July 28, 2019

3242 words 16 mins read

Paper Group ANR 435

Area Protection in Adversarial Path-Finding Scenarios with Multiple Mobile Agents on Graphs: a theoretical and experimental study of target-allocation strategies for defense coordination. Stochastic Graphlet Embedding. Molecular Generation with Recurrent Neural Networks (RNNs). Real-time Egocentric Gesture Recognition on Mobile Head Mounted Display …

Area Protection in Adversarial Path-Finding Scenarios with Multiple Mobile Agents on Graphs: a theoretical and experimental study of target-allocation strategies for defense coordination


Title	Area Protection in Adversarial Path-Finding Scenarios with Multiple Mobile Agents on Graphs: a theoretical and experimental study of target-allocation strategies for defense coordination
Authors	Marika Ivanová, Pavel Surynek
Abstract	We address a problem of area protection in graph-based scenarios with multiple agents. The problem consists of two adversarial teams of agents that move in an undirected graph shared by both teams. Agents are placed in vertices of the graph; at most one agent can occupy a vertex; and they can move into adjacent vertices in a conflict free way. Teams have asymmetric goals: the aim of one team - attackers - is to invade into given area while the aim of the opponent team - defenders - is to protect the area from being entered by attackers by occupying selected vertices. We study strategies for allocating vertices to be occupied by the team of defenders to block attacking agents. We show that the decision version of the problem of area protection is PSPACE-hard under the assumption that agents can allocate their target vertices multiple times. Further we develop various on-line vertex-allocation strategies for the defender team in a simplified variant of the problem with single stage vertex allocation and evaluated their performance in multiple benchmarks. The success of a strategy is heavily dependent on the type of the instance, and so one of the contributions of this work is that we identify suitable vertex-allocation strategies for diverse instance types. In particular, we introduce a simulation-based method that identifies and tries to capture bottlenecks in the graph, that are frequently used by the attackers. Our experimental evaluation suggests that this method often allows a successful defense even in instances where the attackers significantly outnumber the defenders.
Tasks
Published	2017-08-24
URL	http://arxiv.org/abs/1708.07285v1
PDF	http://arxiv.org/pdf/1708.07285v1.pdf
PWC	https://paperswithcode.com/paper/area-protection-in-adversarial-path-finding
Repo
Framework

Stochastic Graphlet Embedding


Title	Stochastic Graphlet Embedding
Authors	Anjan Dutta, Hichem Sahbi
Abstract	Graph-based methods are known to be successful in many machine learning and pattern classification tasks. These methods consider semi-structured data as graphs where nodes correspond to primitives (parts, interest points, segments, etc.) and edges characterize the relationships between these primitives. However, these non-vectorial graph data cannot be straightforwardly plugged into off-the-shelf machine learning algorithms without a preliminary step of – explicit/implicit – graph vectorization and embedding. This embedding process should be resilient to intra-class graph variations while being highly discriminant. In this paper, we propose a novel high-order stochastic graphlet embedding (SGE) that maps graphs into vector spaces. Our main contribution includes a new stochastic search procedure that efficiently parses a given graph and extracts/samples unlimitedly high-order graphlets. We consider these graphlets, with increasing orders, to model local primitives as well as their increasingly complex interactions. In order to build our graph representation, we measure the distribution of these graphlets into a given graph, using particular hash functions that efficiently assign sampled graphlets into isomorphic sets with a very low probability of collision. When combined with maximum margin classifiers, these graphlet-based representations have positive impact on the performance of pattern comparison and recognition as corroborated through extensive experiments using standard benchmark databases.
Tasks
Published	2017-02-01
URL	http://arxiv.org/abs/1702.00156v3
PDF	http://arxiv.org/pdf/1702.00156v3.pdf
PWC	https://paperswithcode.com/paper/stochastic-graphlet-embedding
Repo
Framework

Molecular Generation with Recurrent Neural Networks (RNNs)


Title	Molecular Generation with Recurrent Neural Networks (RNNs)
Authors	Esben Jannik Bjerrum, Richard Threlfall
Abstract	The potential number of drug like small molecules is estimated to be between 10^23 and 10^60 while current databases of known compounds are orders of magnitude smaller with approximately 10^8 compounds. This discrepancy has led to an interest in generating virtual libraries using hand crafted chemical rules and fragment based methods to cover a larger area of chemical space and generate chemical libraries for use in in silico drug discovery endeavors. Here it is explored to what extent a recurrent neural network with long short term memory cells can figure out sensible chemical rules and generate synthesizable molecules by being trained on existing compounds encoded as SMILES. The networks can to a high extent generate novel, but chemically sensible molecules. The properties of the molecules are tuned by training on two different datasets consisting of fragment like molecules and drug like molecules. The produced molecules and the training databases have very similar distributions of molar weight, predicted logP, number of hydrogen bond acceptors and donors, number of rotatable bonds and topological polar surface area when compared to their respective training sets. The compounds are for the most cases synthesizable as assessed with SA score and Wiley ChemPlanner.
Tasks	Drug Discovery
Published	2017-05-12
URL	http://arxiv.org/abs/1705.04612v2
PDF	http://arxiv.org/pdf/1705.04612v2.pdf
PWC	https://paperswithcode.com/paper/molecular-generation-with-recurrent-neural
Repo
Framework

Real-time Egocentric Gesture Recognition on Mobile Head Mounted Displays


Title	Real-time Egocentric Gesture Recognition on Mobile Head Mounted Displays
Authors	Rohit Pandey, Marie White, Pavel Pidlypenskyi, Xue Wang, Christine Kaeser-Chen
Abstract	Mobile virtual reality (VR) head mounted displays (HMD) have become popular among consumers in recent years. In this work, we demonstrate real-time egocentric hand gesture detection and localization on mobile HMDs. Our main contributions are: 1) A novel mixed-reality data collection tool to automatic annotate bounding boxes and gesture labels; 2) The largest-to-date egocentric hand gesture and bounding box dataset with more than 400,000 annotated frames; 3) A neural network that runs real time on modern mobile CPUs, and achieves higher than 76% precision on gesture recognition across 8 classes.
Tasks	Gesture Recognition
Published	2017-12-13
URL	http://arxiv.org/abs/1712.04961v1
PDF	http://arxiv.org/pdf/1712.04961v1.pdf
PWC	https://paperswithcode.com/paper/real-time-egocentric-gesture-recognition-on
Repo
Framework

Block Neural Network Avoids Catastrophic Forgetting When Learning Multiple Task


Title	Block Neural Network Avoids Catastrophic Forgetting When Learning Multiple Task
Authors	Guglielmo Montone, J. Kevin O’Regan, Alexander V. Terekhov
Abstract	In the present work we propose a Deep Feed Forward network architecture which can be trained according to a sequential learning paradigm, where tasks of increasing difficulty are learned sequentially, yet avoiding catastrophic forgetting. The proposed architecture can re-use the features learned on previous tasks in a new task when the old tasks and the new one are related. The architecture needs fewer computational resources (neurons and connections) and less data for learning the new task than a network trained from scratch
Tasks
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10204v1
PDF	http://arxiv.org/pdf/1711.10204v1.pdf
PWC	https://paperswithcode.com/paper/block-neural-network-avoids-catastrophic
Repo
Framework

Decorrelation of Neutral Vector Variables: Theory and Applications


Title	Decorrelation of Neutral Vector Variables: Theory and Applications
Authors	Zhanyu Ma, Jing-Hao Xue, Arne Leijon, Zheng-Hua Tan, Zhen Yang, Jun Guo
Abstract	In this paper, we propose novel strategies for neutral vector variable decorrelation. Two fundamental invertible transformations, namely serial nonlinear transformation and parallel nonlinear transformation, are proposed to carry out the decorrelation. For a neutral vector variable, which is not multivariate Gaussian distributed, the conventional principal component analysis (PCA) cannot yield mutually independent scalar variables. With the two proposed transformations, a highly negatively correlated neutral vector can be transformed to a set of mutually independent scalar variables with the same degrees of freedom. We also evaluate the decorrelation performances for the vectors generated from a single Dirichlet distribution and a mixture of Dirichlet distributions. The mutual independence is verified with the distance correlation measurement. The advantages of the proposed decorrelation strategies are intensively studied and demonstrated with synthesized data and practical application evaluations.
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10524v1
PDF	http://arxiv.org/pdf/1705.10524v1.pdf
PWC	https://paperswithcode.com/paper/decorrelation-of-neutral-vector-variables
Repo
Framework

Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization


Title	Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
Authors	Yanyun Qu, Jinyan Liu, Yuan Xie, Wensheng Zhang
Abstract	Most recently, tensor-SVD is implemented on multi-view self-representation clustering and has achieved the promising results in many real-world applications such as face clustering, scene clustering and generic object clustering. However, tensor-SVD based multi-view self-representation clustering is proposed originally to solve the clustering problem in the multiple linear subspaces, leading to unsatisfactory results when dealing with the case of non-linear subspaces. To handle data clustering from the non-linear subspaces, a kernelization method is designed by mapping the data from the original input space to a new feature space in which the transformed data can be clustered by a multiple linear clustering method. In this paper, we make an optimization model for the kernelized multi-view self-representation clustering problem. We also develop a new efficient algorithm based on the alternation direction method and infer a closed-form solution. Since all the subproblems can be solved exactly, the proposed optimization algorithm is guaranteed to obtain the optimal solution. In particular, the original tensor-based multi-view self-representation clustering problem is a special case of our approach and can be solved by our algorithm. Experimental results on several popular real-world clustering datasets demonstrate that our approach achieves the state-of-the-art performance.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05083v1
PDF	http://arxiv.org/pdf/1709.05083v1.pdf
PWC	https://paperswithcode.com/paper/robust-kernelized-multi-view-self
Repo
Framework

Fully adaptive algorithm for pure exploration in linear bandits


Title	Fully adaptive algorithm for pure exploration in linear bandits
Authors	Liyuan Xu, Junya Honda, Masashi Sugiyama
Abstract	We propose the first fully-adaptive algorithm for pure exploration in linear bandits—the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly. While existing methods partially or entirely fix sequences of arm selections before observing rewards, our method adaptively changes the arm selection strategy based on past observations at each round. We show our sample complexity matches the achievable lower bound up to a constant factor in an extreme case. Furthermore, we evaluate the performance of the methods by simulations based on both synthetic setting and real-world data, in which our method shows vast improvement over existing methods.
Tasks
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05552v1
PDF	http://arxiv.org/pdf/1710.05552v1.pdf
PWC	https://paperswithcode.com/paper/fully-adaptive-algorithm-for-pure-exploration
Repo
Framework

Always Lurking: Understanding and Mitigating Bias in Online Human Trafficking Detection


Title	Always Lurking: Understanding and Mitigating Bias in Online Human Trafficking Detection
Authors	Kyle Hundman, Thamme Gowda, Mayank Kejriwal, Benedikt Boecking
Abstract	Web-based human trafficking activity has increased in recent years but it remains sparsely dispersed among escort advertisements and difficult to identify due to its often-latent nature. The use of intelligent systems to detect trafficking can thus have a direct impact on investigative resource allocation and decision-making, and, more broadly, help curb a widespread social problem. Trafficking detection involves assigning a normalized score to a set of escort advertisements crawled from the Web – a higher score indicates a greater risk of trafficking-related (involuntary) activities. In this paper, we define and study the problem of trafficking detection and present a trafficking detection pipeline architecture developed over three years of research within the DARPA Memex program. Drawing on multi-institutional data, systems, and experiences collected during this time, we also conduct post hoc bias analyses and present a bias mitigation plan. Our findings show that, while automatic trafficking detection is an important application of AI for social good, it also provides cautionary lessons for deploying predictive machine learning algorithms without appropriate de-biasing. This ultimately led to integration of an interpretable solution into a search system that contains over 100 million advertisements and is used by over 200 law enforcement agencies to investigate leads.
Tasks	Decision Making
Published	2017-12-03
URL	http://arxiv.org/abs/1712.00846v1
PDF	http://arxiv.org/pdf/1712.00846v1.pdf
PWC	https://paperswithcode.com/paper/always-lurking-understanding-and-mitigating
Repo
Framework

Superpixels Based Segmentation and SVM Based Classification Method to Distinguish Five Diseases from Normal Regions in Wireless Capsule Endoscopy


Title	Superpixels Based Segmentation and SVM Based Classification Method to Distinguish Five Diseases from Normal Regions in Wireless Capsule Endoscopy
Authors	Omid Haji Maghsoudi
Abstract	Wireless Capsule Endoscopy (WCE) is relatively a new technology to examine the entire GI trace. During an examination, it captures more than 55,000 frames. Reviewing all these images is time-consuming and prone to human error. It has been a challenge to develop intelligent methods assisting physicians to review the frames. The WCE frames are captured in 8-bit color depths which provides enough a color range to detect abnormalities. Here, superpixel based methods are proposed to segment five diseases including: bleeding, Crohn’s disease, Lymphangiectasia, Xanthoma, and Lymphoid hyperplasia. Two superpixels methods are compared to provide semantic segmentation of these prolific diseases: simple linear iterative clustering (SLIC) and quick shift (QS). The segmented superpixels were classified into two classes (normal and abnormal) by support vector machine (SVM) using texture and color features. For both superpixel methods, the accuracy, specificity, sensitivity, and precision (SLIC, QS) were around 92%, 93%, 93%, and 88%, respectively. However, SLIC was dramatically faster than QS.
Tasks	Semantic Segmentation
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06616v1
PDF	http://arxiv.org/pdf/1711.06616v1.pdf
PWC	https://paperswithcode.com/paper/superpixels-based-segmentation-and-svm-based
Repo
Framework

Intrinsic Point of Interest Discovery from Trajectory Data


Title	Intrinsic Point of Interest Discovery from Trajectory Data
Authors	Matthew Piekenbrock, Derek Doran
Abstract	This paper presents a framework for intrinsic point of interest discovery from trajectory databases. Intrinsic points of interest are regions of a geospatial area innately defined by the spatial and temporal aspects of trajectory data, and can be of varying size, shape, and resolution. Any trajectory database exhibits such points of interest, and hence are intrinsic, as compared to most other point of interest definitions which are said to be extrinsic, as they require trajectory metadata, external knowledge about the region the trajectories are observed, or other application-specific information. Spatial and temporal aspects are qualities of any trajectory database, making the framework applicable to data from any domain and of any resolution. The framework is developed under recent developments on the consistency of nonparametric hierarchical density estimators and enables the possibility of formal statistical inference and evaluation over such intrinsic points of interest. Comparisons of the POIs uncovered by the framework in synthetic truth data to thousands of parameter settings for common POI discovery methods show a marked improvement in fidelity without the need to tune any parameters by hand.
Tasks
Published	2017-12-14
URL	http://arxiv.org/abs/1712.05247v1
PDF	http://arxiv.org/pdf/1712.05247v1.pdf
PWC	https://paperswithcode.com/paper/intrinsic-point-of-interest-discovery-from
Repo
Framework

Supervised Learning with Indefinite Topological Kernels


Title	Supervised Learning with Indefinite Topological Kernels
Authors	Tullia Padellini, Pierpaolo Brutti
Abstract	Topological Data Analysis (TDA) is a recent and growing branch of statistics devoted to the study of the shape of the data. In this work we investigate the predictive power of TDA in the context of supervised learning. Since topological summaries, most noticeably the Persistence Diagram, are typically defined in complex spaces, we adopt a kernel approach to translate them into more familiar vector spaces. We define a topological exponential kernel, we characterize it, and we show that, despite not being positive semi-definite, it can be successfully used in regression and classification tasks.
Tasks	Topological Data Analysis
Published	2017-09-20
URL	http://arxiv.org/abs/1709.07100v1
PDF	http://arxiv.org/pdf/1709.07100v1.pdf
PWC	https://paperswithcode.com/paper/supervised-learning-with-indefinite
Repo
Framework

SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control


Title	SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control
Authors	Arunkumar Byravan, Felix Leeb, Franziska Meier, Dieter Fox
Abstract	In this work, we present an approach to deep visuomotor control using structured deep dynamics models. Our deep dynamics model, a variant of SE3-Nets, learns a low-dimensional pose embedding for visuomotor control via an encoder-decoder structure. Unlike prior work, our dynamics model is structured: given an input scene, our network explicitly learns to segment salient parts and predict their pose-embedding along with their motion modeled as a change in the pose space due to the applied actions. We train our model using a pair of point clouds separated by an action and show that given supervision only in the form of point-wise data associations between the frames our network is able to learn a meaningful segmentation of the scene along with consistent poses. We further show that our model can be used for closed-loop control directly in the learned low-dimensional pose space, where the actions are computed by minimizing error in the pose space using gradient-based methods, similar to traditional model-based control. We present results on controlling a Baxter robot from raw depth data in simulation and in the real world and compare against two baseline deep networks. Our method runs in real-time, achieves good prediction of scene dynamics and outperforms the baseline methods on multiple control runs. Video results can be found at: https://rse-lab.cs.washington.edu/se3-structured-deep-ctrl/
Tasks
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00489v1
PDF	http://arxiv.org/pdf/1710.00489v1.pdf
PWC	https://paperswithcode.com/paper/se3-pose-nets-structured-deep-dynamics-models
Repo
Framework

The Dutch’s Real World Financial Institute: Introducing Quantum-Like Bayesian Networks as an Alternative Model to deal with Uncertainty


Title	The Dutch’s Real World Financial Institute: Introducing Quantum-Like Bayesian Networks as an Alternative Model to deal with Uncertainty
Authors	Catarina Moreira, Emmanuel Haven, Sandro Sozzo, Andreas Wichert
Abstract	In this work, we analyse and model a real life financial loan application belonging to a sample bank in the Netherlands. The log is robust in terms of data, containing a total of 262 200 event logs, belonging to 13 087 different credit applications. The dataset is heterogeneous and consists of a mixture of computer generated automatic processes and manual human tasks. The goal is to work out a decision model, which represents the underlying tasks that make up the loan application service, and to assess potential areas of improvement of the institution’s internal processes. To this end we study the impact of incomplete event logs for the extraction and analysis of business processes. It is quite common that event logs are incomplete with several amounts of missing information (for instance, workers forget to register their tasks). Absence of data is translated into a drastic decrease of precision and compromises the decision models, leading to biased and unrepresentative results. We investigate how classical probabilistic models are affected by incomplete event logs and we explore quantum-like probabilistic inferences as an alternative mathematical model to classical probability. This work represents a first step towards systematic investigation of the impact of quantum interference in a real life large scale decision scenario. The results obtained in this study indicate that, under high levels of uncertainty, the quantum-like models generate quantum interference terms, which allow an additional non-linear parameterisation of the data. Experimental results attest the efficiency of the quantum-like Bayesian networks, since the application of interference terms is able to reduce the error percentage of inferences performed over quantum-like models when compared to inferences produced by classical models.
Tasks
Published	2017-10-02
URL	http://arxiv.org/abs/1710.00490v1
PDF	http://arxiv.org/pdf/1710.00490v1.pdf
PWC	https://paperswithcode.com/paper/the-dutchs-real-world-financial-institute
Repo
Framework

Online Product Quantization


Title	Online Product Quantization
Authors	Donna Xu, Ivor W. Tsang, Ying Zhang
Abstract	Approximate nearest neighbor (ANN) search has achieved great success in many tasks. However, existing popular methods for ANN search, such as hashing and quantization methods, are designed for static databases only. They cannot handle well the database with data distribution evolving dynamically, due to the high computational effort for retraining the model based on the new database. In this paper, we address the problem by developing an online product quantization (online PQ) model and incrementally updating the quantization codebook that accommodates to the incoming streaming data. Moreover, to further alleviate the issue of large scale computation for the online PQ update, we design two budget constraints for the model to update partial PQ codebook instead of all. We derive a loss bound which guarantees the performance of our online PQ model. Furthermore, we develop an online PQ model over a sliding window with both data insertion and deletion supported, to reflect the real-time behaviour of the data. The experiments demonstrate that our online PQ model is both time-efficient and effective for ANN search in dynamic large scale databases compared with baseline methods and the idea of partial PQ codebook update further reduces the update cost.
Tasks	Quantization
Published	2017-11-29
URL	http://arxiv.org/abs/1711.10775v2
PDF	http://arxiv.org/pdf/1711.10775v2.pdf
PWC	https://paperswithcode.com/paper/online-product-quantization
Repo
Framework