Paper Group ANR 566
Graph Neural Networks for Learning Robot Team Coordination. Privacy-preserving Machine Learning through Data Obfuscation. Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation. Dynamic and Static Topic Model for Analyzing Time-Series Document Collections. D …
Graph Neural Networks for Learning Robot Team Coordination
| Title | Graph Neural Networks for Learning Robot Team Coordination |
| Authors | Amanda Prorok |
| Abstract | This paper shows how Graph Neural Networks can be used for learning distributed coordination mechanisms in connected teams of robots. We capture the relational aspect of robot coordination by modeling the robot team as a graph, where each robot is a node, and edges represent communication links. During training, robots learn how to pass messages and update internal states, so that a target behavior is reached. As a proxy for more complex problems, this short paper considers the problem where each robot must locally estimate the algebraic connectivity of the team’s network topology. |
| Tasks | |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03737v2 |
| http://arxiv.org/pdf/1805.03737v2.pdf | |
| PWC | https://paperswithcode.com/paper/graph-neural-networks-for-learning-robot-team |
| Repo | |
| Framework | |
Privacy-preserving Machine Learning through Data Obfuscation
| Title | Privacy-preserving Machine Learning through Data Obfuscation |
| Authors | Tianwei Zhang, Zecheng He, Ruby B. Lee |
| Abstract | As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and serving tasks in the cloud, it is important to protect the privacy of sensitive samples in the training dataset and prevent information leakage to untrusted third parties. Past work have shown that a malicious machine learning service provider or end user can easily extract critical information about the training samples, from the model parameters or even just model outputs. In this paper, we propose a novel and generic methodology to preserve the privacy of training data in machine learning applications. Specifically we introduce an obfuscate function and apply it to the training data before feeding them to the model training task. This function adds random noise to existing samples, or augments the dataset with new samples. By doing so sensitive information about the properties of individual samples, or statistical properties of a group of samples, is hidden. Meanwhile the model trained from the obfuscated dataset can still achieve high accuracy. With this approach, the customers can safely disclose the data or models to third-party providers or end users without the need to worry about data privacy. Our experiments show that this approach can effective defeat four existing types of machine learning privacy attacks at negligible accuracy cost. |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.01860v2 |
| http://arxiv.org/pdf/1807.01860v2.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-machine-learning-through |
| Repo | |
| Framework | |
Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation
| Title | Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation |
| Authors | Tomoya Murata, Taiji Suzuki |
| Abstract | We develop new stochastic gradient methods for efficiently solving sparse linear regression in a partial attribute observation setting, where learners are only allowed to observe a fixed number of actively chosen attributes per example at training and prediction times. It is shown that the methods achieve essentially a sample complexity of $O(1/\varepsilon)$ to attain an error of $\varepsilon$ under a variant of restricted eigenvalue condition, and the rate has better dependency on the problem dimension than existing methods. Particularly, if the smallest magnitude of the non-zero components of the optimal solution is not too small, the rate of our proposed {\it Hybrid} algorithm can be boosted to near the minimax optimal sample complexity of {\it full information} algorithms. The core ideas are (i) efficient construction of an unbiased gradient estimator by the iterative usage of the hard thresholding operator for configuring an exploration algorithm; and (ii) an adaptive combination of the exploration and an exploitation algorithms for quickly identifying the support of the optimum and efficiently searching the optimal parameter in its support. Experimental results are presented to validate our theoretical findings and the superiority of our proposed methods. |
| Tasks | |
| Published | 2018-09-05 |
| URL | http://arxiv.org/abs/1809.01765v3 |
| http://arxiv.org/pdf/1809.01765v3.pdf | |
| PWC | https://paperswithcode.com/paper/sample-efficient-stochastic-gradient |
| Repo | |
| Framework | |
Dynamic and Static Topic Model for Analyzing Time-Series Document Collections
| Title | Dynamic and Static Topic Model for Analyzing Time-Series Document Collections |
| Authors | Rem Hida, Naoya Takeishi, Takehisa Yairi, Koichi Hori |
| Abstract | For extracting meaningful topics from texts, their structures should be considered properly. In this paper, we aim to analyze structured time-series documents such as a collection of news articles and a series of scientific papers, wherein topics evolve along time depending on multiple topics in the past and are also related to each other at each time. To this end, we propose a dynamic and static topic model, which simultaneously considers the dynamic structures of the temporal topic evolution and the static structures of the topic hierarchy at each time. We show the results of experiments on collections of scientific papers, in which the proposed method outperformed conventional models. Moreover, we show an example of extracted topic structures, which we found helpful for analyzing research activities. |
| Tasks | Time Series |
| Published | 2018-05-06 |
| URL | http://arxiv.org/abs/1805.02203v1 |
| http://arxiv.org/pdf/1805.02203v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-and-static-topic-model-for-analyzing |
| Repo | |
| Framework | |
Drug Selection via Joint Push and Learning to Rank
| Title | Drug Selection via Joint Push and Learning to Rank |
| Authors | Yicheng He, Junfeng Liu, Xia Ning |
| Abstract | Selecting the right drugs for the right patients is a primary goal of precision medicine. In this manuscript, we consider the problem of cancer drug selection in a learning-to-rank framework. We have formulated the cancer drug selection problem as to accurately predicting 1). the ranking positions of sensitive drugs and 2). the ranking orders among sensitive drugs in cancer cell lines based on their responses to cancer drugs. We have developed a new learning-to-rank method, denoted as pLETORg , that predicts drug ranking structures in each cell line via using drug latent vectors and cell line latent vectors. The pLETORg method learns such latent vectors through explicitly enforcing that, in the drug ranking list of each cell line, the sensitive drugs are pushed above insensitive drugs, and meanwhile the ranking orders among sensitive drugs are correct. Genomics information on cell lines is leveraged in learning the latent vectors. Our experimental results on a benchmark cell line-drug response dataset demonstrate that the new pLETORg significantly outperforms the state-of-the-art method in prioritizing new sensitive drugs. |
| Tasks | Learning-To-Rank |
| Published | 2018-01-23 |
| URL | http://arxiv.org/abs/1801.07691v2 |
| http://arxiv.org/pdf/1801.07691v2.pdf | |
| PWC | https://paperswithcode.com/paper/drug-selection-via-joint-push-and-learning-to |
| Repo | |
| Framework | |
Dynamic Feature Generation Network for Answer Selection
| Title | Dynamic Feature Generation Network for Answer Selection |
| Authors | Longxuan Ma, Pengfei Wang, Lei Zhang |
| Abstract | Extracting appropriate features to represent a corpus is an important task for textual mining. Previous attention based work usually enhance feature at the lexical level, which lacks the exploration of feature augmentation at the sentence level. In this paper, we exploit a Dynamic Feature Generation Network (DFGN) to solve this problem. Specifically, DFGN generates features based on a variety of attention mechanisms and attaches features to sentence representation. Then a thresholder is designed to filter the mined features automatically. DFGN extracts the most significant characteristics from datasets to keep its practicability and robustness. Experimental results on multiple well-known answer selection datasets show that our proposed approach significantly outperforms state-of-the-art baselines. We give a detailed analysis of the experiments to illustrate why DFGN provides excellent retrieval and interpretative ability. |
| Tasks | Answer Selection |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.05366v1 |
| http://arxiv.org/pdf/1812.05366v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-feature-generation-network-for-answer |
| Repo | |
| Framework | |
Text Detection and Recognition in images: A survey
| Title | Text Detection and Recognition in images: A survey |
| Authors | Tanvi Goswami, Zankhana Barad, Prof. Nikita P. Desai |
| Abstract | Text Detection and recognition is a one of the important aspect of image processing. This paper analyzes and compares the methods to handle this task. It summarizes the fundamental problems and enumerates factors that need consideration when addressing these problems. Existing techniques are categorized as either stepwise or integrated and sub-problems are highlighted including digit localization, verification, segmentation and recognition. Special issues associated with the enhancement of degraded text and the processing of video text and multi-oriented text are also addressed. The categories and sub-categories of text are illustrated, benchmark datasets are enumerated, and the performance of the most representative approaches is compared. This review also provides a fundamental comparison and analysis of the remaining problems in the field. |
| Tasks | |
| Published | 2018-03-20 |
| URL | http://arxiv.org/abs/1803.07278v2 |
| http://arxiv.org/pdf/1803.07278v2.pdf | |
| PWC | https://paperswithcode.com/paper/text-detection-and-recognition-in-images-a |
| Repo | |
| Framework | |
Multichannel Sparse Blind Deconvolution on the Sphere
| Title | Multichannel Sparse Blind Deconvolution on the Sphere |
| Authors | Yanjun Li, Yoram Bresler |
| Abstract | Multichannel blind deconvolution is the problem of recovering an unknown signal $f$ and multiple unknown channels $x_i$ from their circular convolution $y_i=x_i \circledast f$ ($i=1,2,\dots,N$). We consider the case where the $x_i$'s are sparse, and convolution with $f$ is invertible. Our nonconvex optimization formulation solves for a filter $h$ on the unit sphere that produces sparse output $y_i\circledast h$. Under some technical assumptions, we show that all local minima of the objective function correspond to the inverse filter of $f$ up to an inherent sign and shift ambiguity, and all saddle points have strictly negative curvatures. This geometric structure allows successful recovery of $f$ and $x_i$ using a simple manifold gradient descent (MGD) algorithm. Our theoretical findings are complemented by numerical experiments, which demonstrate superior performance of the proposed approach over the previous methods. |
| Tasks | |
| Published | 2018-05-26 |
| URL | http://arxiv.org/abs/1805.10437v2 |
| http://arxiv.org/pdf/1805.10437v2.pdf | |
| PWC | https://paperswithcode.com/paper/global-geometry-of-multichannel-sparse-blind |
| Repo | |
| Framework | |
Hypertree Decompositions Revisited for PGMs
| Title | Hypertree Decompositions Revisited for PGMs |
| Authors | Aarthy Shivram Arun, Sai Vikneshwar Mani Jayaraman, Christopher Ré, Atri Rudra |
| Abstract | We revisit the classical problem of exact inference on probabilistic graphical models (PGMs). Our algorithm is based on recent \emph{worst-case optimal database join} algorithms, which can be asymptotically faster than traditional data processing methods. We present the first empirical evaluation of these algorithms via JoinInfer – a new exact inference engine. We empirically explore the properties of the data for which our engine can be expected to outperform traditional inference engines, refining current theoretical notions. Further, JoinInfer outperforms existing state-of-the-art inference engines (ACE, IJGP and libDAI) on some standard benchmark datasets by up to a factor of 630x. Finally, we propose a promising data-driven heuristic that extends JoinInfer to automatically tailor its parameters and/or switch to the traditional inference algorithms. |
| Tasks | |
| Published | 2018-07-02 |
| URL | http://arxiv.org/abs/1807.00886v1 |
| http://arxiv.org/pdf/1807.00886v1.pdf | |
| PWC | https://paperswithcode.com/paper/hypertree-decompositions-revisited-for-pgms |
| Repo | |
| Framework | |
Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions
| Title | Optimal Sensor Data Fusion Architecture for Object Detection in Adverse Weather Conditions |
| Authors | Andreas Pfeuffer, Klaus Dietmayer |
| Abstract | A good and robust sensor data fusion in diverse weather conditions is a quite challenging task. There are several fusion architectures in the literature, e.g. the sensor data can be fused right at the beginning (Early Fusion), or they can be first processed separately and then concatenated later (Late Fusion). In this work, different fusion architectures are compared and evaluated by means of object detection tasks, in which the goal is to recognize and localize predefined objects in a stream of data. Usually, state-of-the-art object detectors based on neural networks are highly optimized for good weather conditions, since the well-known benchmarks only consist of sensor data recorded in optimal weather conditions. Therefore, the performance of these approaches decreases enormously or even fails in adverse weather conditions. In this work, different sensor fusion architectures are compared for good and adverse weather conditions for finding the optimal fusion architecture for diverse weather situations. A new training strategy is also introduced such that the performance of the object detector is greatly enhanced in adverse weather scenarios or if a sensor fails. Furthermore, the paper responds to the question if the detection accuracy can be increased further by providing the neural network with a-priori knowledge such as the spatial calibration of the sensors. |
| Tasks | Calibration, Object Detection, Sensor Fusion |
| Published | 2018-07-06 |
| URL | http://arxiv.org/abs/1807.02323v1 |
| http://arxiv.org/pdf/1807.02323v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-sensor-data-fusion-architecture-for |
| Repo | |
| Framework | |
Semantic Road Layout Understanding by Generative Adversarial Inpainting
| Title | Semantic Road Layout Understanding by Generative Adversarial Inpainting |
| Authors | Lorenzo Berlincioni, Federico Becattini, Leonardo Galteri, Lorenzo Seidenari, Alberto Del Bimbo |
| Abstract | Autonomous driving is becoming a reality, yet vehicles still need to rely on complex sensor fusion to understand the scene they act in. The ability to discern static environment and dynamic entities provides a comprehension of the road layout that poses constraints to the reasoning process about moving objects. We pursue this through a GAN-based semantic segmentation inpainting model to remove all dynamic objects from the scene and focus on understanding its static components such as streets, sidewalks and buildings. We evaluate this task on the Cityscapes dataset and on a novel synthetically generated dataset obtained with the CARLA simulator and specifically designed to quantitatively evaluate semantic segmentation inpaintings. We compare our methods with a variety of baselines working both in the RGB and segmentation domains. |
| Tasks | Autonomous Driving, Semantic Segmentation, Sensor Fusion |
| Published | 2018-05-29 |
| URL | http://arxiv.org/abs/1805.11746v2 |
| http://arxiv.org/pdf/1805.11746v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-road-layout-understanding-by |
| Repo | |
| Framework | |
Multi-Sensor Conflict Measurement and Information Fusion
| Title | Multi-Sensor Conflict Measurement and Information Fusion |
| Authors | Pan Wei, John E. Ball, Derek T. Anderson |
| Abstract | In sensing applications where multiple sensors observe the same scene, fusing sensor outputs can provide improved results. However, if some of the sensors are providing lower quality outputs, the fused results can be degraded. In this work, a multi-sensor conflict measure is proposed which estimates multi-sensor conflict by representing each sensor output as interval-valued information and examines the sensor output overlaps on all possible n-tuple sensor combinations. The conflict is based on the sizes of the intervals and how many sensors output values lie in these intervals. In this work, conflict is defined in terms of how little the output from multiple sensors overlap. That is, high degrees of overlap mean low sensor conflict, while low degrees of overlap mean high conflict. This work is a preliminary step towards a robust conflict and sensor fusion framework. In addition, a sensor fusion algorithm is proposed based on a weighted sum of sensor outputs, where the weights for each sensor diminish as the conflict measure increases. The proposed methods can be utilized to (1) assess a measure of multi-sensor conflict, and (2) improve sensor output fusion by lessening weighting for sensors with high conflict. Using this measure, a simulated example is given to explain the mechanics of calculating the conflict measure, and stereo camera 3D outputs are analyzed and fused. In the stereo camera case, the sensor output is corrupted by additive impulse noise, DC offset, and Gaussian noise. Impulse noise is common in sensors due to intermittent interference, a DC offset a sensor bias or registration error, and Gaussian noise represents a sensor output with low SNR. The results show that sensor output fusion based on the conflict measure shows improved accuracy over a simple averaging fusion strategy. |
| Tasks | Sensor Fusion |
| Published | 2018-03-12 |
| URL | http://arxiv.org/abs/1803.04551v1 |
| http://arxiv.org/pdf/1803.04551v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-sensor-conflict-measurement-and |
| Repo | |
| Framework | |
Finding Mixed Nash Equilibria of Generative Adversarial Networks
| Title | Finding Mixed Nash Equilibria of Generative Adversarial Networks |
| Authors | Ya-Ping Hsieh, Chen Liu, Volkan Cevher |
| Abstract | We reconsider the training objective of Generative Adversarial Networks (GANs) from the mixed Nash Equilibria (NE) perspective. Inspired by the classical prox methods, we develop a novel algorithmic framework for GANs via an infinite-dimensional two-player game and prove rigorous convergence rates to the mixed NE, resolving the longstanding problem that no provably convergent algorithm exists for general GANs. We then propose a principled procedure to reduce our novel prox methods to simple sampling routines, leading to practically efficient algorithms. Finally, we provide experimental evidence that our approach outperforms methods that seek pure strategy equilibria, such as SGD, Adam, and RMSProp, both in speed and quality. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1811.02002v1 |
| http://arxiv.org/pdf/1811.02002v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-mixed-nash-equilibria-of-generative |
| Repo | |
| Framework | |
Simultaneous Segmentation and Classification of Bone Surfaces from Ultrasound Using a Multi-feature Guided CNN
| Title | Simultaneous Segmentation and Classification of Bone Surfaces from Ultrasound Using a Multi-feature Guided CNN |
| Authors | Puyang Wang, Vishal M. Patel, Ilker Hacihaliloglu |
| Abstract | Various imaging artifacts, low signal-to-noise ratio, and bone surfaces appearing several millimeters in thickness have hindered the success of ultrasound (US) guided computer assisted orthopedic surgery procedures. In this work, a multi-feature guided convolutional neural network (CNN) architecture is proposed for simultaneous enhancement, segmentation, and classification of bone surfaces from US data. The proposed CNN consists of two main parts: a pre-enhancing net, that takes the concatenation of B-mode US scan and three filtered image features for the enhancement of bone surfaces, and a modified U-net with a classification layer. The proposed method was validated on 650 in vivo US scans collected using two US machines, by scanning knee, femur, distal radius and tibia bones. Validation, against expert annotation, achieved statistically significant improvements in segmentation of bone surfaces compared to state-of-the-art. |
| Tasks | |
| Published | 2018-06-26 |
| URL | http://arxiv.org/abs/1806.09766v1 |
| http://arxiv.org/pdf/1806.09766v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-segmentation-and-classification |
| Repo | |
| Framework | |
Secure Face Matching Using Fully Homomorphic Encryption
| Title | Secure Face Matching Using Fully Homomorphic Encryption |
| Authors | Vishnu Naresh Boddeti |
| Abstract | Face recognition technology has demonstrated tremendous progress over the past few years, primarily due to advances in representation learning. As we witness the widespread adoption of these systems, it is imperative to consider the security of face representations. In this paper, we explore the practicality of using a fully homomorphic encryption based framework to secure a database of face templates. This framework is designed to preserve the privacy of users and prevent information leakage from the templates, while maintaining their utility through template matching directly in the encrypted domain. Additionally, we also explore a batching and dimensionality reduction scheme to trade-off face matching accuracy and computational complexity. Experiments on benchmark face datasets (LFW, IJB-A, IJB-B, CASIA) indicate that secure face matching can be practically feasible (16 KB template size and 0.01 sec per match pair for 512-dimensional features from SphereFace) while exhibiting minimal loss in matching performance. |
| Tasks | Dimensionality Reduction, Face Recognition, Representation Learning |
| Published | 2018-05-01 |
| URL | http://arxiv.org/abs/1805.00577v2 |
| http://arxiv.org/pdf/1805.00577v2.pdf | |
| PWC | https://paperswithcode.com/paper/secure-face-matching-using-fully-homomorphic |
| Repo | |
| Framework | |
