October 18, 2019

3256 words 16 mins read

Paper Group ANR 475

Envy-Free Classification. Enhancing Gaussian Estimation of Distribution Algorithm by Exploiting Evolution Direction with Archive. Generative Adversarial Privacy. Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks. Learning Scheduling Algorithms for Data Processing Clusters. Towards a Fatality-A …

Envy-Free Classification


Title	Envy-Free Classification
Authors	Maria-Florina Balcan, Travis Dick, Ritesh Noothigattu, Ariel D. Procaccia
Abstract	In classic fair division problems such as cake cutting and rent division, envy-freeness requires that each individual (weakly) prefer his allocation to anyone else’s. On a conceptual level, we argue that envy-freeness also provides a compelling notion of fairness for classification tasks. Our technical focus is the generalizability of envy-free classification, i.e., understanding whether a classifier that is envy free on a sample would be almost envy free with respect to the underlying distribution with high probability. Our main result establishes that a small sample is sufficient to achieve such guarantees, when the classifier in question is a mixture of deterministic classifiers that belong to a family of low Natarajan dimension.
Tasks
Published	2018-09-23
URL	http://arxiv.org/abs/1809.08700v1
PDF	http://arxiv.org/pdf/1809.08700v1.pdf
PWC	https://paperswithcode.com/paper/envy-free-classification
Repo
Framework

Enhancing Gaussian Estimation of Distribution Algorithm by Exploiting Evolution Direction with Archive


Title	Enhancing Gaussian Estimation of Distribution Algorithm by Exploiting Evolution Direction with Archive
Authors	Yongsheng Liang, Zhigang Ren, Xianghua Yao, Zuren Feng, An Chen
Abstract	As a typical model-based evolutionary algorithm (EA), estimation of distribution algorithm (EDA) possesses unique characteristics and has been widely applied to global optimization. However, the common-used Gaussian EDA (GEDA) usually suffers from premature convergence which severely limits its search efficiency. This study first systematically analyses the reasons for the deficiency of the traditional GEDA, then tries to enhance its performance by exploiting its evolution direction, and finally develops a new GEDA variant named EDA2. Instead of only utilizing some good solutions produced in the current generation when estimating the Gaussian model, EDA2 preserves a certain number of high-quality solutions generated in previous generations into an archive and takes advantage of these historical solutions to assist estimating the covariance matrix of Gaussian model. By this means, the evolution direction information hidden in the archive is naturally integrated into the estimated model which in turn can guide EDA2 towards more promising solution regions. Moreover, the new estimation method significantly reduces the population size of EDA2 since it needs fewer individuals in the current population for model estimation. As a result, a fast convergence can be achieved. To verify the efficiency of EDA2, we tested it on a variety of benchmark functions and compared it with several state-of-the-art EAs, including IPOP-CMAES, AMaLGaM, three high-powered DE algorithms, and a new PSO algorithm. The experimental results demonstrate that EDA2 is efficient and competitive.
Tasks
Published	2018-02-25
URL	http://arxiv.org/abs/1802.08989v2
PDF	http://arxiv.org/pdf/1802.08989v2.pdf
PWC	https://paperswithcode.com/paper/enhancing-gaussian-estimation-of-distribution
Repo
Framework

Generative Adversarial Privacy


Title	Generative Adversarial Privacy
Authors	Chong Huang, Peter Kairouz, Xiao Chen, Lalitha Sankar, Ram Rajagopal
Abstract	We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. We show that for appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. We also evaluate GAP’s performance on the GENKI face database.
Tasks
Published	2018-07-13
URL	https://arxiv.org/abs/1807.05306v3
PDF	https://arxiv.org/pdf/1807.05306v3.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-privacy
Repo
Framework

Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks


Title	Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks
Authors	Renjie Zheng, Junkun Chen, Xipeng Qiu
Abstract	Distributed representation plays an important role in deep learning based natural language processing. However, the representation of a sentence often varies in different tasks, which is usually learned from scratch and suffers from the limited amounts of training data. In this paper, we claim that a good sentence representation should be invariant and can benefit the various subsequent tasks. To achieve this purpose, we propose a new scheme of information sharing for multi-task learning. More specifically, all tasks share the same sentence representation and each task can select the task-specific information from the shared sentence representation with attention mechanism. The query vector of each task’s attention could be either static parameters or generated dynamically. We conduct extensive experiments on 16 different text classification tasks, which demonstrate the benefits of our architecture.
Tasks	Multi-Task Learning, Representation Learning, Text Classification
Published	2018-04-22
URL	http://arxiv.org/abs/1804.08139v1
PDF	http://arxiv.org/pdf/1804.08139v1.pdf
PWC	https://paperswithcode.com/paper/same-representation-different-attentions
Repo
Framework

Learning Scheduling Algorithms for Data Processing Clusters


Title	Learning Scheduling Algorithms for Data Processing Clusters
Authors	Hongzi Mao, Malte Schwarzkopf, Shaileshh Bojja Venkatakrishnan, Zili Meng, Mohammad Alizadeh
Abstract	Efficiently scheduling data processing jobs on distributed compute clusters requires complex algorithms. Current systems, however, use simple generalized heuristics and ignore workload characteristics, since developing and tuning a scheduling policy for each workload is infeasible. In this paper, we show that modern machine learning techniques can generate highly-efficient policies automatically. Decima uses reinforcement learning (RL) and neural networks to learn workload-specific scheduling algorithms without any human instruction beyond a high-level objective such as minimizing average job completion time. Off-the-shelf RL techniques, however, cannot handle the complexity and scale of the scheduling problem. To build Decima, we had to develop new representations for jobs’ dependency graphs, design scalable RL models, and invent RL training methods for dealing with continuous stochastic job arrivals. Our prototype integration with Spark on a 25-node cluster shows that Decima improves the average job completion time over hand-tuned scheduling heuristics by at least 21%, achieving up to 2x improvement during periods of high cluster load.
Tasks
Published	2018-10-03
URL	https://arxiv.org/abs/1810.01963v4
PDF	https://arxiv.org/pdf/1810.01963v4.pdf
PWC	https://paperswithcode.com/paper/learning-scheduling-algorithms-for-data
Repo
Framework

Towards a Fatality-Aware Benchmark of Probabilistic Reaction Prediction in Highly Interactive Driving Scenarios


Title	Towards a Fatality-Aware Benchmark of Probabilistic Reaction Prediction in Highly Interactive Driving Scenarios
Authors	Wei Zhan, Liting Sun, Yeping Hu, Jiachen Li, Masayoshi Tomizuka
Abstract	Autonomous vehicles should be able to generate accurate probabilistic predictions for uncertain behavior of other road users. Moreover, reactive predictions are necessary in highly interactive driving scenarios to answer “what if I take this action in the future” for autonomous vehicles. There is no existing unified framework to homogenize the problem formulation, representation simplification, and evaluation metric for various prediction methods, such as probabilistic graphical models (PGM), neural networks (NN) and inverse reinforcement learning (IRL). In this paper, we formulate a probabilistic reaction prediction problem, and reveal the relationship between reaction and situation prediction problems. We employ prototype trajectories with designated motion patterns other than “intention” to homogenize the representation so that probabilities corresponding to each trajectory generated by different methods can be evaluated. We also discuss the reasons why “intention” is not suitable to serve as a motion indicator in highly interactive scenarios. We propose to use Brier score as the baseline metric for evaluation. In order to reveal the fatality of the consequences when the predictions are adopted by decision-making and planning, we propose a fatality-aware metric, which is a weighted Brier score based on the criticality of the trajectory pairs of the interacting entities. Conservatism and non-defensiveness are defined from the weighted Brier score to indicate the consequences caused by inaccurate predictions. Modified methods based on PGM, NN and IRL are provided to generate probabilistic reaction predictions in an exemplar scenario of nudging from a highway ramp. The results are evaluated by the baseline and proposed metrics to construct a mini benchmark. Analysis on the properties of each method is also provided by comparing the baseline and proposed metric scores.
Tasks	Autonomous Vehicles, Decision Making
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03478v1
PDF	http://arxiv.org/pdf/1809.03478v1.pdf
PWC	https://paperswithcode.com/paper/towards-a-fatality-aware-benchmark-of
Repo
Framework

Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks


Title	Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks
Authors	Ghouthi Boukli Hacene, Vincent Gripon, Matthieu Arzel, Nicolas Farrugia, Yoshua Bengio
Abstract	Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and strongly limits their usability in budget-constrained devices such as embedded devices. In this paper, we propose a combination of a new pruning technique and a quantization scheme that effectively reduce the complexity and memory usage of convolutional layers of CNNs, and replace the complex convolutional operation by a low-cost multiplexer. We perform experiments on the CIFAR10, CIFAR100 and SVHN and show that the proposed method achieves almost state-of-the-art accuracy, while drastically reducing the computational and memory footprints. We also propose an efficient hardware architecture to accelerate CNN operations. The proposed hardware architecture is a pipeline and accommodates multiple layers working at the same time to speed up the inference process.
Tasks	Object Classification, Quantization
Published	2018-12-29
URL	http://arxiv.org/abs/1812.11337v1
PDF	http://arxiv.org/pdf/1812.11337v1.pdf
PWC	https://paperswithcode.com/paper/quantized-guided-pruning-for-efficient
Repo
Framework

Signal Classification under structure sparsity constraints


Title	Signal Classification under structure sparsity constraints
Authors	Tiep Huu Vu
Abstract	Object Classification is a key direction of research in signal and image processing, computer vision and artificial intelligence. The goal is to come up with algorithms that automatically analyze images and put them in predefined categories. This dissertation focuses on the theory and application of sparse signal processing and learning algorithms for image processing and computer vision, especially object classification problems. A key emphasis of this work is to formulate novel optimization problems for learning dictionary and structured sparse representations. Tractable solutions are proposed subsequently for the corresponding optimization problems. An important goal of this dissertation is to demonstrate the wide applications of these algorithmic tools for real-world applications. To that end, we explored important problems in the areas of: 1. Medical imaging: histopathological images acquired from mammalian tissues, human breast tissues, and human brain tissues. 2. Low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar: detecting bombs and mines buried under rough surfaces. 3. General object classification: face, flowers, objects, dogs, indoor scenes, etc.
Tasks	Object Classification
Published	2018-12-28
URL	http://arxiv.org/abs/1812.10859v1
PDF	http://arxiv.org/pdf/1812.10859v1.pdf
PWC	https://paperswithcode.com/paper/signal-classification-under-structure
Repo
Framework

Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow


Title	Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow
Authors	Pengcheng Yin, Bowen Deng, Edgar Chen, Bogdan Vasilescu, Graham Neubig
Abstract	For tasks like code synthesis from natural language, code retrieval, and code summarization, data-driven models have shown great promise. However, creating these models require parallel data between natural language (NL) and code with fine-grained alignments. Stack Overflow (SO) is a promising source to create such a data set: the questions are diverse and most of them have corresponding answers with high-quality code snippets. However, existing heuristic methods (e.g., pairing the title of a post with the code in the accepted answer) are limited both in their coverage and the correctness of the NL-code pairs obtained. In this paper, we propose a novel method to mine high-quality aligned data from SO using two sets of features: hand-crafted features considering the structure of the extracted snippets, and correspondence features obtained by training a probabilistic model to capture the correlation between NL and code using neural networks. These features are fed into a classifier that determines the quality of mined NL-code pairs. Experiments using Python and Java as test beds show that the proposed method greatly expands coverage and accuracy over existing mining methods, even when using only a small number of labeled examples. Further, we find that reasonable results are achieved even when training the classifier on one language and testing on another, showing promise for scaling NL-code mining to a wide variety of programming languages beyond those for which we are able to annotate data.
Tasks	Code Summarization
Published	2018-05-23
URL	http://arxiv.org/abs/1805.08949v1
PDF	http://arxiv.org/pdf/1805.08949v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-mine-aligned-code-and-natural
Repo
Framework

Optimizing Quantum Error Correction Codes with Reinforcement Learning


Title	Optimizing Quantum Error Correction Codes with Reinforcement Learning
Authors	Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Briegel, Nicolai Friis
Abstract	Quantum error correction is widely thought to be the key to fault-tolerant quantum computation. However, determining the most suited encoding for unknown error channels or specific laboratory setups is highly challenging. Here, we present a reinforcement learning framework for optimizing and fault-tolerantly adapting quantum error correction codes. We consider a reinforcement learning agent tasked with modifying a family of surface code quantum memories until a desired logical error rate is reached. Using efficient simulations with about 70 data qubits with arbitrary connectivity, we demonstrate that such a reinforcement learning agent can determine near-optimal solutions, in terms of the number of data qubits, for various error models of interest. Moreover, we show that agents trained on one setting are able to successfully transfer their experience to different settings. This ability for transfer learning showcases the inherent strengths of reinforcement learning and the applicability of our approach for optimization from off-line simulations to on-line laboratory settings.
Tasks	Transfer Learning
Published	2018-12-20
URL	https://arxiv.org/abs/1812.08451v4
PDF	https://arxiv.org/pdf/1812.08451v4.pdf
PWC	https://paperswithcode.com/paper/optimizing-quantum-error-correction-codes
Repo
Framework

Automatic generation of object shapes with desired functionalities


Title	Automatic generation of object shapes with desired functionalities
Authors	Mihai Andries, Atabak Dehban, José Santos-Victor
Abstract	3D objects (artefacts) are made to fulfill functions. Designing an object often starts with defining a list of functionalities that it should provide, also known as functional requirements. Today, the design of 3D object models is still a slow and largely artisanal activity, with few Computer-Aided Design (CAD) tools existing to aid the exploration of the design solution space. To accelerate the design process, we introduce an algorithm for generating object shapes with desired functionalities. Following the concept of form follows function, we assume that existing object shapes were rationally chosen to provide desired functionalities. First, we use an artificial neural network to learn a function-to-form mapping by analysing a dataset of objects labeled with their functionalities. Then, we combine forms providing one or more desired functions, generating an object shape that is expected to provide all of them. Finally, we verify in simulation whether the generated object possesses the desired functionalities, by defining and executing functionality tests on it.
Tasks
Published	2018-05-30
URL	http://arxiv.org/abs/1805.11984v2
PDF	http://arxiv.org/pdf/1805.11984v2.pdf
PWC	https://paperswithcode.com/paper/automatic-generation-of-object-shapes-with
Repo
Framework

Basis Pursuit Denoise with Nonsmooth Constraints


Title	Basis Pursuit Denoise with Nonsmooth Constraints
Authors	Robert Baraldi, Rajiv Kumar, Aleksandr Aravkin
Abstract	Level-set optimization formulations with data-driven constraints minimize a regularization functional subject to matching observations to a given error level. These formulations are widely used, particularly for matrix completion and sparsity promotion in data interpolation and denoising. The misfit level is typically measured in the l2 norm, or other smooth metrics. In this paper, we present a new flexible algorithmic framework that targets nonsmooth level-set constraints, including L1, Linf, and even L0 norms. These constraints give greater flexibility for modeling deviations in observation and denoising, and have significant impact on the solution. Measuring error in the L1 and L0 norms makes the result more robust to large outliers, while matching many observations exactly. We demonstrate the approach for basis pursuit denoise (BPDN) problems as well as for extensions of BPDN to matrix factorization, with applications to interpolation and denoising of 5D seismic data. The new methods are particularly promising for seismic applications, where the amplitude in the data varies significantly, and measurement noise in low-amplitude regions can wreak havoc for standard Gaussian error models.
Tasks	Denoising, Matrix Completion
Published	2018-11-28
URL	http://arxiv.org/abs/1811.11633v1
PDF	http://arxiv.org/pdf/1811.11633v1.pdf
PWC	https://paperswithcode.com/paper/basis-pursuit-denoise-with-nonsmooth
Repo
Framework

CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification


Title	CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
Authors	Jiawei Liu, Zheng-Jun Zha, Hongtao Xie, Zhiwei Xiong, Yongdong Zhang
Abstract	Person re-identification aims to identify the same pedestrian across non-overlapping camera views. Deep learning techniques have been applied for person re-identification recently, towards learning representation of pedestrian appearance. This paper presents a novel Contextual-Attentional Attribute-Appearance Network (CA3Net) for person re-identification. The CA3Net simultaneously exploits the complementarity between semantic attributes and visual appearance, the semantic context among attributes, visual attention on attributes as well as spatial dependencies among body parts, leading to discriminative and robust pedestrian representation. Specifically, an attribute network within CA3Net is designed with an Attention-LSTM module. It concentrates the network on latent image regions related to each attribute as well as exploits the semantic context among attributes by a LSTM module. An appearance network is developed to learn appearance features from the full body, horizontal and vertical body parts of pedestrians with spatial dependencies among body parts. The CA3Net jointly learns the attribute and appearance features in a multi-task learning manner, generating comprehensive representation of pedestrians. Extensive experiments on two challenging benchmarks, i.e., Market-1501 and DukeMTMC-reID datasets, have demonstrated the effectiveness of the proposed approach.
Tasks	Multi-Task Learning, Person Re-Identification
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07544v1
PDF	http://arxiv.org/pdf/1811.07544v1.pdf
PWC	https://paperswithcode.com/paper/ca3net-contextual-attentional-attribute
Repo
Framework

Trajectory-based Scene Understanding using Dirichlet Process Mixture Model


Title	Trajectory-based Scene Understanding using Dirichlet Process Mixture Model
Authors	Santhosh Kelathodi Kumaran, Debi Prosad Dogra, Partha Pratim Roy, Bidyut Baran Chaudhuri
Abstract	Appropriate modeling of a surveillance scene is essential for detection of anomalies in road traffic. Learning usual paths can provide valuable insight into road traffic conditions and thus can help in identifying unusual routes taken by commuters/vehicles. If usual traffic paths are learned in a nonparametric way, manual interventions in road marking road can be avoided. In this paper, we propose an unsupervised and nonparametric method to learn frequently used paths from the tracks of moving objects in $\Theta(kn)$ time, where $k$ denotes the number of paths and $n$ represents the number of tracks. In the proposed method, temporal dependencies of the moving objects are considered to make the clustering meaningful using Temporally Incremental Gravity Model (TIGM). In addition, the distance-based scene learning makes it intuitive to estimate the model parameters. Further, we have extended TIGM hierarchically as Dynamically Evolving Model (DEM) to represent notable traffic dynamics of a scene. Experimental validation reveals that the proposed method can learn a scene quickly without prior knowledge about the number of paths ($k$). We have compared the results with various state-of-the-art methods. We have also highlighted the advantages of the proposed method over existing techniques popularly used for designing traffic monitoring applications. It can be used for administrative decision making to control traffic at junctions or crowded places and generate alarm signals, if necessary.
Tasks	Decision Making, Scene Understanding
Published	2018-03-18
URL	https://arxiv.org/abs/1803.06613v3
PDF	https://arxiv.org/pdf/1803.06613v3.pdf
PWC	https://paperswithcode.com/paper/dynamic-state-model-for-analysis-of-traffic
Repo
Framework

Non-iterative recomputation of dense layers for performance improvement of DCNN


Title	Non-iterative recomputation of dense layers for performance improvement of DCNN
Authors	Yimin Yang, Q. M. Jonathan Wu, Xiexing Feng, Thangarajah Akilan
Abstract	An iterative method of learning has become a paradigm for training deep convolutional neural networks (DCNN). However, utilizing a non-iterative learning strategy can accelerate the training process of the DCNN and surprisingly such approach has been rarely explored by the deep learning (DL) community. It motivates this paper to introduce a non-iterative learning strategy that eliminates the backpropagation (BP) at the top dense or fully connected (FC) layers of DCNN, resulting in, lower training time and higher performance. The proposed method exploits the Moore-Penrose Inverse to pull back the current residual error to each FC layer, generating well-generalized features. Then using the recomputed features, i.e., the new generalized features the weights of each FC layer is computed according to the Moore-Penrose Inverse. We evaluate the proposed approach on six widely accepted object recognition benchmark datasets: Scene-15, CIFAR-10, CIFAR-100, SUN-397, Places365, and ImageNet. The experimental results show that the proposed method obtains significant improvements over 30 state-of-the-art methods. Interestingly, it also indicates that any DCNN with the proposed method can provide better performance than the same network with its original training based on BP.
Tasks	Object Recognition
Published	2018-09-14
URL	http://arxiv.org/abs/1809.05606v1
PDF	http://arxiv.org/pdf/1809.05606v1.pdf
PWC	https://paperswithcode.com/paper/non-iterative-recomputation-of-dense-layers
Repo
Framework