our application of SWA to the ovarian serous cystadenocarcinoma specimens from the Broad Institute revealed functionally important genes and pathways, which we verified by additional genomics tools. This second-stage investigation is essential in the current discussion of the proper use of P-values.
Tasks Feature Selection
Published 2020-02-07
URL https://arxiv.org/abs/2002.02903v1
PDF https://arxiv.org/pdf/2002.02903v1.pdf
PWC https://paperswithcode.com/paper/subsampling-winner-algorithm-for-feature

Stein Variational Inference for Discrete Distributions

Title Stein Variational Inference for Discrete Distributions
Authors Jun Han, Fan Ding, Xianglong Liu, Lorenzo Torresani, Jian Peng, Qiang Liu
Abstract Gradient-based approximate inference methods, such as Stein variational gradient descent (SVGD), provide simple and general-purpose inference engines for differentiable continuous distributions. However, existing forms of SVGD cannot be directly applied to discrete distributions. In this work, we fill this gap by proposing a simple yet general framework that transforms discrete distributions to equivalent piecewise continuous distributions, on which the gradient-free SVGD is applied to perform efficient approximate inference. The empirical results show that our method outperforms traditional algorithms such as Gibbs sampling and discontinuous Hamiltonian Monte Carlo on various challenging benchmarks of discrete graphical models. We demonstrate that our method provides a promising tool for learning ensembles of binarized neural network (BNN), outperforming other widely used ensemble methods on learning binarized AlexNet on CIFAR-10 dataset. In addition, such transform can be straightforwardly employed in gradient-free kernelized Stein discrepancy to perform goodness-of-fit (GOF) test on discrete distributions. Our proposed method outperforms existing GOF test methods for intractable discrete distributions.
Published 2020-03-01
URL https://arxiv.org/abs/2003.00605v1
PDF https://arxiv.org/pdf/2003.00605v1.pdf
PWC https://paperswithcode.com/paper/stein-variational-inference-for-discrete

Effect of Analysis Window and Feature Selection on Classification of Hand Movements Using EMG Signal

Title Effect of Analysis Window and Feature Selection on Classification of Hand Movements Using EMG Signal
Authors Asad Ullah, Sarwan Ali, Imdadullah Khan, Muhammad Asad Khan, Safiullah Faizullah
Abstract Electromyography (EMG) signals have been successfully employed for driving prosthetic limbs of a single or double degree of freedom. This principle works by using the amplitude of the EMG signals to decide between one or two simpler movements. This method underperforms as compare to the contemporary advances done at the mechanical, electronics, and robotics end, and it lacks intuition. Recently, research on myoelectric control based on pattern recognition (PR) shows promising results with the aid of machine learning classifiers. Using the approach termed as, EMG-PR, EMG signals are divided into analysis windows, and features are extracted for each window. These features are then fed to the machine learning classifiers as input. By offering multiple class movements and intuitive control, this method has the potential to power an amputated subject to perform everyday life movements. In this paper, we investigate the effect of the analysis window and feature selection on classification accuracy of different hand and wrist movements using time-domain features. We show that effective data preprocessing and optimum feature selection helps to improve the classification accuracy of hand movements. We use publicly available hand and wrist gesture dataset of $40$ intact subjects for experimentation. Results computed using different classification algorithms show that the proposed preprocessing and features selection outperforms the baseline and achieve up to $98%$ classification accuracy.
Tasks Electromyography (EMG), Feature Selection
Published 2020-02-02
URL https://arxiv.org/abs/2002.00461v3
PDF https://arxiv.org/pdf/2002.00461v3.pdf
PWC https://paperswithcode.com/paper/effect-of-analysis-window-and-feature

From IC Layout to Die Photo: A CNN-Based Data-Driven Approach

Title From IC Layout to Die Photo: A CNN-Based Data-Driven Approach
Authors Hao-Chiang Shao, Chao-Yi Peng, Jun-Rei Wu, Chia-Wen Lin, Shao-Yun Fang, Pin-Yen Tsai, Yan-Hsiu Liu
Abstract Since IC fabrication is costly and time-consuming, it is highly desirable to develop virtual metrology tools that can predict the properties of a wafer based on fabrication configurations without performing physical measurements on a fabricated IC. We propose a deep learning-based data-driven framework consisting of two convolutional neural networks: i) LithoNet that predicts the shape deformations on a circuit due to IC fabrication, and ii) OPCNet that suggests IC layout corrections to compensate for such shape deformations. By learning the shape correspondence between pairs of layout design patterns and their SEM images of the product wafer thereof, given an IC layout pattern, LithoNet can mimic the fabrication procedure to predict its fabricated circuit shape for virtual metrology. Furthermore, LithoNet can take the wafer fabrication parameters as a latent vector to model the parametric product variations that can be inspected on SEM images. In addition, traditional lithography simulation methods used to suggest a correction on a lithographic photomask is computationally expensive. Our proposed OPCNet mimics the optical proximity correction (OPC) procedure and efficiently generates a corrected photomask by collaborating with LithoNet to examine if the shape of a fabricated IC circuitry best matches its original layout design. As a result, the proposed LithoNet-OPCNet framework cannot only predict the shape of a fabricated IC from its layout pattern, but also suggests a layout correction according to the consistency between the predicted shape and the given layout. Experimental results with several benchmark layout patterns demonstrate the effectiveness of the proposed method.
Published 2020-02-11
URL https://arxiv.org/abs/2002.04967v1
PDF https://arxiv.org/pdf/2002.04967v1.pdf
PWC https://paperswithcode.com/paper/from-ic-layout-to-die-photo-a-cnn-based-data

A Hybrid Two-layer Feature Selection Method Using GeneticAlgorithm and Elastic Net

Title A Hybrid Two-layer Feature Selection Method Using GeneticAlgorithm and Elastic Net
Authors Fatemeh Amini, Guiping Hu
Abstract Feature selection, as a critical pre-processing step for machine learning, aims at determining representative predictors from a high-dimensional feature space dataset to improve the prediction accuracy. However, the increase in feature space dimensionality, comparing to the number of observations, poses a severe challenge to many existing feature selection methods with respect to computational efficiency and prediction performance. This paper presents a new hybrid two-layer feature selection approach that combines a wrapper and an embedded method in constructing an appropriate subset of predictors. In the first layer of the proposed method, the Genetic Algorithm(GA) has been adopted as a wrapper to search for the optimal subset of predictors, which aims to reduce the number of predictors and the prediction error. As one of the meta-heuristic approaches, GA is selected due to its computational efficiency; however, GAs do not guarantee the optimality. To address this issue, a second layer is added to the proposed method to eliminate any remaining redundant/irrelevant predictors to improve the prediction accuracy. Elastic Net(EN) has been selected as the embedded method in the second layer because of its flexibility in adjusting the penalty terms in regularization process and time efficiency. This hybrid two-layer approach has been applied on a Maize genetic dataset from NAM population, which consists of multiple subsets of datasets with different ratio of the number of predictors to the number of observations. The numerical results confirm the superiority of the proposed model.
Tasks Feature Selection
Published 2020-01-30
URL https://arxiv.org/abs/2001.11177v1
PDF https://arxiv.org/pdf/2001.11177v1.pdf
PWC https://paperswithcode.com/paper/a-hybrid-two-layer-feature-selection-method

Assistive Relative Pose Estimation for On-orbit Assembly using Convolutional Neural Networks

Title Assistive Relative Pose Estimation for On-orbit Assembly using Convolutional Neural Networks
Authors Shubham Sonawani, Ryan Alimo, Renaud Detry, Daniel Jeong, Andrew Hess, Heni Ben Amor
Abstract Accurate real-time pose estimation of spacecraft or object in space is a key capability necessary for on-orbit spacecraft servicing and assembly tasks. Pose estimation of objects in space is more challenging than for objects on Earth due to space images containing widely varying illumination conditions, high contrast, and poor resolution in addition to power and mass constraints. In this paper, a convolutional neural network is leveraged to uniquely determine the translation and rotation of an object of interest relative to the camera. The main idea of using CNN model is to assist object tracker used in on space assembly tasks where only feature based method is always not sufficient. The simulation framework designed for assembly task is used to generate dataset for training the modified CNN models and, then results of different models are compared with measure of how accurately models are predicting the pose. Unlike many current approaches for spacecraft or object in space pose estimation, the model does not rely on hand-crafted object-specific features which makes this model more robust and easier to apply to other types of spacecraft. It is shown that the model performs comparable to the current feature-selection methods and can therefore be used in conjunction with them to provide more reliable estimates.
Tasks Feature Selection, Pose Estimation
Published 2020-01-29
URL https://arxiv.org/abs/2001.10673v2
PDF https://arxiv.org/pdf/2001.10673v2.pdf
PWC https://paperswithcode.com/paper/assistive-relative-pose-estimation-for-on

Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods

Title Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods
Authors Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci
Abstract We provide an exact analysis of the limiting spectrum of matrices randomly projected either with the subsampled randomized Hadamard transform, or truncated Haar matrices. We characterize this limiting distribution through its Stieltjes transform, a classical object in random matrix theory, and compute the first and second inverse moments. We leverage the limiting spectrum and asymptotic freeness of random matrices to obtain an exact analysis of iterative sketching methods for solving least squares problems. Our results also yield optimal step-sizes and convergence rates in terms of simple closed-form expressions. Moreover, we show that the convergence rate for Haar and randomized Hadamard matrices are identical, and uniformly improve upon Gaussian random projections. The developed techniques and formulas can be applied to a plethora of randomized algorithms that employ fast randomized Hadamard dimension reduction.
Tasks Dimensionality Reduction
Published 2020-02-03
URL https://arxiv.org/abs/2002.00864v2
PDF https://arxiv.org/pdf/2002.00864v2.pdf
PWC https://paperswithcode.com/paper/limiting-spectrum-of-randomized-hadamard

Learning of signaling networks: molecular mechanisms

Title Learning of signaling networks: molecular mechanisms
Authors Péter Csermely, Nina Kunsic, Péter Mendik, Márk Kerestély, Teodóra Faragó, Dániel V. Veres, Péter Tompa
Abstract Molecular processes of neuronal learning have been well-described. However, learning mechanisms of non-neuronal cells have not been fully understood at the molecular level. Here, we discuss molecular mechanisms of cellular learning, including conformational memory of intrinsically disordered proteins and prions, signaling cascades, protein translocation, RNAs (microRNA and lncRNA), and chromatin memory. We hypothesize that these processes constitute the learning of signaling networks and correspond to a generalized Hebbian learning process of single, non-neuronal cells, and discuss how cellular learning may open novel directions in drug design and inspire new artificial intelligence methods.
Published 2020-01-31
URL https://arxiv.org/abs/2001.11679v2
PDF https://arxiv.org/pdf/2001.11679v2.pdf
PWC https://paperswithcode.com/paper/learning-of-signaling-networks-molecular
comments powered by Disqus