January 28, 2020

3317 words 16 mins read

Paper Group ANR 981

Online Synthesis for Runtime Enforcement of Safety in Multi-Agent Systems. Data hiding in complex-amplitude modulation using a digital micromirror device. Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds. Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention. Outlier-Robust Spatia …

Online Synthesis for Runtime Enforcement of Safety in Multi-Agent Systems


Title	Online Synthesis for Runtime Enforcement of Safety in Multi-Agent Systems
Authors	Dhananjay Raju, Suda Bharadwaj, Ufuk Topcu
Abstract	A shield is attached to a system to guarantee safety by correcting the system’s behavior at runtime. Existing methods that employ design-time synthesis of shields do not scale to multi-agent systems. Moreover, such shields are typically implemented in a centralized manner, requiring global information on the state of all agents in the system. We address these limitations through a new approach where the shields are synthesized at runtime and do not require global information. There is a shield onboard every agent, which can only modify the behavior of the corresponding agent. In this approach, which is fundamentally decentralized, the shield on every agent has two components: a pathfinder that corrects the behavior of the agent and an ordering mechanism that dynamically modifies the priority of the agent. The current priority determines if the shield uses the pathfinder to modify behavior of the agent. We derive an upper bound on the maximum deviation for any agent from its original behavior. We prove that the worst-case synthesis time is quadratic in the number of agents at runtime as opposed to exponential at design-time for existing methods. We test the performance of the decentralized, runtime shield synthesis approach on a collision-avoidance problem. For 50 agents in a 50x50 grid, the synthesis at runtime requires a few seconds per agent whenever a potential collision is detected. In contrast, the centralized design-time synthesis of shields for a similar setting is intractable beyond 4 agents in a 5x5 grid.
Tasks
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10380v2
PDF	https://arxiv.org/pdf/1910.10380v2.pdf
PWC	https://paperswithcode.com/paper/decentralized-runtime-synthesis-of-shields
Repo
Framework

Data hiding in complex-amplitude modulation using a digital micromirror device


Title	Data hiding in complex-amplitude modulation using a digital micromirror device
Authors	Shuming Jiao, Dongfang Zhang, Chonglei Zhang, Yang Gao, Ting Lei, Xiaocong Yuan
Abstract	A digital micromirror device (DMD) is an amplitude-type spatial light modulator. However, a complex-amplitude light modulation with a DMD can be achieved using the superpixel scheme. In the superpixel scheme, we notice that multiple different DMD local block patterns may correspond to the same complex superpixel value. Based on this inherent encoding redundancy, a large amount of external data can be embedded into the DMD pattern without extra cost. Meanwhile, the original complex light field information carried by the DMD pattern is fully preserved. This proposed scheme is favorable for applications such as secure information transmission and copyright protection.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11222v1
PDF	https://arxiv.org/pdf/1910.11222v1.pdf
PWC	https://paperswithcode.com/paper/data-hiding-in-complex-amplitude-modulation
Repo
Framework

Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds


Title	Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds
Authors	Michael Perlmutter, Feng Gao, Guy Wolf, Matthew Hirn
Abstract	The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural networks. Inspired by recent interest in geometric deep learning, which aims to generalize convolutional neural networks to manifold and graph-structured domains, we define a geometric scattering transform on manifolds. Similar to the Euclidean scattering transform, the geometric scattering transform is based on a cascade of wavelet filters and pointwise nonlinearities. It is invariant to local isometries and stable to certain types of diffeomorphisms. Empirical results demonstrate its utility on several geometric learning tasks. Our results generalize the deformation stability and local translation invariance of Euclidean scattering, and demonstrate the importance of linking the used filter structures to the underlying geometry of the data.
Tasks
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10448v2
PDF	https://arxiv.org/pdf/1905.10448v2.pdf
PWC	https://paperswithcode.com/paper/geometric-wavelet-scattering-networks-on
Repo
Framework

Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention


Title	Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention
Authors	Lei Cao, Huijun Zhang, Ling Feng, Zihan Wei, Xin Wang, Ningyun Li, Xiaohao He
Abstract	Despite detection of suicidal ideation on social media has made great progress in recent years, people’s implicitly and anti-real contrarily expressed posts still remain as an obstacle, constraining the detectors to acquire higher satisfactory performance. Enlightened by the hidden “tree holes” phenomenon on microblog, where people at suicide risk tend to disclose their inner real feelings and thoughts to the microblog space whose authors have committed suicide, we explore the use of tree holes to enhance microblog-based suicide risk detection from the following two perspectives. (1) We build suicide-oriented word embeddings based on tree hole contents to strength the sensibility of suicide-related lexicons and context based on tree hole contents. (2) A two-layered attention mechanism is deployed to grasp intermittently changing points from individual’s open blog streams, revealing one’s inner emotional world more or less. Our experimental results show that with suicide-oriented word embeddings and attention, microblog-based suicide risk detection can achieve over 91% accuracy. A large-scale well-labelled suicide data set is also reported in the paper.
Tasks	Word Embeddings
Published	2019-10-26
URL	https://arxiv.org/abs/1910.12038v1
PDF	https://arxiv.org/pdf/1910.12038v1.pdf
PWC	https://paperswithcode.com/paper/latent-suicide-risk-detection-on-microblog
Repo
Framework

Outlier-Robust Spatial Perception: Hardness, General-Purpose Algorithms, and Guarantees


Title	Outlier-Robust Spatial Perception: Hardness, General-Purpose Algorithms, and Guarantees
Authors	Vasileios Tzoumas, Pasquale Antonante, Luca Carlone
Abstract	Spatial perception is the backbone of many robotics applications, and spans a broad range of research problems, including localization and mapping, point cloud alignment, and relative pose estimation from camera images. Robust spatial perception is jeopardized by the presence of incorrect data association, and in general, outliers. Although techniques to handle outliers do exist, they can fail in unpredictable manners (e.g., RANSAC, robust estimators), or can have exponential runtime (e.g., branch-and-bound). In this paper, we advance the state of the art in outlier rejection by making three contributions. First, we show that even a simple linear instance of outlier rejection is inapproximable: in the worst-case one cannot design a quasi-polynomial time algorithm that computes an approximate solution efficiently. Our second contribution is to provide the first per-instance sub-optimality bounds to assess the approximation quality of a given outlier rejection outcome. Our third contribution is to propose a simple general-purpose algorithm, named adaptive trimming, to remove outliers. Our algorithm leverages recently-proposed global solvers that are able to solve outlier-free problems, and iteratively removes measurements with large errors. We demonstrate the proposed algorithm on three spatial perception problems: 3D registration, two-view geometry, and SLAM. The results show that our algorithm outperforms several state-of-the-art methods across applications while being a general-purpose method.
Tasks	Pose Estimation
Published	2019-03-27
URL	https://arxiv.org/abs/1903.11683v2
PDF	https://arxiv.org/pdf/1903.11683v2.pdf
PWC	https://paperswithcode.com/paper/outlier-robust-spatial-perception-hardness
Repo
Framework

The method of automatic summarization from different sources


Title	The method of automatic summarization from different sources
Authors	Nataliya Shakhovska, Taras Cherna
Abstract	In this article is analyzed technology of automatic text abstracting and annotation. The role of annotation in automatic search and classification for different scientific articles is described. The algorithm of summarization of natural language documents using the concept of importance coefficients is developed. Such concept allows considering the peculiarity of subject areas and topics that could be found in different kinds of documents. Method for generating abstracts of single document based on frequency analysis is developed. The recognition elements for unstructured text analysis are given. The method of pre-processing analysis of several documents is developed. This technique simultaneously considers both statistical approaches to abstracting and the importance of terms in a particular subject domain. The quality of generated abstract is evaluated. For the developed system there was conducted experts evaluation. It was held only for texts in Ukrainian. The developed system concluding essay has higher aggregate score on all criteria. The summarization system architecture is building. To build an information system model there is used CASE-tool AllFusion ERwin Data Modeler. The database scheme for information saving was built. The system is designed to work primarily with Ukrainian texts, which gives a significant advantage, since most modern systems still oriented to English texts
Tasks
Published	2019-05-04
URL	https://arxiv.org/abs/1905.02623v1
PDF	https://arxiv.org/pdf/1905.02623v1.pdf
PWC	https://paperswithcode.com/paper/the-method-of-automatic-summarization-from
Repo
Framework

A Probabilistic Approach to Satisfiability of Propositional Logic Formulae


Title	A Probabilistic Approach to Satisfiability of Propositional Logic Formulae
Authors	Reazul Hasan Russel
Abstract	We propose a version of WalkSAT algorithm, named as BetaWalkSAT. This method uses probabilistic reasoning for biasing the starting state of the local search algorithm. Beta distribution is used to model the belief over boolean values of the literals. Our results suggest that, the proposed BetaWalkSAT algorithm can outperform other uninformed local search approaches for complex boolean satisfiability problems.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02150v1
PDF	https://arxiv.org/pdf/1912.02150v1.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-approach-to-satisfiability-of
Repo
Framework

Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registration


Title	Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registration
Authors	Dwarikanath Mahapatra
Abstract	Medical image registration is an important task in automated analysis of multi-modal images and temporal data involving multiple patient visits. Conventional approaches, although useful for different image types, are time consuming. Of late, deep learning (DL) based image registration methods have been proposed that outperform traditional methods in terms of accuracy and time. However,DL based methods are heavily dependent on training data and do not generalize well when presented with images of different scanners or anatomies. We present a DL based approach that can perform medical image registration of one image type despite being trained with images of a different type. This is achieved by unsupervised domain adaptation in the registration process and allows for easier application to different datasets without extensive retraining.To achieve our objective we train a network that transforms the given input image pair to a latent feature space vector using autoencoders. The resultant encoded feature space is used to generate the registered images with the help of generative adversarial networks (GANs). This feature transformation ensures greater invariance to the input image type. Experiments on chest Xray, retinal and brain MR images show that our method, trained on one dataset gives better registration performance for other datasets, outperforming conventional methods that do not incorporate domain adaptation
Tasks	Domain Adaptation, Image Registration, Medical Image Registration, Unsupervised Domain Adaptation
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08593v2
PDF	https://arxiv.org/pdf/1910.08593v2.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-networks-and-domain
Repo
Framework

Resolving 3D Human Pose Ambiguities with 3D Scene Constraints


Title	Resolving 3D Human Pose Ambiguities with 3D Scene Constraints
Authors	Mohamed Hassan, Vasileios Choutas, Dimitrios Tzionas, Michael J. Black
Abstract	To understand and analyze human behavior, we need to capture humans moving in, and interacting with, the world. Most existing methods perform 3D human pose estimation without explicitly considering the scene. We observe however that the world constrains the body and vice-versa. To motivate this, we show that current 3D human pose estimation methods produce results that are not consistent with the 3D scene. Our key contribution is to exploit static 3D scene structure to better estimate human pose from monocular images. The method enforces Proximal Relationships with Object eXclusion and is called PROX. To test this, we collect a new dataset composed of 12 different 3D scenes and RGB sequences of 20 subjects moving in and interacting with the scenes. We represent human pose using the 3D human body model SMPL-X and extend SMPLify-X to estimate body pose using scene constraints. We make use of the 3D scene information by formulating two main constraints. The inter-penetration constraint penalizes intersection between the body model and the surrounding 3D scene. The contact constraint encourages specific parts of the body to be in contact with scene surfaces if they are close enough in distance and orientation. For quantitative evaluation we capture a separate dataset with 180 RGB frames in which the ground-truth body pose is estimated using a motion capture system. We show quantitatively that introducing scene constraints significantly reduces 3D joint error and vertex error. Our code and data are available for research at https://prox.is.tue.mpg.de.
Tasks	3D Human Pose Estimation, Motion Capture, Pose Estimation
Published	2019-08-20
URL	https://arxiv.org/abs/1908.06963v1
PDF	https://arxiv.org/pdf/1908.06963v1.pdf
PWC	https://paperswithcode.com/paper/resolving-3d-human-pose-ambiguities-with-3d
Repo
Framework

Heterogeneous Edge Embeddings for Friend Recommendation


Title	Heterogeneous Edge Embeddings for Friend Recommendation
Authors	Janu Verma, Srishti Gupta, Debdoot Mukherjee, Tanmoy Chakraborty
Abstract	We propose a friend recommendation system (an application of link prediction) using edge embeddings on social networks. Most real-world social networks are multi-graphs, where different kinds of relationships (e.g. chat, friendship) are possible between a pair of users. Existing network embedding techniques do not leverage signals from different edge types and thus perform inadequately on link prediction in such networks. We propose a method to mine network representation that effectively exploits heterogeneity in multi-graphs. We evaluate our model on a real-world, active social network where this system is deployed for friend recommendation for millions of users. Our method outperforms various state-of-the-art baselines on Hike’s social network in terms of accuracy as well as user satisfaction.
Tasks	Link Prediction, Network Embedding
Published	2019-02-07
URL	http://arxiv.org/abs/1902.03124v1
PDF	http://arxiv.org/pdf/1902.03124v1.pdf
PWC	https://paperswithcode.com/paper/heterogeneous-edge-embeddings-for-friend
Repo
Framework

Semi-Supervised Method using Gaussian Random Fields for Boilerplate Removal in Web Browsers


Title	Semi-Supervised Method using Gaussian Random Fields for Boilerplate Removal in Web Browsers
Authors	Joy Bose, Sumanta Mukherjee
Abstract	Boilerplate removal refers to the problem of removing noisy content from a webpage such as ads and extracting relevant content that can be used by various services. This can be useful in several features in web browsers such as ad blocking, accessibility tools such as read out loud, translation, summarization etc. In order to create a training dataset to train a model for boilerplate detection and removal, labeling or tagging webpage data manually can be tedious and time consuming. Hence, a semi-supervised model, in which some of the webpage elements are labeled manually and labels for others are inferred based on some parameters, can be useful. In this paper we present a solution for extraction of relevant content from a webpage that relies on semi-supervised learning using Gaussian Random Fields. We first represent the webpage as a graph, with text elements as nodes and the edge weights representing similarity between nodes. After this, we label a few nodes in the graph using heuristics and label the remaining nodes by a weighted measure of similarity to the already labeled nodes. We describe the system architecture and a few preliminary results on a dataset of webpages.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.02991v1
PDF	https://arxiv.org/pdf/1911.02991v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-method-using-gaussian-random
Repo
Framework

Towards Further Understanding of Sparse Filtering via Information Bottleneck


Title	Towards Further Understanding of Sparse Filtering via Information Bottleneck
Authors	Fabio Massimo Zennaro, Ke Chen
Abstract	In this paper we examine a formalization of feature distribution learning (FDL) in information-theoretic terms relying on the analytical approach and on the tools already used in the study of the information bottleneck (IB). It has been conjectured that the behavior of FDL algorithms could be expressed as an optimization problem over two information-theoretic quantities: the mutual information of the data with the learned representations and the entropy of the learned distribution. In particular, such a formulation was offered in order to explain the success of the most prominent FDL algorithm, sparse filtering (SF). This conjecture was, however, left unproven. In this work, we aim at providing preliminary empirical support to this conjecture by performing experiments reminiscent of the work done on deep neural networks in the context of the IB research. Specifically, we borrow the idea of using information planes to analyze the behavior of the SF algorithm and gain insights on its dynamics. A confirmation of the conjecture about the dynamics of FDL may provide solid ground to develop information-theoretic tools to assess the quality of the learning process in FDL, and it may be extended to other unsupervised learning algorithms.
Tasks
Published	2019-10-20
URL	https://arxiv.org/abs/1910.08964v1
PDF	https://arxiv.org/pdf/1910.08964v1.pdf
PWC	https://paperswithcode.com/paper/towards-further-understanding-of-sparse
Repo
Framework

Robust Federated Training via Collaborative Machine Teaching using Trusted Instances


Title	Robust Federated Training via Collaborative Machine Teaching using Trusted Instances
Authors	Yufei Han, Xiangliang Zhang
Abstract	Federated learning performs distributed model training using local data hosted by agents. It shares only model parameter updates for iterative aggregation at the server. Although it is privacy-preserving by design, federated learning is vulnerable to noise corruption of local agents, as demonstrated in the previous study on adversarial data poisoning threat against federated learning systems. Even a single noise-corrupted agent can bias the model training. In our work, we propose a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers, to improve robustness of the federated training process against local data corruption. We assume that each local agent (teacher) have the resources to verify a small portions of trusted instances, which may not by itself be adequate for learning. In the proposed collaborative machine teaching method, these trusted instances guide the distributed agents to jointly select a compact while informative training subset from data hosted by their own. Simultaneously, the agents learn to add changes of limited magnitudes into the selected data instances, in order to improve the testing performances of the federally trained model despite of the training data corruption. Experiments on toy and real data demonstrate that our approach can identify training set bugs effectively and suggest appropriate changes to the labels. Our algorithm is a step toward trustworthy machine learning.
Tasks	data poisoning
Published	2019-05-08
URL	https://arxiv.org/abs/1905.02941v1
PDF	https://arxiv.org/pdf/1905.02941v1.pdf
PWC	https://paperswithcode.com/paper/robust-federated-training-via-collaborative
Repo
Framework

ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks


Title	ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks
Authors	Ali Madani, Cyna Shirazinejad, Jia Rui Ong, Hengameh Shams, Mohammad Mofrad
Abstract	Graph neural networks are a quickly emerging field for non-Euclidean data that leverage the inherent graphical structure to predict node, edge, and global-level properties of a system. Protein properties can not easily be understood as a simple sum of their parts (i.e. amino acids), therefore, understanding their dynamical properties in the context of graphs is attractive for revealing how perturbations to their structure can affect their global function. To tackle this problem, we generate a database of 2020 mutated calponin homology (CH) domains undergoing large-scale separation in molecular dynamics. To predict the mechanosensitive force response, we develop neural message passing networks and residual gated graph convnets which predict the protein dependent force separation at 86.63 percent, 81.59 kJ/mol/nm MAE, 76.99 psec MAE for force mode classification, max force magnitude, max force time respectively– significantly better than non-graph-based deep learning techniques. Towards uniting geometric learning techniques and biophysical observables, we premiere our simulation database as a benchmark dataset for further development/evaluation of graph neural network architectures.
Tasks
Published	2019-10-22
URL	https://arxiv.org/abs/1910.09738v1
PDF	https://arxiv.org/pdf/1910.09738v1.pdf
PWC	https://paperswithcode.com/paper/prodyn0-inferring-calponin-homology-domain
Repo
Framework

Identifying Illicit Accounts in Large Scale E-payment Networks – A Graph Representation Learning Approach


Title	Identifying Illicit Accounts in Large Scale E-payment Networks – A Graph Representation Learning Approach
Authors	Da Sun Handason Tam, Wing Cheong Lau, Bin Hu, Qiu Fang Ying, Dah Ming Chiu, Hong Liu
Abstract	Rapid and massive adoption of mobile/ online payment services has brought new challenges to the service providers as well as regulators in safeguarding the proper uses such services/ systems. In this paper, we leverage recent advances in deep-neural-network-based graph representation learning to detect abnormal/ suspicious financial transactions in real-world e-payment networks. In particular, we propose an end-to-end Graph Convolution Network (GCN)-based algorithm to learn the embeddings of the nodes and edges of a large-scale time-evolving graph. In the context of e-payment transaction graphs, the resultant node and edge embeddings can effectively characterize the user-background as well as the financial transaction patterns of individual account holders. As such, we can use the graph embedding results to drive downstream graph mining tasks such as node-classification to identify illicit accounts within the payment networks. Our algorithm outperforms state-of-the-art schemes including GraphSAGE, Gradient Boosting Decision Tree and Random Forest to deliver considerably higher accuracy (94.62% and 86.98% respectively) in classifying user accounts within 2 practical e-payment transaction datasets. It also achieves outstanding accuracy (97.43%) for another biomedical entity identification task while using only edge-related information.
Tasks	Graph Embedding, Graph Representation Learning, Node Classification, Representation Learning
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05546v1
PDF	https://arxiv.org/pdf/1906.05546v1.pdf
PWC	https://paperswithcode.com/paper/identifying-illicit-accounts-in-large-scale-e
Repo
Framework