April 2, 2020

3251 words 16 mins read

Paper Group ANR 284

Binary Probability Model for Learning Based Image Compression. Hierarchical Quantized Autoencoders. Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform. Federated Learning for Localization: A Privacy-Preserving Crowdsourcing Method. REAK: Reliability analysis through Error rate-based Adaptive Kriging. Sequential Neura …

Binary Probability Model for Learning Based Image Compression


Title	Binary Probability Model for Learning Based Image Compression
Authors	Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Deforges
Abstract	In this paper, we propose to enhance learned image compression systems with a richer probability model for the latent variables. Previous works model the latents with a Gaussian or a Laplace distribution. Inspired by binary arithmetic coding , we propose to signal the latents with three binary values and one integer, with different probability models. A relaxation method is designed to perform gradient-based training. The richer probability model results in a better entropy coding leading to lower rate. Experiments under the Challenge on Learned Image Compression (CLIC) test conditions demonstrate that this method achieves 18% rate saving compared to Gaussian or Laplace models.
Tasks	Image Compression
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09259v1
PDF	https://arxiv.org/pdf/2002.09259v1.pdf
PWC	https://paperswithcode.com/paper/binary-probability-model-for-learning-based
Repo
Framework

Hierarchical Quantized Autoencoders


Title	Hierarchical Quantized Autoencoders
Authors	Will Williams, Sam Ringer, Tom Ash, John Hughes, David MacLeod, Jamie Dougherty
Abstract	Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and high-level features at very low bitrates. Encouraged by recent success in learning discrete representations with Vector Quantized Variational AutoEncoders (VQ-VAEs), we motivate the use of a hierarchy of VQ-VAEs to attain high factors of compression. We show that the combination of quantization and hierarchical latent structure aids likelihood-based image compression. This leads us to introduce a more probabilistic framing of the VQ-VAE, of which previous work is a limiting case. Our hierarchy produces a Markovian series of latent variables that reconstruct high-quality images which retain semantically meaningful features. These latents can then be further used to generate realistic samples. We provide qualitative and quantitative evaluations of reconstructions and samples on the CelebA and MNIST datasets.
Tasks	Image Compression, Quantization
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08111v1
PDF	https://arxiv.org/pdf/2002.08111v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-quantized-autoencoders
Repo
Framework

Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform


Title	Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform
Authors	Jun Li, Li Fuxin, Sinisa Todorovic
Abstract	Strictly enforcing orthonormality constraints on parameter matrices has been shown advantageous in deep learning. This amounts to Riemannian optimization on the Stiefel manifold, which, however, is computationally expensive. To address this challenge, we present two main contributions: (1) A new efficient retraction map based on an iterative Cayley transform for optimization updates, and (2) An implicit vector transport mechanism based on the combination of a projection of the momentum and the Cayley transform on the Stiefel manifold. We specify two new optimization algorithms: Cayley SGD with momentum, and Cayley ADAM on the Stiefel manifold. Convergence of Cayley SGD is theoretically analyzed. Our experiments for CNN training demonstrate that both algorithms: (a) Use less running time per iteration relative to existing approaches that enforce orthonormality of CNN parameters; and (b) Achieve faster convergence rates than the baseline SGD and ADAM algorithms without compromising the performance of the CNN. Cayley SGD and Cayley ADAM are also shown to reduce the training time for optimizing the unitary transition matrices in RNNs.
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01113v1
PDF	https://arxiv.org/pdf/2002.01113v1.pdf
PWC	https://paperswithcode.com/paper/efficient-riemannian-optimization-on-the-1
Repo
Framework

Federated Learning for Localization: A Privacy-Preserving Crowdsourcing Method


Title	Federated Learning for Localization: A Privacy-Preserving Crowdsourcing Method
Authors	Bekir Sait Ciftler, Abdullatif Albaseer, Noureddine Lasla, Mohamed Abdallah
Abstract	Received Signal Strength (RSS) fingerprint-based localization has attracted a lot of research effort and cultivated many commercial applications of location-based services due to its low cost and ease of implementation. Many studies are exploring the use of deep learning (DL) algorithms for localization. DL’s ability to extract features and to classify autonomously makes it an attractive solution for fingerprint-based localization. These solutions require frequent retraining of DL models with vast amounts of measurements. Although crowdsourcing is an excellent way to gather immense amounts of data, it jeopardizes the privacy of participants, as it requires to collect labeled data at a centralized server. Recently, federated learning has emerged as a practical concept in solving the privacy preservation issue of crowdsourcing participants by performing model training at the edge devices in a decentralized manner; the participants do not expose their data anymore to a centralized server. This paper presents a novel method utilizing federated learning to improve the accuracy of RSS fingerprint-based localization while preserving the privacy of the crowdsourcing participants. Employing federated learning allows ensuring \emph{preserving the privacy of user data} while enabling an adequate localization performance with experimental data captured in real-world settings. The proposed method improved localization accuracy by 1.8 meters when used as a booster for centralized learning and achieved satisfactory localization accuracy when used standalone.
Tasks
Published	2020-01-07
URL	https://arxiv.org/abs/2001.01911v2
PDF	https://arxiv.org/pdf/2001.01911v2.pdf
PWC	https://paperswithcode.com/paper/federated-learning-for-localization-a-privacy
Repo
Framework

REAK: Reliability analysis through Error rate-based Adaptive Kriging


Title	REAK: Reliability analysis through Error rate-based Adaptive Kriging
Authors	Zeyu Wang, Abdollah Shafieezadeh
Abstract	As models in various fields are becoming more complex, associated computational demands have been increasing significantly. Reliability analysis for these systems when failure probabilities are small is significantly challenging, requiring a large number of costly simulations. To address this challenge, this paper introduces Reliability analysis through Error rate-based Adaptive Kriging (REAK). An extension of the Central Limit Theorem based on Lindeberg condition is adopted here to derive the distribution of the number of design samples with wrong sign estimate and subsequently determine the maximum error rate for failure probability estimates. This error rate enables optimal establishment of effective sampling regions at each stage of an adaptive scheme for strategic generation of design samples. Moreover, it facilitates setting a target accuracy for failure probability estimation, which is used as stopping criterion for reliability analysis. These capabilities together can significantly reduce the number of calls to sophisticated, computationally demanding models. The application of REAK for four examples with varying extent of nonlinearity and dimension is presented. Results indicate that REAK is able to reduce the computational demand by as high as 50% compared to state-of-the-art methods of Adaptive Kriging with Monte Carlo Simulation (AK-MCS) and Improved Sequential Kriging Reliability Analysis (ISKRA).
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01110v1
PDF	https://arxiv.org/pdf/2002.01110v1.pdf
PWC	https://paperswithcode.com/paper/reak-reliability-analysis-through-error-rate
Repo
Framework

Sequential Neural Networks for Noetic End-to-End Response Selection


Title	Sequential Neural Networks for Noetic End-to-End Response Selection
Authors	Qian Chen, Wen Wang
Abstract	The noetic end-to-end response selection challenge as one track in the 7th Dialog System Technology Challenges (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context. This paper presents our systems that are ranked top 1 on both datasets under this challenge, one focused and small (Advising) and the other more diverse and large (Ubuntu). Previous state-of-the-art models use hierarchy-based (utterance-level and token-level) neural networks to explicitly model the interactions among different turns’ utterances for context modeling. In this paper, we investigate a sequential matching model based only on chain sequence for multi-turn response selection. Our results demonstrate that the potentials of sequential matching approaches have not yet been fully exploited in the past for multi-turn response selection. In addition to ranking top 1 in the challenge, the proposed model outperforms all previous models, including state-of-the-art hierarchy-based models, on two large-scale public multi-turn response selection benchmark datasets.
Tasks	Goal-Oriented Dialog
Published	2020-03-03
URL	https://arxiv.org/abs/2003.02126v1
PDF	https://arxiv.org/pdf/2003.02126v1.pdf
PWC	https://paperswithcode.com/paper/sequential-neural-networks-for-noetic-end-to
Repo
Framework

Catch the Ball: Accurate High-Speed Motions for Mobile Manipulators via Inverse Dynamics Learning


Title	Catch the Ball: Accurate High-Speed Motions for Mobile Manipulators via Inverse Dynamics Learning
Authors	Ke Dong, Karime Pereida, Florian Shkurti, Angela P. Schoellig
Abstract	Mobile manipulators consist of a mobile platform equipped with one or more robot arms and are of interest for a wide array of challenging tasks because of their extended workspace and dexterity. Typically, mobile manipulators are deployed in slow-motion collaborative robot scenarios. In this paper, we consider scenarios where accurate high-speed motions are required. We introduce a framework for this regime of tasks including two main components: (i) a bi-level motion optimization algorithm for real-time trajectory generation, which relies on Sequential Quadratic Programming (SQP) and Quadratic Programming (QP), respectively; and (ii) a learning-based controller optimized for precise tracking of high-speed motions via a learned inverse dynamics model. We evaluate our framework with a mobile manipulator platform through numerous high-speed ball catching experiments, where we show a success rate of 85.33%. To the best of our knowledge, this success rate exceeds the reported performance of existing related systems and sets a new state of the art.
Tasks
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07489v1
PDF	https://arxiv.org/pdf/2003.07489v1.pdf
PWC	https://paperswithcode.com/paper/catch-the-ball-accurate-high-speed-motions
Repo
Framework

Aesthetic Quality Assessment for Group photograph


Title	Aesthetic Quality Assessment for Group photograph
Authors	Yaoting Wang, Yongzhen Ke, Kai Wang, Cuijiao Zhang, Fan Qin
Abstract	Image aesthetic quality assessment has got much attention in recent years, but not many works have been done on a specific genre of photos: Group photograph. In this work, we designed a set of high-level features based on the experience and principles of group photography: Opened-eye, Gaze, Smile, Occluded faces, Face Orientation, Facial blur, Character center. Then we combined them and 83 generic aesthetic features to build two aesthetic assessment models. We also constructed a large dataset of group photographs - GPD- annotated with the aesthetic score. The experimental result shows that our features perform well for categorizing professional photos and snapshots and predicting the distinction of multiple group photographs of diverse human states under the same scene.
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01096v1
PDF	https://arxiv.org/pdf/2002.01096v1.pdf
PWC	https://paperswithcode.com/paper/aesthetic-quality-assessment-for-group
Repo
Framework

Algorithmic Fairness


Title	Algorithmic Fairness
Authors	Dana Pessach, Erez Shmueli
Abstract	An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence (AI) algorithms in spheres ranging from healthcare, transportation, and education to college admissions, recruitment, provision of loans and many more realms. Since they now touch on many aspects of our lives, it is crucial to develop AI algorithms that are not only accurate but also objective and fair. Recent studies have shown that algorithmic decision-making may be inherently prone to unfairness, even when there is no intention for it. This paper presents an overview of the main concepts of identifying, measuring and improving algorithmic fairness when using AI algorithms. The paper begins by discussing the causes of algorithmic bias and unfairness and the common definitions and measures for fairness. Fairness-enhancing mechanisms are then reviewed and divided into pre-process, in-process and post-process mechanisms. A comprehensive comparison of the mechanisms is then conducted, towards a better understanding of which mechanisms should be used in different scenarios. The paper then describes the most commonly used fairness-related datasets in this field. Finally, the paper ends by reviewing several emerging research sub-fields of algorithmic fairness.
Tasks	Decision Making
Published	2020-01-21
URL	https://arxiv.org/abs/2001.09784v1
PDF	https://arxiv.org/pdf/2001.09784v1.pdf
PWC	https://paperswithcode.com/paper/algorithmic-fairness
Repo
Framework

The perceptual boost of visual attention is task-dependent in naturalistic settings


Title	The perceptual boost of visual attention is task-dependent in naturalistic settings
Authors	Freddie Bickford Smith, Xiaoliang Luo, Brett D. Roads, Bradley C. Love
Abstract	Attentional modulation of neural representations is known to enhance processing of task-relevant visual information. Is the resulting perceptual boost task-dependent in naturalistic settings? We aim to answer this with a large-scale computational experiment. First we design a series of visual tasks, each consisting of classifying images from a particular task set (group of image categories). The nature of a given task is determined by which categories are included in the task set. Then on each task we compare the accuracy of an attention-augmented neural network to that of an attention-free counterpart. We show that, all else being equal, the performance impact of attention is stronger with increasing task-set difficulty, weaker with increasing task-set size, and weaker with increasing perceptual similarity within a task set.
Tasks
Published	2020-02-22
URL	https://arxiv.org/abs/2003.00882v1
PDF	https://arxiv.org/pdf/2003.00882v1.pdf
PWC	https://paperswithcode.com/paper/the-perceptual-boost-of-visual-attention-is
Repo
Framework

Provably Efficient Safe Exploration via Primal-Dual Policy Optimization


Title	Provably Efficient Safe Exploration via Primal-Dual Policy Optimization
Authors	Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanović
Abstract	We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation in which an agent aims to maximize the expected total reward subject to a safety constraint on the expected total value of a criterion function (e.g., utility). We focus on an episodic setting with the function approximation where the reward and criterion functions and the Markov transition kernels all have a linear structure but do not impose any additional assumptions on the sampling model. Designing SRL algorithms with provable computational and statistical efficiency is particularly challenging under this setting because of the need to incorporate both the safety constraint and the function approximation into the fundamental exploitation/exploration tradeoff. To this end, we present an {O}ptimistic {P}rimal-{D}ual Proximal Policy {OP}timization (OPDOP) algorithm where the value function is estimated by combining the least-squares policy evaluation and an additional bonus term for safe exploration. We prove that the proposed algorithm achieves an O(d^{1.5}H^{3.5}\sqrt{T}) regret and an O(d^{1.5}H^{3.5}\sqrt{T}) constraint violation, where d is the dimension of the feature mapping, H is the horizon of each episode, and T is the total number of steps. We establish these bounds under the following two settings: (i) Both the reward and criterion functions can change adversarially but are revealed entirely after each episode. (ii) The reward/criterion functions are fixed but the feedback after each episode is bandit. Our bounds depend on the capacity of the state space only through the dimension of the feature mapping and thus our results hold even when the number of states goes to infinity. To the best of our knowledge, we provide the first provably efficient policy optimization algorithm for CMDPs with safe exploration.
Tasks	Safe Exploration
Published	2020-03-01
URL	https://arxiv.org/abs/2003.00534v1
PDF	https://arxiv.org/pdf/2003.00534v1.pdf
PWC	https://paperswithcode.com/paper/provably-efficient-safe-exploration-via
Repo
Framework

Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks


Title	Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks
Authors	Mihaela Dimovska, Travis Johnston, Catherine D. Schuman, J. Parker Mitchell, Thomas E. Potok
Abstract	Inspired by the connectivity mechanisms in the brain, neuromorphic computing architectures model Spiking Neural Networks (SNNs) in silicon. As such, neuromorphic architectures are designed and developed with the goal of having small, low power chips that can perform control and machine learning tasks. However, the power consumption of the developed hardware can greatly depend on the size of the network that is being evaluated on the chip. Furthermore, the accuracy of a trained SNN that is evaluated on chip can change due to voltage and current variations in the hardware that perturb the learned weights of the network. While efforts are made on the hardware side to minimize those perturbations, a software based strategy to make the deployed networks more resilient can help further alleviate that issue. In this work, we study Spiking Neural Networks in two neuromorphic architecture implementations with the goal of decreasing their size, while at the same time increasing their resiliency to hardware faults. We leverage an evolutionary algorithm to train the SNNs and propose a multiobjective fitness function to optimize the size and resiliency of the SNN. We demonstrate that this strategy leads to well-performing, small-sized networks that are more resilient to hardware faults.
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01406v1
PDF	https://arxiv.org/pdf/2002.01406v1.pdf
PWC	https://paperswithcode.com/paper/multi-objective-optimization-for-size-and
Repo
Framework

Safe Exploration for Optimizing Contextual Bandits


Title	Safe Exploration for Optimizing Contextual Bandits
Authors	Rolf Jagerman, Ilya Markov, Maarten de Rijke
Abstract	Contextual bandit problems are a natural fit for many information retrieval tasks, such as learning to rank, text classification, recommendation, etc. However, existing learning methods for contextual bandit problems have one of two drawbacks: they either do not explore the space of all possible document rankings (i.e., actions) and, thus, may miss the optimal ranking, or they present suboptimal rankings to a user and, thus, may harm the user experience. We introduce a new learning method for contextual bandit problems, Safe Exploration Algorithm (SEA), which overcomes the above drawbacks. SEA starts by using a baseline (or production) ranking system (i.e., policy), which does not harm the user experience and, thus, is safe to execute, but has suboptimal performance and, thus, needs to be improved. Then SEA uses counterfactual learning to learn a new policy based on the behavior of the baseline policy. SEA also uses high-confidence off-policy evaluation to estimate the performance of the newly learned policy. Once the performance of the newly learned policy is at least as good as the performance of the baseline policy, SEA starts using the new policy to execute new actions, allowing it to actively explore favorable regions of the action space. This way, SEA never performs worse than the baseline policy and, thus, does not harm the user experience, while still exploring the action space and, thus, being able to find an optimal policy. Our experiments using text classification and document retrieval confirm the above by comparing SEA (and a boundless variant called BSEA) to online and offline learning methods for contextual bandit problems.
Tasks	Information Retrieval, Learning-To-Rank, Multi-Armed Bandits, Safe Exploration, Text Classification
Published	2020-02-02
URL	https://arxiv.org/abs/2002.00467v1
PDF	https://arxiv.org/pdf/2002.00467v1.pdf
PWC	https://paperswithcode.com/paper/safe-exploration-for-optimizing-contextual
Repo
Framework

Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing


Title	Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing
Authors	Ziqi Liu, Dong Wang, Qianyu Yu, Zhiqiang Zhang, Yue Shen, Jian Ma, Wenliang Zhong, Jinjie Gu, Jun Zhou, Shuang Yang, Yuan Qi
Abstract	Mobile payment such as Alipay has been widely used in our daily lives. To further promote the mobile payment activities, it is important to run marketing campaigns under a limited budget by providing incentives such as coupons, commissions to merchants. As a result, incentive optimization is the key to maximizing the commercial objective of the marketing campaign. With the analyses of online experiments, we found that the transaction network can subtly describe the similarity of merchants’ responses to different incentives, which is of great use in the incentive optimization problem. In this paper, we present a graph representation learning method atop of transaction networks for merchant incentive optimization in mobile payment marketing. With limited samples collected from online experiments, our end-to-end method first learns merchant representations based on an attributed transaction networks, then effectively models the correlations between the commercial objectives each merchant may achieve and the incentives under varying treatments. Thus we are able to model the sensitivity to incentive for each merchant, and spend the most budgets on those merchants that show strong sensitivities in the marketing campaign. Extensive offline and online experimental results at Alipay demonstrate the effectiveness of our proposed approach.
Tasks	Graph Representation Learning, Representation Learning
Published	2020-02-27
URL	https://arxiv.org/abs/2003.01515v1
PDF	https://arxiv.org/pdf/2003.01515v1.pdf
PWC	https://paperswithcode.com/paper/graph-representation-learning-for-merchant
Repo
Framework

Axiom Pinpointing


Title	Axiom Pinpointing
Authors	Rafael Peñaloza
Abstract	Axiom pinpointing refers to the task of finding the specific axioms in an ontology which are responsible for a consequence to follow. This task has been studied, under different names, in many research areas, leading to a reformulation and reinvention of techniques. In this work, we present a general overview to axiom pinpointing, providing the basic notions, different approaches for solving it, and some variations and applications which have been considered in the literature. This should serve as a starting point for researchers interested in related problems, with an ample bibliography for delving deeper into the details.
Tasks
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08298v1
PDF	https://arxiv.org/pdf/2003.08298v1.pdf
PWC	https://paperswithcode.com/paper/axiom-pinpointing
Repo
Framework