January 30, 2020

3206 words 16 mins read

Paper Group ANR 407

Zero Shot Learning on Simulated Robots. Robust Regression via Online Feature Selection under Adversarial Data Corruption. Latent-Variable Generative Models for Data-Efficient Text Classification. Implicit Regularization in Over-parameterized Neural Networks. Adaptive Honeypot Engagement through Reinforcement Learning of Semi-Markov Decision Process …

Zero Shot Learning on Simulated Robots


Title	Zero Shot Learning on Simulated Robots
Authors	Robert Kwiatkowski, Hod Lipson
Abstract	In this work we present a method for leveraging data from one source to learn how to do multiple new tasks. Task transfer is achieved using a self-model that encapsulates the dynamics of a system and serves as an environment for reinforcement learning. To study this approach, we train a self-models on various robot morphologies, using randomly sampled actions. Using a self-model, an initial state and corresponding actions, we can predict the next state. This predictive self-model is then used by a standard reinforcement learning algorithm to accomplish tasks without ever seeing a state from the “real” environment. These trained policies allow the robots to successfully achieve their goals in the “real” environment. We demonstrate that not only is training on the self-model far more data efficient than learning even a single task, but also that it allows for learning new tasks without necessitating any additional data collection, essentially allowing zero-shot learning of new tasks.
Tasks	Zero-Shot Learning
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01994v1
PDF	https://arxiv.org/pdf/1910.01994v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-learning-on-simulated-robots
Repo
Framework

Robust Regression via Online Feature Selection under Adversarial Data Corruption


Title	Robust Regression via Online Feature Selection under Adversarial Data Corruption
Authors	Xuchao Zhang, Shuo Lei, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu
Abstract	The presence of data corruption in user-generated streaming data, such as social media, motivates a new fundamental problem that learns reliable regression coefficient when features are not accessible entirely at one time. Until now, several important challenges still cannot be handled concurrently: 1) corrupted data estimation when only partial features are accessible; 2) online feature selection when data contains adversarial corruption; and 3) scaling to a massive dataset. This paper proposes a novel RObust regression algorithm via Online Feature Selection (\textit{RoOFS}) that concurrently addresses all the above challenges. Specifically, the algorithm iteratively updates the regression coefficients and the uncorrupted set via a robust online feature substitution method. We also prove that our algorithm has a restricted error bound compared to the optimal solution. Extensive empirical experiments in both synthetic and real-world datasets demonstrated that the effectiveness of our new method is superior to that of existing methods in the recovery of both feature selection and regression coefficients, with very competitive efficiency.
Tasks	Feature Selection
Published	2019-02-05
URL	http://arxiv.org/abs/1902.01729v1
PDF	http://arxiv.org/pdf/1902.01729v1.pdf
PWC	https://paperswithcode.com/paper/robust-regression-via-online-feature
Repo
Framework

Latent-Variable Generative Models for Data-Efficient Text Classification


Title	Latent-Variable Generative Models for Data-Efficient Text Classification
Authors	Xiaoan Ding, Kevin Gimpel
Abstract	Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et al., 2017; Lewis and Fan,2019). In this paper, we improve generative text classifiers by introducing discrete latent variables into the generative story, and explore several graphical model configurations. We parameterize the distributions using standard neural architectures used in conditional language modeling and perform learning by directly maximizing the log marginal likelihood via gradient-based optimization, which avoids the need to do expectation-maximization. We empirically characterize the performance of our models on six text classification datasets. The choice of where to include the latent variable has a significant impact on performance, with the strongest results obtained when using the latent variable as an auxiliary conditioning variable in the generation of the textual input. This model consistently outperforms both the generative and discriminative classifiers in small-data settings. We analyze our model by using it for controlled generation, finding that the latent variable captures interpretable properties of the data, even with very small training sets.
Tasks	Language Modelling, Text Classification, Zero-Shot Learning
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00382v1
PDF	https://arxiv.org/pdf/1910.00382v1.pdf
PWC	https://paperswithcode.com/paper/latent-variable-generative-models-for-data
Repo
Framework

Implicit Regularization in Over-parameterized Neural Networks


Title	Implicit Regularization in Over-parameterized Neural Networks
Authors	Masayoshi Kubo, Ryotaro Banno, Hidetaka Manabe, Masataka Minoji
Abstract	Over-parameterized neural networks generalize well in practice without any explicit regularization. Although it has not been proven yet, empirical evidence suggests that implicit regularization plays a crucial role in deep learning and prevents the network from overfitting. In this work, we introduce the gradient gap deviation and the gradient deflection as statistical measures corresponding to the network curvature and the Hessian matrix to analyze variations of network derivatives with respect to input parameters, and investigate how implicit regularization works in ReLU neural networks from both theoretical and empirical perspectives. Our result reveals that the network output between each pair of input samples is properly controlled by random initialization and stochastic gradient descent to keep interpolating between samples almost straight, which results in low complexity of over-parameterized neural networks.
Tasks
Published	2019-03-05
URL	http://arxiv.org/abs/1903.01997v1
PDF	http://arxiv.org/pdf/1903.01997v1.pdf
PWC	https://paperswithcode.com/paper/implicit-regularization-in-over-parameterized
Repo
Framework

Adaptive Honeypot Engagement through Reinforcement Learning of Semi-Markov Decision Processes


Title	Adaptive Honeypot Engagement through Reinforcement Learning of Semi-Markov Decision Processes
Authors	Linan Huang, Quanyan Zhu
Abstract	A honeynet is a promising active cyber defense mechanism. It reveals the fundamental Indicators of Compromise (IoCs) by luring attackers to conduct adversarial behaviors in a controlled and monitored environment. The active interaction at the honeynet brings a high reward but also introduces high implementation costs and risks of adversarial honeynet exploitation. In this work, we apply infinite-horizon Semi-Markov Decision Process (SMDP) to characterize a stochastic transition and sojourn time of attackers in the honeynet and quantify the reward-risk trade-off. In particular, we design adaptive long-term engagement policies shown to be risk-averse, cost-effective, and time-efficient. Numerical results have demonstrated that our adaptive engagement policies can quickly attract attackers to the target honeypot and engage them for a sufficiently long period to obtain worthy threat information. Meanwhile, the penetration probability is kept at a low level. The results show that the expected utility is robust against attackers of a large range of persistence and intelligence. Finally, we apply reinforcement learning to the SMDP to solve the curse of modeling. Under a prudent choice of the learning rate and exploration policy, we achieve a quick and robust convergence of the optimal policy and value.
Tasks
Published	2019-06-27
URL	https://arxiv.org/abs/1906.12182v2
PDF	https://arxiv.org/pdf/1906.12182v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-honeypot-engagement-through
Repo
Framework

One Sample Stochastic Frank-Wolfe


Title	One Sample Stochastic Frank-Wolfe
Authors	Mingrui Zhang, Zebang Shen, Aryan Mokhtari, Hamed Hassani, Amin Karbasi
Abstract	One of the beauties of the projected gradient descent method lies in its rather simple mechanism and yet stable behavior with inexact, stochastic gradients, which has led to its wide-spread use in many machine learning applications. However, once we replace the projection operator with a simpler linear program, as is done in the Frank-Wolfe method, both simplicity and stability take a serious hit. The aim of this paper is to bring them back without sacrificing the efficiency. In this paper, we propose the first one-sample stochastic Frank-Wolfe algorithm, called 1-SFW, that avoids the need to carefully tune the batch size, step size, learning rate, and other complicated hyper parameters. In particular, 1-SFW achieves the optimal convergence rate of $\mathcal{O}(1/\epsilon^2)$ for reaching an $\epsilon$-suboptimal solution in the stochastic convex setting, and a $(1-1/e)-\epsilon$ approximate solution for a stochastic monotone DR-submodular maximization problem. Moreover, in a general non-convex setting, 1-SFW finds an $\epsilon$-first-order stationary point after at most $\mathcal{O}(1/\epsilon^3)$ iterations, achieving the current best known convergence rate. All of this is possible by designing a novel unbiased momentum estimator that governs the stability of the optimization process while using a single sample at each iteration.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04322v1
PDF	https://arxiv.org/pdf/1910.04322v1.pdf
PWC	https://paperswithcode.com/paper/one-sample-stochastic-frank-wolfe
Repo
Framework

Edge-Semantic Learning Strategy for Layout Estimation in Indoor Environment


Title	Edge-Semantic Learning Strategy for Layout Estimation in Indoor Environment
Authors	Weidong Zhang, Wei Zhang, Jason Gu
Abstract	Visual cognition of the indoor environment can benefit from the spatial layout estimation, which is to represent an indoor scene with a 2D box on a monocular image. In this paper, we propose to fully exploit the edge and semantic information of a room image for layout estimation. More specifically, we present an encoder-decoder network with shared encoder and two separate decoders, which are composed of multiple deconvolution (transposed convolution) layers, to jointly learn the edge maps and semantic labels of a room image. We combine these two network predictions in a scoring function to evaluate the quality of the layouts, which are generated by ray sampling and from a predefined layout pool. Guided by the scoring function, we apply a novel refinement strategy to further optimize the layout hypotheses. Experimental results show that the proposed network can yield accurate estimates of edge maps and semantic labels. By fully utilizing the two different types of labels, the proposed method achieves state-of-the-art layout estimation performance on benchmark datasets.
Tasks
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00621v1
PDF	http://arxiv.org/pdf/1901.00621v1.pdf
PWC	https://paperswithcode.com/paper/edge-semantic-learning-strategy-for-layout
Repo
Framework

Single-Path NAS: Device-Aware Efficient ConvNet Design


Title	Single-Path NAS: Device-Aware Efficient ConvNet Design
Authors	Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu
Abstract	Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a challenging problem due to the combinatorially large design space and search time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing device-efficient ConvNets in less than 4 hours. 1. Novel NAS formulation: our method introduces a single-path, over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters. 2. NAS efficiency: Our method decreases the NAS search cost down to 8 epochs (30 TPU-hours), i.e., up to 5,000x faster compared to prior work. 3. On-device image classification: Single-Path NAS achieves 74.96% top-1 accuracy on ImageNet with 79ms inference latency on a Pixel 1 phone, which is state-of-the-art accuracy compared to NAS methods with similar latency (<80ms).
Tasks	Image Classification, Neural Architecture Search
Published	2019-05-10
URL	https://arxiv.org/abs/1905.04159v1
PDF	https://arxiv.org/pdf/1905.04159v1.pdf
PWC	https://paperswithcode.com/paper/single-path-nas-device-aware-efficient
Repo
Framework

Interactive Variance Attention based Online Spoiler Detection for Time-Sync Comments


Title	Interactive Variance Attention based Online Spoiler Detection for Time-Sync Comments
Authors	Wenmian Yang, Weijia Jia, Wenyuan Gao, Xiaojie Zhou, Yutao Luo
Abstract	Nowadays, time-sync comment (TSC), a new form of interactive comments, has become increasingly popular in Chinese video websites. By posting TSCs, people can easily express their feelings and exchange their opinions with others when watching online videos. However, some spoilers appear among the TSCs. These spoilers reveal crucial plots in videos that ruin people’s surprise when they first watch the video. In this paper, we proposed a novel Similarity-Based Network with Interactive Variance Attention (SBN-IVA) to classify comments as spoilers or not. In this framework, we firstly extract textual features of TSCs through the word-level attentive encoder. We design Similarity-Based Network (SBN) to acquire neighbor and keyframe similarity according to semantic similarity and timestamps of TSCs. Then, we implement Interactive Variance Attention (IVA) to eliminate the impact of noise comments. Finally, we obtain the likelihood of spoiler based on the difference between the neighbor and keyframe similarity. Experiments show SBN-IVA is on average 11.2% higher than the state-of-the-art method on F1-score in baselines.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2019-08-09
URL	https://arxiv.org/abs/1908.03451v2
PDF	https://arxiv.org/pdf/1908.03451v2.pdf
PWC	https://paperswithcode.com/paper/interactive-variance-attention-based-online
Repo
Framework

Active Goal Recognition


Title	Active Goal Recognition
Authors	Christopher Amato, Andrea Baisero
Abstract	To coordinate with other systems, agents must be able to determine what the systems are currently doing and predict what they will be doing in the future—plan and goal recognition. There are many methods for plan and goal recognition, but they assume a passive observer that continually monitors the target system. Real-world domains, where information gathering has a cost (e.g., moving a camera or a robot, or time taken away from another task), will often require a more active observer. We propose to combine goal recognition with other observer tasks in order to obtain \emph{active goal recognition} (AGR). We discuss this problem and provide a model and preliminary experimental results for one form of this composite problem. As expected, the results show that optimal behavior in AGR problems balance information gathering with other actions (e.g., task completion) such as to achieve all tasks jointly and efficiently. We hope that our formulation opens the door for extensive further research on this interesting and realistic problem.
Tasks
Published	2019-09-24
URL	https://arxiv.org/abs/1909.11173v1
PDF	https://arxiv.org/pdf/1909.11173v1.pdf
PWC	https://paperswithcode.com/paper/active-goal-recognition
Repo
Framework

Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network


Title	Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network
Authors	Longyin Wen, Dawei Du, Pengfei Zhu, Qinghua Hu, Qilong Wang, Liefeng Bo, Siwei Lyu
Abstract	This paper proposes a space-time multi-scale attention network (STANet) to solve density map estimation, localization and tracking in dense crowds of video clips captured by drones with arbitrary crowd density, perspective, and flight altitude. Our STANet method aggregates multi-scale feature maps in sequential frames to exploit the temporal coherency, and then predict the density maps, localize the targets, and associate them in crowds simultaneously. A coarse-to-fine process is designed to gradually apply the attention module on the aggregated multi-scale feature maps to enforce the network to exploit the discriminative space-time features for better performance. The whole network is trained in an end-to-end manner with the multi-task loss, formed by three terms, i.e., the density map loss, localization loss and association loss. The non-maximal suppression followed by the min-cost flow framework is used to generate the trajectories of targets’ in scenarios. Since existing crowd counting datasets merely focus on crowd counting in static cameras rather than density map estimation, counting and tracking in crowds on drones, we have collected a new large-scale drone-based dataset, DroneCrowd, formed by 112 video clips with 33,600 high resolution frames (i.e., 1920x1080) captured in 70 different scenarios. With intensive amount of effort, our dataset provides 20,800 people trajectories with 4.8 million head annotations and several video-level attributes in sequences. Extensive experiments are conducted on two challenging public datasets, i.e., Shanghaitech and UCF-QNRF, and our DroneCrowd, to demonstrate that STANet achieves favorable performance against the state-of-the-arts. The datasets and codes can be found at https://github.com/VisDrone.
Tasks	Crowd Counting
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01811v1
PDF	https://arxiv.org/pdf/1912.01811v1.pdf
PWC	https://paperswithcode.com/paper/drone-based-joint-density-map-estimation
Repo
Framework

Self Organizing Supply Chains for Micro-Prediction: Present and Future uses of the ROAR Protocol


Title	Self Organizing Supply Chains for Micro-Prediction: Present and Future uses of the ROAR Protocol
Authors	Peter Cotton
Abstract	A multi-agent system is trialed as a means of crowd-sourcing inexpensive but high quality streams of predictions. Each agent is a microservice embodying statistical models and endowed with economic self-interest. The ability to fork and modify simple agents is granted to a large number of employees in a firm and empirical lessons are reported. We suggest that one plausible trajectory for this project is the creation of a Prediction Web.
Tasks
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07514v1
PDF	https://arxiv.org/pdf/1907.07514v1.pdf
PWC	https://paperswithcode.com/paper/self-organizing-supply-chains-for-micro
Repo
Framework

Exploring Semi-Automatic Map Labeling


Title	Exploring Semi-Automatic Map Labeling
Authors	Fabian Klute, Guangping Li, Raphael Löffler, Martin Nöllenburg, Manuela Schmidt
Abstract	Label placement in maps is a very challenging task that is critical for the overall map quality. Most previous work focused on designing and implementing fully automatic solutions, but the resulting visual and aesthetic quality has not reached the same level of sophistication that skilled human cartographers achieve. We investigate a different strategy that combines the strengths of humans and algorithms. In our proposed method, first an initial labeling is computed that has many well-placed labels but is not claiming to be perfect. Instead it serves as a starting point for an expert user who can then interactively and locally modify the labeling where necessary. In an iterative human-in-the-loop process alternating between user modifications and local algorithmic updates and refinements the labeling can be tuned to the user’s needs. We demonstrate our approach by performing different possible modification steps in a sample workflow with a prototypical interactive labeling editor. Further, we report computational performance results from a simulation experiment in QGIS, which investigates the differences between exact and heuristic algorithms for semi-automatic map labeling. To that end, we compare several alternatives for recomputing the labeling after local modifications and updates, as a major ingredient for an interactive labeling editor.
Tasks
Published	2019-10-17
URL	https://arxiv.org/abs/1910.07799v1
PDF	https://arxiv.org/pdf/1910.07799v1.pdf
PWC	https://paperswithcode.com/paper/exploring-semi-automatic-map-labeling
Repo
Framework

Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization


Title	Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization
Authors	Feihu Huang, Bin Gu, Zhouyuan Huo, Songcan Chen, Heng Huang
Abstract	Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems. However, in some machine learning problems such as the bandit model and the black-box learning problem, proximal gradient method could fail because the explicit gradients of these problems are difficult or infeasible to obtain. The gradient-free (zeroth-order) method can address these problems because only the objective function values are required in the optimization. Recently, the first zeroth-order proximal stochastic algorithm was proposed to solve the nonconvex nonsmooth problems. However, its convergence rate is $O(\frac{1}{\sqrt{T}})$ for the nonconvex problems, which is significantly slower than the best convergence rate $O(\frac{1}{T})$ of the zeroth-order stochastic algorithm, where $T$ is the iteration number. To fill this gap, in the paper, we propose a class of faster zeroth-order proximal stochastic methods with the variance reduction techniques of SVRG and SAGA, which are denoted as ZO-ProxSVRG and ZO-ProxSAGA, respectively. In theoretical analysis, we address the main challenge that an unbiased estimate of the true gradient does not hold in the zeroth-order case, which was required in previous theoretical analysis of both SVRG and SAGA. Moreover, we prove that both ZO-ProxSVRG and ZO-ProxSAGA algorithms have $O(\frac{1}{T})$ convergence rates. Finally, the experimental results verify that our algorithms have a faster convergence rate than the existing zeroth-order proximal stochastic algorithm.
Tasks
Published	2019-02-16
URL	http://arxiv.org/abs/1902.06158v1
PDF	http://arxiv.org/pdf/1902.06158v1.pdf
PWC	https://paperswithcode.com/paper/faster-gradient-free-proximal-stochastic
Repo
Framework

Online Signature Verification Based on Writer Specific Feature Selection and Fuzzy Similarity Measure


Title	Online Signature Verification Based on Writer Specific Feature Selection and Fuzzy Similarity Measure
Authors	Chandra Sekhar V, Prerana Mukherjee, D. S. Guru, Viswanath Pulabaigari
Abstract	Online Signature Verification (OSV) is a widely used biometric attribute for user behavioral characteristic verification in digital forensics. In this manuscript, owing to large intra-individual variability, a novel method for OSV based on an interval symbolic representation and a fuzzy similarity measure grounded on writer specific parameter selection is proposed. The two parameters, namely, writer specific acceptance threshold and optimal feature set to be used for authenticating the writer are selected based on minimum equal error rate (EER) attained during parameter fixation phase using the training signature samples. This is in variation to current techniques for OSV, which are primarily writer independent, in which a common set of features and acceptance threshold are chosen. To prove the robustness of our system, we have exhaustively assessed our system with four standard datasets i.e. MCYT-100 (DB1), MCYT-330 (DB2), SUSIG-Visual corpus and SVC-2004- Task2. Experimental outcome confirms the effectiveness of fuzzy similarity metric-based writer dependent parameter selection for OSV by achieving a lower error rate as compared to many recent and state-of-the art OSV models.
Tasks	Feature Selection
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08574v1
PDF	https://arxiv.org/pdf/1905.08574v1.pdf
PWC	https://paperswithcode.com/paper/online-signature-verification-based-on-writer
Repo
Framework