April 2, 2020

3258 words 16 mins read

Paper Group ANR 222

FedRec: Privacy-Preserving News Recommendation with Federated Learning. Anticipatory Psychological Models for Quickest Change Detection: Human Sensor Interaction. BBAND Index: A No-Reference Banding Artifact Predictor. Are You Satisfied by This Partial Assignment?. FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images. …

FedRec: Privacy-Preserving News Recommendation with Federated Learning


Title	FedRec: Privacy-Preserving News Recommendation with Federated Learning
Authors	Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang, Xing Xie
Abstract	News recommendation aims to display news articles to users based on their personal interest. Existing news recommendation methods rely on centralized storage of user behavior data for model training, which may lead to privacy concerns and risks due to the privacy-sensitive nature of user behaviors. In this paper, we propose a privacy-preserving method for news recommendation model training based on federated learning, where the user behavior data is locally stored on user devices. Our method can leverage the useful information in the behaviors of massive users to train accurate news recommendation models and meanwhile remove the need to centralized storage of them. More specifically, on each user device we keep a local copy of the news recommendation model, and compute gradients of the local model based on the user behaviors in this device. The local gradients from a group of randomly selected users are uploaded to server, which are further aggregated to update the global model in the server. Since the model gradients may contain some implicit private information, we apply local differential privacy (LDP) to them before uploading for better privacy protection. The updated global model is then distributed to each user device for local model update. We repeat this process for multiple rounds. Extensive experiments on a real-world dataset show the effectiveness of our method in news recommendation model training with privacy protection.
Tasks
Published	2020-03-21
URL	https://arxiv.org/abs/2003.09592v2
PDF	https://arxiv.org/pdf/2003.09592v2.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-news-recommendation-model
Repo
Framework

Anticipatory Psychological Models for Quickest Change Detection: Human Sensor Interaction


Title	Anticipatory Psychological Models for Quickest Change Detection: Human Sensor Interaction
Authors	Vikram Krishnamurthy
Abstract	We consider anticipatory psychological models for human decision makers and their effect on sequential decision making. From a decision theoretic point of view, such models are time inconsistent meaning that Bellman’s principle of optimality does not hold. The aim of this paper is to study how such an anxiety-based anticipatory utility can affect sequential decision making, such as quickest change detection, in multi-agent systems. We show that the interaction between anticipation-driven agents and sequential decision maker results in unusual (nonconvex) structure of the optimal decision policy. The methodology yields a useful mathematical framework for sensor interaction involving a human decision maker (with behavioral economics constraints) and a sensor equipped with automated sequential detector.
Tasks	Decision Making
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10910v1
PDF	https://arxiv.org/pdf/2003.10910v1.pdf
PWC	https://paperswithcode.com/paper/anticipatory-psychological-models-for
Repo
Framework

BBAND Index: A No-Reference Banding Artifact Predictor


Title	BBAND Index: A No-Reference Banding Artifact Predictor
Authors	Zhengzhong Tu, Jessie Lin, Yilin Wang, Balu Adsumilli, Alan C. Bovik
Abstract	Banding artifact, or false contouring, is a common video compression impairment that tends to appear on large flat regions in encoded videos. These staircase-shaped color bands can be very noticeable in high-definition videos. Here we study this artifact, and propose a new distortion-specific no-reference video quality model for predicting banding artifacts, called the Blind BANding Detector (BBAND index). BBAND is inspired by human visual models. The proposed detector can generate a pixel-wise banding visibility map and output a banding severity score at both the frame and video levels. Experimental results show that our proposed method outperforms state-of-the-art banding detection algorithms and delivers better consistency with subjective evaluations.
Tasks	Video Compression
Published	2020-02-27
URL	https://arxiv.org/abs/2002.11891v1
PDF	https://arxiv.org/pdf/2002.11891v1.pdf
PWC	https://paperswithcode.com/paper/bband-index-a-no-reference-banding-artifact
Repo
Framework

Are You Satisfied by This Partial Assignment?


Title	Are You Satisfied by This Partial Assignment?
Authors	Roberto Sebastiani
Abstract	Many procedures for SAT and SAT-related problems – in particular for those requiring the complete enumeration of satisfying truth assignments – rely their efficiency on the detection of partial assignments satisfying an input formula. In this paper we analyze the notion of partial-assignment satisfiability – in particular when dealing with non-CNF and existentially-quantified formulas – raising a flag about the ambiguities and subtleties of this concept, and investigating their practical consequences. This may drive the development of more effective assignment-enumeration algorithms.
Tasks
Published	2020-02-28
URL	https://arxiv.org/abs/2003.04225v1
PDF	https://arxiv.org/pdf/2003.04225v1.pdf
PWC	https://paperswithcode.com/paper/are-you-satisfied-by-this-partial-assignment
Repo
Framework

FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images


Title	FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images
Authors	Kaiyan Chen, Ming Wu, Jiaming Liu, Chuang Zhang
Abstract	Ship detection using high-resolution remote sensing images is an important task, which contribute to sea surface regulation. The complex background and special visual angle make ship detection relies in high quality datasets to a certain extent. However, there is few works on giving both precise classification and accurate location of ships in existing ship detection datasets. To further promote the research of ship detection, we introduced a new fine-grained ship detection datasets, which is named as FGSD. The dataset collects high-resolution remote sensing images that containing ship samples from multiple large ports around the world. Ship samples were fine categorized and annotated with both horizontal and rotating bounding boxes. To further detailed the information of the dataset, we put forward a new representation method of ships’ orientation. For future research, the dock as a new class was annotated in the dataset. Besides, rich information of images were provided in FGSD, including the source port, resolution and corresponding GoogleEarth’ s resolution level of each image. As far as we know, FGSD is the most comprehensive ship detection dataset currently and it’ll be available soon. Some baselines for FGSD are also provided in this paper.
Tasks
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06832v1
PDF	https://arxiv.org/pdf/2003.06832v1.pdf
PWC	https://paperswithcode.com/paper/fgsd-a-dataset-for-fine-grained-ship
Repo
Framework

The Goal-Gradient Hypothesis in Stack Overflow


Title	The Goal-Gradient Hypothesis in Stack Overflow
Authors	Nicholas Hoernle, Gregory Kehne, Ariel D. Procaccia, Kobi Gal
Abstract	According to the goal-gradient hypothesis, people increase their efforts toward a reward as they close in on the reward. This hypothesis has recently been used to explain users’ behavior in online communities that use badges as rewards for completing specific activities. In such settings, users exhibit a “steering effect,” a dramatic increase in activity as the users approach a badge threshold, thereby following the predictions made by the goal-gradient hypothesis. This paper provides a new probabilistic model of users’ behavior, which captures users who exhibit different levels of steering. We apply this model to data from the popular Q&A site, Stack Overflow, and study users who achieve one of the badges available on this platform. Our results show that only a fraction (20%) of all users strongly experience steering, whereas the activity of more than 40% of badge achievers appears not to be affected by the badge. In particular, we find that for some of the population, an increased activity in and around the badge acquisition date may reflect a statistical artifact rather than steering, as was previously thought in prior work. These results are important for system designers who hope to motivate and guide their users towards certain actions. We have highlighted the need for further studies which investigate what motivations drive the non-steered users to contribute to online communities.
Tasks
Published	2020-02-14
URL	https://arxiv.org/abs/2002.06160v1
PDF	https://arxiv.org/pdf/2002.06160v1.pdf
PWC	https://paperswithcode.com/paper/the-goal-gradient-hypothesis-in-stack
Repo
Framework

Cramér-Rao Lower Bounds Arising from Generalized Csiszár Divergences


Title	Cramér-Rao Lower Bounds Arising from Generalized Csiszár Divergences
Authors	M. Ashok Kumar, Kumar Vijay Mishra
Abstract	We study the geometry of probability distributions with respect to a generalized family of Csisz'ar $f$-divergences. A member of this family is the relative $\alpha$-entropy which is also a R'enyi analog of relative entropy in information theory and known as logarithmic or projective power divergence in statistics. We apply Eguchi’s theory to derive the Fisher information metric and the dual affine connections arising from these generalized divergence functions. The notion enables us to arrive at a more widely applicable version of the Cram'{e}r-Rao inequality, which provides a lower bound for the variance of an estimator for an escort of the underlying parametric probability distribution. We then extend the Amari-Nagaoka’s dually flat structure of the exponential and mixer models to other distributions with respect to the aforementioned generalized metric. We show that these formulations lead us to find unbiased and efficient estimators for the escort model.
Tasks
Published	2020-01-14
URL	https://arxiv.org/abs/2001.04769v1
PDF	https://arxiv.org/pdf/2001.04769v1.pdf
PWC	https://paperswithcode.com/paper/cramer-rao-lower-bounds-arising-from
Repo
Framework

Adversarial TCAV – Robust and Effective Interpretation of Intermediate Layers in Neural Networks


Title	Adversarial TCAV – Robust and Effective Interpretation of Intermediate Layers in Neural Networks
Authors	Rahul Soni, Naresh Shah, Chua Tat Seng, Jimmy D. Moore
Abstract	Interpreting neural network decisions and the information learned in intermediate layers is still a challenge due to the opaque internal state and shared non-linear interactions. Although (Kim et al, 2017) proposed to interpret intermediate layers by quantifying its ability to distinguish a user-defined concept (from random examples), the questions of robustness (variation against the choice of random examples) and effectiveness (retrieval rate of concept images) remain. We investigate these two properties and propose improvements to make concept activations reliable for practical use. Effectiveness: If the intermediate layer has effectively learned a user-defined concept, it should be able to recall — at the testing step — most of the images containing the proposed concept. For instance, we observed that the recall rate of Tiger shark and Great white shark from the ImageNet dataset with “Fins” as a user-defined concept was only 18.35% for VGG16. To increase the effectiveness of concept learning, we propose A-CAV — the Adversarial Concept Activation Vector — this results in larger margins between user concepts and (negative) random examples. This approach improves the aforesaid recall to 76.83% for VGG16. For robustness, we define it as the ability of an intermediate layer to be consistent in its recall rate (the effectiveness) for different random seeds. We observed that TCAV has a large variance in recalling a concept across different random seeds. For example, the recall of cat images (from a layer learning the concept of tail) varies from 18% to 86% with 20.85% standard deviation on VGG16. We propose a simple and scalable modification that employs a Gram-Schmidt process to sample random noise from concepts and learn an average “concept classifier”. This approach improves the aforesaid standard deviation from 20.85% to 6.4%.
Tasks
Published	2020-02-10
URL	https://arxiv.org/abs/2002.03549v2
PDF	https://arxiv.org/pdf/2002.03549v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-tcav-robust-and-effective
Repo
Framework

Multi-Task Learning from Videos via Efficient Inter-Frame Attention


Title	Multi-Task Learning from Videos via Efficient Inter-Frame Attention
Authors	Donghyun Kim, Tian Lan, Chuhang Zou, Ning Xu, Bryan A. Plummer, Stan Sclaroff, Jayan Eledath, Gerard Medioni
Abstract	Prior work in multi-task learning has mainly focused on predictions on a single image. In this work, we present a new approach for multi-task learning from videos. Our approach contains a novel inter-frame attention module which allows learning of task-specific attention across frames. We embed the attention module in a “slow-fast” architecture, where the slower network runs on sparsely sampled keyframes and the lightweight shallow network runs on non-key frames at a high frame rate. We further propose an effective adversarial learning strategy to encourage the slow and fast network to learn similar features. The proposed architecture ensures low-latency multi-task learning while maintaining high quality prediction. Experiments show competitive accuracy compared to state-of-the-art on two multi-task learning benchmarks while reducing the number of floating point operations (FLOPs) by 70%. Meanwhile, our attention based feature propagation outperforms other feature propagation methods in accuracy by up to 90% reduction of FLOPs.
Tasks	Multi-Task Learning
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07362v1
PDF	https://arxiv.org/pdf/2002.07362v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-learning-from-videos-via-efficient
Repo
Framework

Speech-to-Singing Conversion in an Encoder-Decoder Framework


Title	Speech-to-Singing Conversion in an Encoder-Decoder Framework
Authors	Jayneel Parekh, Preeti Rao, Yi-Hsuan Yang
Abstract	In this paper our goal is to convert a set of spoken lines into sung ones. Unlike previous signal processing based methods, we take a learning based approach to the problem. This allows us to automatically model various aspects of this transformation, thus overcoming dependence on specific inputs such as high quality singing templates or phoneme-score synchronization information. Specifically, we propose an encoder–decoder framework for our task. Given time-frequency representations of speech and a target melody contour, we learn encodings that enable us to synthesize singing that preserves the linguistic content and timbre of the speaker while adhering to the target melody. We also propose a multi-task learning based objective to improve lyric intelligibility. We present a quantitative and qualitative analysis of our framework.
Tasks	Multi-Task Learning
Published	2020-02-16
URL	https://arxiv.org/abs/2002.06595v1
PDF	https://arxiv.org/pdf/2002.06595v1.pdf
PWC	https://paperswithcode.com/paper/speech-to-singing-conversion-in-an-encoder
Repo
Framework

Deep Multi-Task Augmented Feature Learning via Hierarchical Graph Neural Network


Title	Deep Multi-Task Augmented Feature Learning via Hierarchical Graph Neural Network
Authors	Pengxin Guo, Chang Deng, Linjie Xu, Xiaonan Huang, Yu Zhang
Abstract	Deep multi-task learning attracts much attention in recent years as it achieves good performance in many applications. Feature learning is important to deep multi-task learning for sharing common information among tasks. In this paper, we propose a Hierarchical Graph Neural Network (HGNN) to learn augmented features for deep multi-task learning. The HGNN consists of two-level graph neural networks. In the low level, an intra-task graph neural network is responsible of learning a powerful representation for each data point in a task by aggregating its neighbors. Based on the learned representation, a task embedding can be generated for each task in a similar way to max pooling. In the second level, an inter-task graph neural network updates task embeddings of all the tasks based on the attention mechanism to model task relations. Then the task embedding of one task is used to augment the feature representation of data points in this task. Moreover, for classification tasks, an inter-class graph neural network is introduced to conduct similar operations on a finer granularity, i.e., the class level, to generate class embeddings for each class in all the tasks use class embeddings to augment the feature representation. The proposed feature augmentation strategy can be used in many deep multi-task learning models. we analyze the HGNN in terms of training and generalization losses. Experiments on real-world datastes show the significant performance improvement when using this strategy.
Tasks	Multi-Task Learning
Published	2020-02-12
URL	https://arxiv.org/abs/2002.04813v1
PDF	https://arxiv.org/pdf/2002.04813v1.pdf
PWC	https://paperswithcode.com/paper/deep-multi-task-augmented-feature-learning
Repo
Framework

Developing a Hybrid Data-Driven, Mechanistic Virtual Flow Meter – a Case Study


Title	Developing a Hybrid Data-Driven, Mechanistic Virtual Flow Meter – a Case Study
Authors	Mathilde Hotvedt, Bjarne Grimstad, Lars Imsland
Abstract	Virtual flow meters, mathematical models predicting production flow rates in petroleum assets, are useful aids in production monitoring and optimization. Mechanistic models based on first-principles are most common, however, data-driven models exploiting patterns in measurements are gaining popularity. This research investigates a hybrid modeling approach, utilizing techniques from both the aforementioned areas of expertise, to model a well production choke. The choke is represented with a simplified set of first-principle equations and a neural network to estimate the valve flow coefficient. Historical production data from the petroleum platform Edvard Grieg is used for model validation. Additionally, a mechanistic and a data-driven model are constructed for comparison of performance. A practical framework for development of models with varying degree of hybridity and stochastic optimization of its parameters is established. Results of the hybrid model performance are promising albeit with considerable room for improvements.
Tasks	Stochastic Optimization
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02737v1
PDF	https://arxiv.org/pdf/2002.02737v1.pdf
PWC	https://paperswithcode.com/paper/developing-a-hybrid-data-driven-mechanistic
Repo
Framework

Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applications


Title	Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: A New Insight into Machine Learning Applications
Authors	Yun Yuan, Xianfeng Terry Yang, Zhao Zhang, Shandian Zhe
Abstract	Despite the wide implementation of machine learning (ML) techniques in traffic flow modeling recently, those data-driven approaches often fall short of accuracy in the cases with a small or noisy dataset. To address this issue, this study presents a new modeling framework, named physics regularized machine learning (PRML), to encode classical traffic flow models (referred as physical models) into the ML architecture and to regularize the ML training process. More specifically, a stochastic physics regularized Gaussian process (PRGP) model is developed and a Bayesian inference algorithm is used to estimate the mean and kernel of the PRGP. A physical regularizer based on macroscopic traffic flow models is also developed to augment the estimation via a shadow GP and an enhanced latent force model is used to encode physical knowledge into stochastic processes. Based on the posterior regularization inference framework, an efficient stochastic optimization algorithm is also developed to maximize the evidence lowerbound of the system likelihood. To prove the effectiveness of the proposed model, this paper conducts empirical studies on a real-world dataset which is collected from a stretch of I-15 freeway, Utah. Results show the new PRGP model can outperform the previous compatible methods, such as calibrated pure physical models and pure machine learning methods, in estimation precision and input robustness.
Tasks	Bayesian Inference, Stochastic Optimization
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02374v1
PDF	https://arxiv.org/pdf/2002.02374v1.pdf
PWC	https://paperswithcode.com/paper/macroscopic-traffic-flow-modeling-with
Repo
Framework

Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling


Title	Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling
Authors	Will Grathwohl, Kuan-Chieh Wang, Jorn-Henrik Jacobsen, David Duvenaud, Richard Zemel
Abstract	We present a new method for evaluating and training unnormalized density models. Our approach only requires access to the gradient of the unnormalized model’s log-density. We estimate the Stein discrepancy between the data density p(x) and the model density q(x) defined by a vector function of the data. We parameterize this function with a neural network and fit its parameters to maximize the discrepancy. This yields a novel goodness-of-fit test which outperforms existing methods on high dimensional data. Furthermore, optimizing $q(x)$ to minimize this discrepancy produces a novel method for training unnormalized models which scales more gracefully than existing methods. The ability to both learn and compare models is a unique feature of the proposed method.
Tasks
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05616v2
PDF	https://arxiv.org/pdf/2002.05616v2.pdf
PWC	https://paperswithcode.com/paper/cutting-out-the-middle-man-training-and
Repo
Framework

Road Curb Detection and Localization with Monocular Forward-view Vehicle Camera


Title	Road Curb Detection and Localization with Monocular Forward-view Vehicle Camera
Authors	Stanislav Panev, Francisco Vicente, Fernando De la Torre, Véronique Prinet
Abstract	We propose a robust method for estimating road curb 3D parameters (size, location, orientation) using a calibrated monocular camera equipped with a fisheye lens. Automatic curb detection and localization is particularly important in the context of Advanced Driver Assistance System (ADAS), i.e. to prevent possible collision and damage of the vehicle’s bumper during perpendicular and diagonal parking maneuvers. Combining 3D geometric reasoning with advanced vision-based detection methods, our approach is able to estimate the vehicle to curb distance in real time with mean accuracy of more than 90%, as well as its orientation, height and depth. Our approach consists of two distinct components - curb detection in each individual video frame and temporal analysis. The first part comprises of sophisticated curb edges extraction and parametrized 3D curb template fitting. Using a few assumptions regarding the real world geometry, we can thus retrieve the curb’s height and its relative position w.r.t. the moving vehicle on which the camera is mounted. Support Vector Machine (SVM) classifier fed with Histograms of Oriented Gradients (HOG) is used for appearance-based filtering out outliers. In the second part, the detected curb regions are tracked in the temporal domain, so as to perform a second pass of false positives rejection. We have validated our approach on a newly collected database of 11 videos under different conditions. We have used point-wise LIDAR measurements and manual exhaustive labels as a ground truth.
Tasks
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12492v1
PDF	https://arxiv.org/pdf/2002.12492v1.pdf
PWC	https://paperswithcode.com/paper/road-curb-detection-and-localization-with
Repo
Framework