October 18, 2019

2778 words 14 mins read

Paper Group ANR 643

Graph-Based Recommendation System. Discrete Potts Model for Generating Superpixels on Noisy Images. Deep BV: A Fully Automated System for Brain Ventricle Localization and Segmentation in 3D Ultrasound Images of Embryonic Mice. Get Your Workload in Order: Game Theoretic Prioritization of Database Auditing. ReDMark: Framework for Residual Diffusion W …

Graph-Based Recommendation System


Title	Graph-Based Recommendation System
Authors	Kaige Yang, Laura Toni
Abstract	In this work, we study recommendation systems modelled as contextual multi-armed bandit (MAB) problems. We propose a graph-based recommendation system that learns and exploits the geometry of the user space to create meaningful clusters in the user domain. This reduces the dimensionality of the recommendation problem while preserving the accuracy of MAB. We then study the effect of graph sparsity and clusters size on the MAB performance and provide exhaustive simulation results both in synthetic and in real-case datasets. Simulation results show improvements with respect to state-of-the-art MAB algorithms.
Tasks	Recommendation Systems
Published	2018-07-31
URL	http://arxiv.org/abs/1808.00004v1
PDF	http://arxiv.org/pdf/1808.00004v1.pdf
PWC	https://paperswithcode.com/paper/graph-based-recommendation-system
Repo
Framework

Discrete Potts Model for Generating Superpixels on Noisy Images


Title	Discrete Potts Model for Generating Superpixels on Noisy Images
Authors	Ruobing Shen, Xiaoyu Chen, Xiangrui Zheng, Gerhard Reinelt
Abstract	Many computer vision applications, such as object recognition and segmentation, increasingly build on superpixels. However, there have been so far few superpixel algorithms that systematically deal with noisy images. We propose to first decompose the image into equal-sized rectangular patches, which also sets the maximum superpixel size. Within each patch, a Potts model for simultaneous segmentation and denoising is applied, that guarantees connected and non-overlapping superpixels and also produces a denoised image. The corresponding optimization problem is formulated as a mixed integer linear program (MILP), and solved by a commercial solver. Extensive experiments on the BSDS500 dataset images with noises are compared with other state-of-the-art superpixel methods. Our method achieves the best result in terms of a combined score (OP) composed of the under-segmentation error, boundary recall and compactness.
Tasks	Denoising, Object Recognition
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07351v1
PDF	http://arxiv.org/pdf/1803.07351v1.pdf
PWC	https://paperswithcode.com/paper/discrete-potts-model-for-generating
Repo
Framework

Deep BV: A Fully Automated System for Brain Ventricle Localization and Segmentation in 3D Ultrasound Images of Embryonic Mice


Title	Deep BV: A Fully Automated System for Brain Ventricle Localization and Segmentation in 3D Ultrasound Images of Embryonic Mice
Authors	Ziming Qiu, Jack Langerman, Nitin Nair, Orlando Aristizabal, Jonathan Mamou, Daniel H. Turnbull, Jeffrey Ketterling, Yao Wang
Abstract	Volumetric analysis of brain ventricle (BV) structure is a key tool in the study of central nervous system development in embryonic mice. High-frequency ultrasound (HFU) is the only non-invasive, real-time modality available for rapid volumetric imaging of embryos in utero. However, manual segmentation of the BV from HFU volumes is tedious, time-consuming, and requires specialized expertise. In this paper, we propose a novel deep learning based BV segmentation system for whole-body HFU images of mouse embryos. Our fully automated system consists of two modules: localization and segmentation. It first applies a volumetric convolutional neural network on a 3D sliding window over the entire volume to identify a 3D bounding box containing the entire BV. It then employs a fully convolutional network to segment the detected bounding box into BV and background. The system achieves a Dice Similarity Coefficient (DSC) of 0.8956 for BV segmentation on an unseen 111 HFU volume test set surpassing the previous state-of-the-art method (DSC of 0.7119) by a margin of 25%.
Tasks	Brain Ventricle Localization And Segmentation In 3D Ultrasound Images
Published	2018-11-05
URL	http://arxiv.org/abs/1811.03601v1
PDF	http://arxiv.org/pdf/1811.03601v1.pdf
PWC	https://paperswithcode.com/paper/deep-bv-a-fully-automated-system-for-brain
Repo
Framework

Get Your Workload in Order: Game Theoretic Prioritization of Database Auditing


Title	Get Your Workload in Order: Game Theoretic Prioritization of Database Auditing
Authors	Chao Yan, Bo Li, Yevgeniy Vorobeychik, Aron Laszka, Daniel Fabbri, Bradley Malin
Abstract	For enhancing the privacy protections of databases, where the increasing amount of detailed personal data is stored and processed, multiple mechanisms have been developed, such as audit logging and alert triggers, which notify administrators about suspicious activities; however, the two main limitations in common are: 1) the volume of such alerts is often substantially greater than the capabilities of resource-constrained organizations, and 2) strategic attackers may disguise their actions or carefully choosing which records they touch, making incompetent the statistical detection models. For solving them, we introduce a novel approach to database auditing that explicitly accounts for adversarial behavior by 1) prioritizing the order in which types of alerts are investigated and 2) providing an upper bound on how much resource to allocate for each type. We model the interaction between a database auditor and potential attackers as a Stackelberg game in which the auditor chooses an auditing policy and attackers choose which records to target. A corresponding approach combining linear programming, column generation, and heuristic search is proposed to derive an auditing policy. For testing the policy-searching performance, a publicly available credit card application dataset are adopted, on which it shows that our methods produce high-quality mixed strategies as database audit policies, and our general approach significantly outperforms non-game-theoretic baselines.
Tasks
Published	2018-01-22
URL	http://arxiv.org/abs/1801.07215v1
PDF	http://arxiv.org/pdf/1801.07215v1.pdf
PWC	https://paperswithcode.com/paper/get-your-workload-in-order-game-theoretic
Repo
Framework

ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks


Title	ReDMark: Framework for Residual Diffusion Watermarking on Deep Networks
Authors	Mahdi Ahmadi, Alireza Norouzi, S. M. Reza Soroushmehr, Nader Karimi, Kayvan Najarian, Shadrokh Samavi, Ali Emami
Abstract	Due to the rapid growth of machine learning tools and specifically deep networks in various computer vision and image processing areas, application of Convolutional Neural Networks for watermarking have recently emerged. In this paper, we propose a deep end-to-end diffusion watermarking framework (ReDMark) which can be adapted for any desired transform space. The framework is composed of two Fully Convolutional Neural Networks with the residual structure for embedding and extraction. The whole deep network is trained end-to-end to conduct a blind secure watermarking. The framework is customizable for the level of robustness vs. imperceptibility. It is also adjustable for the trade-off between capacity and robustness. The proposed framework simulates various attacks as a differentiable network layer to facilitate end-to-end training. For JPEG attack, a differentiable approximation is utilized, which drastically improves the watermarking robustness to this attack. Another important characteristic of the proposed framework, which leads to improved security and robustness, is its capability to diffuse watermark information among a relatively wide area of the image. Comparative results versus recent state-of-the-art researches highlight the superiority of the proposed framework in terms of imperceptibility and robustness.
Tasks
Published	2018-10-16
URL	http://arxiv.org/abs/1810.07248v3
PDF	http://arxiv.org/pdf/1810.07248v3.pdf
PWC	https://paperswithcode.com/paper/redmark-framework-for-residual-diffusion
Repo
Framework

Interpreting recurrent neural networks behaviour via excitable network attractors


Title	Interpreting recurrent neural networks behaviour via excitable network attractors
Authors	Andrea Ceni, Peter Ashwin, Lorenzo Livi
Abstract	Introduction: Machine learning provides fundamental tools both for scientific research and for the development of technologies with significant impact on society. It provides methods that facilitate the discovery of regularities in data and that give predictions without explicit knowledge of the rules governing a system. However, a price is paid for exploiting such flexibility: machine learning methods are typically black-boxes where it is difficult to fully understand what the machine is doing or how it is operating. This poses constraints on the applicability and explainability of such methods. Methods: Our research aims to open the black-box of recurrent neural networks, an important family of neural networks used for processing sequential data. We propose a novel methodology that provides a mechanistic interpretation of behaviour when solving a computational task. Our methodology uses mathematical constructs called excitable network attractors, which are invariant sets in phase space composed of stable attractors and excitable connections between them. Results and Discussion: As the behaviour of recurrent neural networks depends both on training and on inputs to the system, we introduce an algorithm to extract network attractors directly from the trajectory of a neural network while solving tasks. Simulations conducted on a controlled benchmark task confirm the relevance of these attractors for interpreting the behaviour of recurrent neural networks, at least for tasks that involve learning a finite number of stable states and transitions between them.
Tasks
Published	2018-07-27
URL	http://arxiv.org/abs/1807.10478v6
PDF	http://arxiv.org/pdf/1807.10478v6.pdf
PWC	https://paperswithcode.com/paper/interpreting-recurrent-neural-networks
Repo
Framework

Trichotomic Argumentation Representation


Title	Trichotomic Argumentation Representation
Authors	Merlin Göttlinger, Lutz Schröder
Abstract	The Aristotelian trichotomy distinguishes three aspects of argumentation: Logos, Ethos, and Pathos. Even rich argumentation representations like the Argument Interchange Format (AIF) are only concerned with capturing the Logos aspect. Inference Anchoring Theory (IAT) adds the possibility to represent ethical requirements on the illocutionary force edges linking locutions to illocutions, thereby allowing to capture some aspects of ethos. With the recent extensions AIF+ and Social Argument Interchange Format (S-AIF), which embed dialogue and speakers into the AIF argumentation representation, the basis for representing all three aspects identified by Aristotle was formed. In the present work, we develop the Trichotomic Argument Interchange Format (T-AIF), building on the idea from S-AIF of adding the speakers to the argumentation graph. We capture Logos in the usual known from AIF+, Ethos in form of weighted edges between actors representing trust, and Pathos via weighted edges from actors to illocutions representing their level of commitment to the propositions. This extended structured argumentation representation opens up new possibilities of defining semantic properties on this rich graph in order to characterize and profile the reasoning patterns of the participating actors.
Tasks
Published	2018-12-17
URL	http://arxiv.org/abs/1812.06745v1
PDF	http://arxiv.org/pdf/1812.06745v1.pdf
PWC	https://paperswithcode.com/paper/trichotomic-argumentation-representation
Repo
Framework

Action-conditional Sequence Modeling for Recommendation


Title	Action-conditional Sequence Modeling for Recommendation
Authors	Elena Smirnova
Abstract	In many online applications interactions between a user and a web-service are organized in a sequential way, e.g., user browsing an e-commerce website. In this setting, recommendation system acts throughout user navigation by showing items. Previous works have addressed this recommendation setup through the task of predicting the next item user will interact with. In particular, Recurrent Neural Networks (RNNs) has been shown to achieve substantial improvements over collaborative filtering baselines. In this paper, we consider interactions triggered by the recommendations of deployed recommender system in addition to browsing behavior. Indeed, it is reported that in online services interactions with recommendations represent up to 30% of total interactions. Moreover, in practice, recommender system can greatly influence user behavior by promoting specific items. In this paper, we extend the RNN modeling framework by taking into account user interaction with recommended items. We propose and evaluate RNN architectures that consist of the recommendation action module and the state-action fusion module. Using real-world large-scale datasets we demonstrate improved performance on the next item prediction task compared to the baselines.
Tasks	Recommendation Systems
Published	2018-09-07
URL	http://arxiv.org/abs/1809.03291v1
PDF	http://arxiv.org/pdf/1809.03291v1.pdf
PWC	https://paperswithcode.com/paper/action-conditional-sequence-modeling-for
Repo
Framework

Topological Data Analysis of Decision Boundaries with Application to Model Selection


Title	Topological Data Analysis of Decision Boundaries with Application to Model Selection
Authors	Karthikeyan Natesan Ramamurthy, Kush R. Varshney, Krishnan Mody
Abstract	We propose the labeled \v{C}ech complex, the plain labeled Vietoris-Rips complex, and the locally scaled labeled Vietoris-Rips complex to perform persistent homology inference of decision boundaries in classification tasks. We provide theoretical conditions and analysis for recovering the homology of a decision boundary from samples. Our main objective is quantification of deep neural network complexity to enable matching of datasets to pre-trained models; we report results for experiments using MNIST, FashionMNIST, and CIFAR10.
Tasks	Model Selection, Topological Data Analysis
Published	2018-05-25
URL	http://arxiv.org/abs/1805.09949v1
PDF	http://arxiv.org/pdf/1805.09949v1.pdf
PWC	https://paperswithcode.com/paper/topological-data-analysis-of-decision
Repo
Framework

A New Angle on L2 Regularization


Title	A New Angle on L2 Regularization
Authors	Thomas Tanay, Lewis D Griffin
Abstract	Imagine two high-dimensional clusters and a hyperplane separating them. Consider in particular the angle between: the direction joining the two clusters’ centroids and the normal to the hyperplane. In linear classification, this angle depends on the level of L2 regularization used. Can you explain why?
Tasks	L2 Regularization
Published	2018-06-28
URL	http://arxiv.org/abs/1806.11186v1
PDF	http://arxiv.org/pdf/1806.11186v1.pdf
PWC	https://paperswithcode.com/paper/a-new-angle-on-l2-regularization
Repo
Framework

A Tutorial on Modular Ontology Modeling with Ontology Design Patterns: The Cooking Recipes Ontology


Title	A Tutorial on Modular Ontology Modeling with Ontology Design Patterns: The Cooking Recipes Ontology
Authors	Pascal Hitzler, Adila Krisnadhi
Abstract	We provide a detailed example for modular ontology modeling based on ontology design patterns.
Tasks
Published	2018-08-25
URL	http://arxiv.org/abs/1808.08433v1
PDF	http://arxiv.org/pdf/1808.08433v1.pdf
PWC	https://paperswithcode.com/paper/a-tutorial-on-modular-ontology-modeling-with
Repo
Framework

SGR: Self-Supervised Spectral Graph Representation Learning


Title	SGR: Self-Supervised Spectral Graph Representation Learning
Authors	Anton Tsitsulin, Davide Mottin, Panagiotis Karras, Alex Bronstein, Emmanuel Müller
Abstract	Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand. Unfortunately, a “one-size-fits-all” solution is unattainable, as different analytical tasks may require different attention to global or local graph features. We develop SGR, the first, to our knowledge, method for learning graph representations in a self-supervised manner. Grounded on spectral graph analysis, SGR seamlessly combines all aforementioned desirable properties. In extensive experiments, we show how our approach works on large graph collections, facilitates self-supervised representation learning across a variety of application domains, and performs competitively to state-of-the-art methods without re-training.
Tasks	Graph Representation Learning, Representation Learning
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06237v1
PDF	http://arxiv.org/pdf/1811.06237v1.pdf
PWC	https://paperswithcode.com/paper/sgr-self-supervised-spectral-graph
Repo
Framework

RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series


Title	RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series
Authors	Qingsong Wen, Jingkun Gao, Xiaomin Song, Liang Sun, Huan Xu, Shenghuo Zhu
Abstract	Decomposing complex time series into trend, seasonality, and remainder components is an important task to facilitate time series anomaly detection and forecasting. Although numerous methods have been proposed, there are still many time series characteristics exhibiting in real-world data which are not addressed properly, including 1) ability to handle seasonality fluctuation and shift, and abrupt change in trend and reminder; 2) robustness on data with anomalies; 3) applicability on time series with long seasonality period. In the paper, we propose a novel and generic time series decomposition algorithm to address these challenges. Specifically, we extract the trend component robustly by solving a regression problem using the least absolute deviations loss with sparse regularization. Based on the extracted trend, we apply the the non-local seasonal filtering to extract the seasonality component. This process is repeated until accurate decomposition is obtained. Experiments on different synthetic and real-world time series datasets demonstrate that our method outperforms existing solutions.
Tasks	Anomaly Detection, Time Series
Published	2018-12-05
URL	http://arxiv.org/abs/1812.01767v1
PDF	http://arxiv.org/pdf/1812.01767v1.pdf
PWC	https://paperswithcode.com/paper/robuststl-a-robust-seasonal-trend
Repo
Framework

Trusted Neural Networks for Safety-Constrained Autonomous Control


Title	Trusted Neural Networks for Safety-Constrained Autonomous Control
Authors	Shalini Ghosh, Amaury Mercier, Dheeraj Pichapati, Susmit Jha, Vinod Yegneswaran, Patrick Lincoln
Abstract	We propose Trusted Neural Network (TNN) models, which are deep neural network models that satisfy safety constraints critical to the application domain. We investigate different mechanisms for incorporating rule-based knowledge in the form of first-order logic constraints into a TNN model, where rules that encode safety are accompanied by weights indicating their relative importance. This framework allows the TNN model to learn from knowledge available in form of data as well as logical rules. We propose multiple approaches for solving this problem: (a) a multi-headed model structure that allows trade-off between satisfying logical constraints and fitting training data in a unified training framework, and (b) creating a constrained optimization problem and solving it in dual formulation by posing a new constrained loss function and using a proximal gradient descent algorithm. We demonstrate the efficacy of our TNN framework through experiments using the open-source TORCS~\cite{BernhardCAA15} 3D simulator for self-driving cars. Experiments using our first approach of a multi-headed TNN model, on a dataset generated by a customized version of TORCS, show that (1) adding safety constraints to a neural network model results in increased performance and safety, and (2) the improvement increases with increasing importance of the safety constraints. Experiments were also performed using the second approach of proximal algorithm for constrained optimization — they demonstrate how the proposed method ensures that (1) the overall TNN model satisfies the constraints even when the training data violates some of the constraints, and (2) the proximal gradient descent algorithm on the constrained objective converges faster than the unconstrained version.
Tasks	Self-Driving Cars
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07075v1
PDF	http://arxiv.org/pdf/1805.07075v1.pdf
PWC	https://paperswithcode.com/paper/trusted-neural-networks-for-safety
Repo
Framework

Vehicle Communication Strategies for Simulated Highway Driving


Title	Vehicle Communication Strategies for Simulated Highway Driving
Authors	Cinjon Resnick, Ilya Kulikov, Kyunghyun Cho, Jason Weston
Abstract	Interest in emergent communication has recently surged in Machine Learning. The focus of this interest has largely been either on investigating the properties of the learned protocol or on utilizing emergent communication to better solve problems that already have a viable solution. Here, we consider self-driving cars coordinating with each other and focus on how communication influences the agents’ collective behavior. Our main result is that communication helps (most) with adverse conditions.
Tasks	Self-Driving Cars
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07178v2
PDF	http://arxiv.org/pdf/1804.07178v2.pdf
PWC	https://paperswithcode.com/paper/vehicle-communication-strategies-for
Repo
Framework