October 18, 2019

2997 words 15 mins read

Paper Group ANR 480

Confidence Intervals for Testing Disparate Impact in Fair Learning. Online Center of Mass Estimation for a Humanoid Wheeled Inverted Pendulum Robot. Modular Materialisation of Datalog Programs. Combined Reinforcement Learning via Abstract Representations. Interactive Generative Adversarial Networks for Facial Expression Generation in Dyadic Interac …

Confidence Intervals for Testing Disparate Impact in Fair Learning


Title	Confidence Intervals for Testing Disparate Impact in Fair Learning
Authors	Philippe Besse, Eustasio del Barrio, Paula Gordaliza, Jean-Michel Loubes
Abstract	We provide the asymptotic distribution of the major indexes used in the statistical literature to quantify disparate treatment in machine learning. We aim at promoting the use of confidence intervals when testing the so-called group disparate impact. We illustrate on some examples the importance of using confidence intervals and not a single value.
Tasks
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06362v1
PDF	http://arxiv.org/pdf/1807.06362v1.pdf
PWC	https://paperswithcode.com/paper/confidence-intervals-for-testing-disparate
Repo
Framework

Online Center of Mass Estimation for a Humanoid Wheeled Inverted Pendulum Robot


Title	Online Center of Mass Estimation for a Humanoid Wheeled Inverted Pendulum Robot
Authors	Munzir Zafar, Akash Patel, Bogdan Vlahov, Nathaniel Glaser, Sergio Aguillera, Seth Hutchinson
Abstract	We present a novel application of robust control and online learning for the balancing of a n Degree of Freedom (DoF), Wheeled Inverted Pendulum (WIP) humanoid robot. Our technique condenses the inaccuracies of a mass model into a Center of Mass (CoM) error, balances despite this error, and uses online learning to update the mass model for a better CoM estimate. Using a simulated model of our robot, we meta-learn a set of excitory joint poses that makes our gradient descent algorithm quickly converge to an accurate (CoM) estimate. This simulated pipeline executes in a fully online fashion, using active disturbance rejection to address the mass errors that result from a steadily evolving mass model. Experiments were performed on a 19 DoF WIP, in which we manually acquired the data for the learned set of poses and show that the mass model produced by a gradient descent produces a CoM estimate that improves overall control and efficiency. This work contributes to a greater corpus of whole body control on the Golem Krang humanoid robot.
Tasks
Published	2018-10-07
URL	https://arxiv.org/abs/1810.03076v2
PDF	https://arxiv.org/pdf/1810.03076v2.pdf
PWC	https://paperswithcode.com/paper/online-center-of-mass-estimation-for-a
Repo
Framework

Modular Materialisation of Datalog Programs


Title	Modular Materialisation of Datalog Programs
Authors	Pan Hu, Boris Motik, Ian Horrocks
Abstract	The semina"ive algorithm can materialise all consequences of arbitrary datalog rules, and it also forms the basis for incremental algorithms that update a materialisation as the input facts change. Certain (combinations of) rules, however, can be handled much more efficiently using custom algorithms. To integrate such algorithms into a general reasoning approach that can handle arbitrary rules, we propose a modular framework for materialisation computation and its maintenance. We split a datalog program into modules that can be handled using specialised algorithms, and handle the remaining rules using the semina"ive algorithm. We also present two algorithms for computing the transitive and the symmetric-transitive closure of a relation that can be used within our framework. Finally, we show empirically that our framework can handle arbitrary datalog programs while outperforming existing approaches, often by orders of magnitude.
Tasks
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02304v2
PDF	http://arxiv.org/pdf/1811.02304v2.pdf
PWC	https://paperswithcode.com/paper/modular-materialisation-of-datalog-programs
Repo
Framework

Combined Reinforcement Learning via Abstract Representations


Title	Combined Reinforcement Learning via Abstract Representations
Authors	Vincent François-Lavet, Yoshua Bengio, Doina Precup, Joelle Pineau
Abstract	In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this paper we propose a new way of explicitly bridging both approaches via a shared low-dimensional learned encoding of the environment, meant to capture summarizing abstractions. We show that the modularity brought by this approach leads to good generalization while being computationally efficient, with planning happening in a smaller latent state space. In addition, this approach recovers a sufficient low-dimensional representation of the environment, which opens up new strategies for interpretable AI, exploration and transfer learning.
Tasks	Transfer Learning
Published	2018-09-12
URL	http://arxiv.org/abs/1809.04506v2
PDF	http://arxiv.org/pdf/1809.04506v2.pdf
PWC	https://paperswithcode.com/paper/combined-reinforcement-learning-via-abstract
Repo
Framework

Interactive Generative Adversarial Networks for Facial Expression Generation in Dyadic Interactions


Title	Interactive Generative Adversarial Networks for Facial Expression Generation in Dyadic Interactions
Authors	Behnaz Nojavanasghari, Yuchi Huang, Saad Khan
Abstract	A social interaction is a social exchange between two or more individuals,where individuals modify and adjust their behaviors in response to their interaction partners. Our social interactions are one of most fundamental aspects of our lives and can profoundly affect our mood, both positively and negatively. With growing interest in virtual reality and avatar-mediated interactions,it is desirable to make these interactions natural and human like to promote positive effect in the interactions and applications such as intelligent tutoring systems, automated interview systems and e-learning. In this paper, we propose a method to generate facial behaviors for an agent. These behaviors include facial expressions and head pose and they are generated considering the users affective state. Our models learn semantically meaningful representations of the face and generate appropriate and temporally smooth facial behaviors in dyadic interactions.
Tasks
Published	2018-01-27
URL	http://arxiv.org/abs/1801.09092v2
PDF	http://arxiv.org/pdf/1801.09092v2.pdf
PWC	https://paperswithcode.com/paper/interactive-generative-adversarial-networks
Repo
Framework

Comparison Based Learning from Weak Oracles


Title	Comparison Based Learning from Weak Oracles
Authors	Ehsan Kazemi, Lin Chen, Sanjoy Dasgupta, Amin Karbasi
Abstract	There is increasing interest in learning algorithms that involve interaction between human and machine. Comparison-based queries are among the most natural ways to get feedback from humans. A challenge in designing comparison-based interactive learning algorithms is coping with noisy answers. The most common fix is to submit a query several times, but this is not applicable in many situations due to its prohibitive cost and due to the unrealistic assumption of independent noise in different repetitions of the same query. In this paper, we introduce a new weak oracle model, where a non-malicious user responds to a pairwise comparison query only when she is quite sure about the answer. This model is able to mimic the behavior of a human in noise-prone regions. We also consider the application of this weak oracle model to the problem of content search (a variant of the nearest neighbor search problem) through comparisons. More specifically, we aim at devising efficient algorithms to locate a target object in a database equipped with a dissimilarity metric via invocation of the weak comparison oracle. We propose two algorithms termed WORCS-I and WORCS-II (Weak-Oracle Comparison-based Search), which provably locate the target object in a number of comparisons close to the entropy of the target distribution. While WORCS-I provides better theoretical guarantees, WORCS-II is applicable to more technically challenging scenarios where the algorithm has limited access to the ranking dissimilarity between objects. A series of experiments validate the performance of our proposed algorithms.
Tasks
Published	2018-02-20
URL	http://arxiv.org/abs/1802.06942v1
PDF	http://arxiv.org/pdf/1802.06942v1.pdf
PWC	https://paperswithcode.com/paper/comparison-based-learning-from-weak-oracles
Repo
Framework

MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation


Title	MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation
Authors	David Keetae Park, Seungjoo Yoo, Hyojin Bahng, Jaegul Choo, Noseong Park
Abstract	Recently, generative adversarial networks (GANs) have shown promising performance in generating realistic images. However, they often struggle in learning complex underlying modalities in a given dataset, resulting in poor-quality generated images. To mitigate this problem, we present a novel approach called mixture of experts GAN (MEGAN), an ensemble approach of multiple generator networks. Each generator network in MEGAN specializes in generating images with a particular subset of modalities, e.g., an image class. Instead of incorporating a separate step of handcrafted clustering of multiple modalities, our proposed model is trained through an end-to-end learning of multiple generators via gating networks, which is responsible for choosing the appropriate generator network for a given condition. We adopt the categorical reparameterization trick for a categorical decision to be made in selecting a generator while maintaining the flow of the gradients. We demonstrate that individual generators learn different and salient subparts of the data and achieve a multiscale structural similarity (MS-SSIM) score of 0.2470 for CelebA and a competitive unsupervised inception score of 8.33 in CIFAR-10.
Tasks	Image Generation
Published	2018-05-07
URL	http://arxiv.org/abs/1805.02481v2
PDF	http://arxiv.org/pdf/1805.02481v2.pdf
PWC	https://paperswithcode.com/paper/megan-mixture-of-experts-of-generative
Repo
Framework

QUEST: Quadriletral Senary bit Pattern for Facial Expression Recognition


Title	QUEST: Quadriletral Senary bit Pattern for Facial Expression Recognition
Authors	Monu Verma, Prafulla Saxena, Santosh. K. Vipparthi, Gridhari Singh
Abstract	Facial expression has a significant role in analyzing human cognitive state. Deriving an accurate facial appearance representation is a critical task for an automatic facial expression recognition application. This paper provides a new feature descriptor named as Quadrilateral Senary bit Pattern for facial expression recognition. The QUEST pattern encoded the intensity changes by emphasizing the relationship between neighboring and reference pixels by dividing them into two quadrilaterals in a local neighborhood. Thus, the resultant gradient edges reveal the transitional variation information, that improves the classification rate by discriminating expression classes. Moreover, it also enhances the capability of the descriptor to deal with viewpoint variations and illumination changes. The trine relationship in a quadrilateral structure helps to extract the expressive edges and suppressing noise elements to enhance the robustness to noisy conditions. The QUEST pattern generates a six-bit compact code, which improves the efficiency of the FER system with more discriminability. The effectiveness of the proposed method is evaluated by conducting several experiments on four benchmark datasets: MMI, GEMEP-FERA, OULU-CASIA, and ISED. The experimental results show better performance of the proposed method as compared to existing state-art-the approaches.
Tasks	Facial Expression Recognition
Published	2018-07-24
URL	http://arxiv.org/abs/1807.09154v1
PDF	http://arxiv.org/pdf/1807.09154v1.pdf
PWC	https://paperswithcode.com/paper/quest-quadriletral-senary-bit-pattern-for
Repo
Framework

Predictive Modeling with Delayed Information: a Case Study in E-commerce Transaction Fraud Control


Title	Predictive Modeling with Delayed Information: a Case Study in E-commerce Transaction Fraud Control
Authors	Junxuan Li, Yung-wen Liu, Yuting Jia, Yifei Ren, Jay Nanduri
Abstract	In Business Intelligence, accurate predictive modeling is the key for providing adaptive decisions. We studied predictive modeling problems in this research which was motivated by real-world cases that Microsoft data scientists encountered while dealing with e-commerce transaction fraud control decisions using transaction streaming data in an uncertain probabilistic decision environment. The values of most online transactions related features can return instantly, while the true fraud labels only return after a stochastic delay. Using partially mature data directly for predictive modeling in an uncertain probabilistic decision environment would lead to significant inaccuracy on risk decision-making. To improve accurate estimation of the probabilistic prediction environment, which leads to more accurate predictive modeling, two frameworks, Current Environment Inference (CEI) and Future Environment Inference (FEI), are proposed. These frameworks generated decision environment related features using long-term fully mature and short-term partially mature data, and the values of those features were estimated using varies of learning methods, including linear regression, random forest, gradient boosted tree, artificial neural network, and recurrent neural network. Performance tests were conducted using some e-commerce transaction data from Microsoft. Testing results suggested that proposed frameworks significantly improved the accuracy of decision environment estimation.
Tasks	Decision Making
Published	2018-11-14
URL	http://arxiv.org/abs/1811.06109v1
PDF	http://arxiv.org/pdf/1811.06109v1.pdf
PWC	https://paperswithcode.com/paper/predictive-modeling-with-delayed-information
Repo
Framework

Online optimal task offloading with one-bit feedback


Title	Online optimal task offloading with one-bit feedback
Authors	Shangshu Zhao, Zhaowei Zhu, Fuqian Yang, Xiliang Luo
Abstract	Task offloading is an emerging technology in fog-enabled networks. It allows users to transmit tasks to neighbor fog nodes so as to utilize the computing resources of the networks. In this paper, we investigate a stochastic task offloading model and propose a multi-armed bandit framework to formulate this model. We consider the fact that different helper nodes prefer different kinds of tasks. Further, we assume each helper node just feeds back one-bit information to the task node to indicate the level of happiness. The key challenge of this problem lies in the exploration-exploitation tradeoff. We thus implement a UCB-type algorithm to maximize the long-term happiness metric. Numerical simulations are given in the end of the paper to corroborate our strategy.
Tasks
Published	2018-06-27
URL	http://arxiv.org/abs/1806.10547v2
PDF	http://arxiv.org/pdf/1806.10547v2.pdf
PWC	https://paperswithcode.com/paper/online-optimal-task-offloading-with-one-bit
Repo
Framework

Multiple-Attribute Text Style Transfer


Title	Multiple-Attribute Text Style Transfer
Authors	Sandeep Subramanian, Guillaume Lample, Eric Michael Smith, Ludovic Denoyer, Marc’Aurelio Ranzato, Y-Lan Boureau
Abstract	The dominant approach to unsupervised “style transfer” in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its “style”. In this paper, we show that this condition is not necessary and is not always met in practice, even with domain adversarial training that explicitly aims at learning such disentangled representations. We thus propose a new model that controls several factors of variation in textual data where this condition on disentanglement is replaced with a simpler mechanism based on back-translation. Our method allows control over multiple attributes, like gender, sentiment, product type, etc., and a more fine-grained control on the trade-off between content preservation and change of style with a pooling operator in the latent space. Our experiments demonstrate that the fully entangled model produces better generations, even when tested on new and more challenging benchmarks comprising reviews with multiple sentences and multiple attributes.
Tasks	Style Transfer, Text Style Transfer
Published	2018-11-01
URL	https://arxiv.org/abs/1811.00552v2
PDF	https://arxiv.org/pdf/1811.00552v2.pdf
PWC	https://paperswithcode.com/paper/multiple-attribute-text-style-transfer
Repo
Framework

A Sequence-to-Sequence Model for Semantic Role Labeling


Title	A Sequence-to-Sequence Model for Semantic Role Labeling
Authors	Angel Daza, Anette Frank
Abstract	We explore a novel approach for Semantic Role Labeling (SRL) by casting it as a sequence-to-sequence process. We employ an attention-based model enriched with a copying mechanism to ensure faithful regeneration of the input sequence, while enabling interleaved generation of argument role labels. Here, we apply this model in a monolingual setting, performing PropBank SRL on English language data. The constrained sequence generation set-up enforced with the copying mechanism allows us to analyze the performance and special properties of the model on manually labeled data and benchmarking against state-of-the-art sequence labeling models. We show that our model is able to solve the SRL argument labeling task on English data, yet further structural decoding constraints will need to be added to make the model truly competitive. Our work represents a first step towards more advanced, generative SRL labeling setups.
Tasks	Semantic Role Labeling
Published	2018-07-09
URL	http://arxiv.org/abs/1807.03006v1
PDF	http://arxiv.org/pdf/1807.03006v1.pdf
PWC	https://paperswithcode.com/paper/a-sequence-to-sequence-model-for-semantic
Repo
Framework

An Adaptive Oversampling Learning Method for Class-Imbalanced Fault Diagnostics and Prognostics


Title	An Adaptive Oversampling Learning Method for Class-Imbalanced Fault Diagnostics and Prognostics
Authors	Wenfang Lin, Zhenyu Wu, Yang Ji
Abstract	Data-driven fault diagnostics and prognostics suffers from class-imbalance problem in industrial systems and it raises challenges to common machine learning algorithms as it becomes difficult to learn the features of the minority class samples. Synthetic oversampling methods are commonly used to tackle these problems by generating the minority class samples to balance the distributions between majority and minority classes. However, many of oversampling methods are inappropriate that they cannot generate effective and useful minority class samples according to different distributions of data, which further complicate the process of learning samples. Thus, this paper proposes a novel adaptive oversampling technique: EM-based Weighted Minority Oversampling TEchnique (EWMOTE) for industrial fault diagnostics and prognostics. The methods comprises a weighted minority sampling strategy to identify hard-to-learn informative minority fault samples and Expectation Maximization (EM) based imputation algorithm to generate fault samples. To validate the performance of the proposed methods, experiments are conducted in two real datasets. The results show that the method could achieve better performance on not only binary class, but multi-class imbalance learning task in different imbalance ratios than other oversampling-based baseline models.
Tasks	Imputation
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07674v1
PDF	http://arxiv.org/pdf/1811.07674v1.pdf
PWC	https://paperswithcode.com/paper/an-adaptive-oversampling-learning-method-for
Repo
Framework

A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification


Title	A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification
Authors	Bin Wang, Yanan Sun, Bing Xue, Mengjie Zhang
Abstract	Convolutional Neural Networks (CNNs) have demonstrated their superiority in image classification, and evolutionary computation (EC) methods have recently been surging to automatically design the architectures of CNNs to save the tedious work of manually designing CNNs. In this paper, a new hybrid differential evolution (DE) algorithm with a newly added crossover operator is proposed to evolve the architectures of CNNs of any lengths, which is named DECNN. There are three new ideas in the proposed DECNN method. Firstly, an existing effective encoding scheme is refined to cater for variable-length CNN architectures; Secondly, the new mutation and crossover operators are developed for variable-length DE to optimise the hyperparameters of CNNs; Finally, the new second crossover is introduced to evolve the depth of the CNN architectures. The proposed algorithm is tested on six widely-used benchmark datasets and the results are compared to 12 state-of-the-art methods, which shows the proposed method is vigorously competitive to the state-of-the-art algorithms. Furthermore, the proposed method is also compared with a method using particle swarm optimisation with a similar encoding strategy named IPPSO, and the proposed DECNN outperforms IPPSO in terms of the accuracy.
Tasks	Image Classification
Published	2018-08-20
URL	http://arxiv.org/abs/1808.06661v2
PDF	http://arxiv.org/pdf/1808.06661v2.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-differential-evolution-approach-to
Repo
Framework

Tackling Early Sparse Gradients in Softmax Activation Using Leaky Squared Euclidean Distance


Title	Tackling Early Sparse Gradients in Softmax Activation Using Leaky Squared Euclidean Distance
Authors	Wei Shen, Rujie Liu
Abstract	Softmax activation is commonly used to output the probability distribution over categories based on certain distance metric. In scenarios like one-shot learning, the distance metric is often chosen to be squared Euclidean distance between the query sample and the category prototype. This practice works well in most time. However, we find that choosing squared Euclidean distance may cause distance explosion leading gradients to be extremely sparse in the early stage of back propagation. We term this phenomena as the early sparse gradients problem. Though it doesn’t deteriorate the convergence of the model, it may set up a barrier to further model improvement. To tackle this problem, we propose to use leaky squared Euclidean distance to impose a restriction on distances. In this way, we can avoid distance explosion and increase the magnitude of gradients. Extensive experiments are conducted on Omniglot and miniImageNet datasets. We show that using leaky squared Euclidean distance can improve one-shot classification accuracy on both datasets.
Tasks	Omniglot, One-Shot Learning
Published	2018-11-27
URL	http://arxiv.org/abs/1811.10779v1
PDF	http://arxiv.org/pdf/1811.10779v1.pdf
PWC	https://paperswithcode.com/paper/tackling-early-sparse-gradients-in-softmax
Repo
Framework