October 20, 2019

3162 words 15 mins read

Paper Group ANR 26

On the Conditional Logic of Simulation Models. Multimodal Sentiment Analysis: Addressing Key Issues and Setting up the Baselines. A CADe System for Gliomas in Brain MRI using Convolutional Neural Networks. AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference. Intertwiners between Induced Representations (with Applications to …

On the Conditional Logic of Simulation Models


Title	On the Conditional Logic of Simulation Models
Authors	Duligur Ibeling, Thomas Icard
Abstract	We propose analyzing conditional reasoning by appeal to a notion of intervention on a simulation program, formalizing and subsuming a number of approaches to conditional thinking in the recent AI literature. Our main results include a series of axiomatizations, allowing comparison between this framework and existing frameworks (normality-ordering models, causal structural equation models), and a complexity result establishing NP-completeness of the satisfiability problem. Perhaps surprisingly, some of the basic logical principles common to all existing approaches are invalidated in our causal simulation approach. We suggest that this additional flexibility is important in modeling some intuitive examples.
Tasks
Published	2018-05-08
URL	http://arxiv.org/abs/1805.02859v1
PDF	http://arxiv.org/pdf/1805.02859v1.pdf
PWC	https://paperswithcode.com/paper/on-the-conditional-logic-of-simulation-models
Repo
Framework

Multimodal Sentiment Analysis: Addressing Key Issues and Setting up the Baselines


Title	Multimodal Sentiment Analysis: Addressing Key Issues and Setting up the Baselines
Authors	Soujanya Poria, Navonil Majumder, Devamanyu Hazarika, Erik Cambria, Alexander Gelbukh, Amir Hussain
Abstract	We compile baselines, along with dataset split, for multimodal sentiment analysis. In this paper, we explore three different deep-learning based architectures for multimodal sentiment classification, each improving upon the previous. Further, we evaluate these architectures with multiple datasets with fixed train/test partition. We also discuss some major issues, frequently ignored in multimodal sentiment analysis research, e.g., role of speaker-exclusive models, importance of different modalities, and generalizability. This framework illustrates the different facets of analysis to be considered while performing multimodal sentiment analysis and, hence, serves as a new benchmark for future research in this emerging field.
Tasks	Multimodal Sentiment Analysis, Sentiment Analysis
Published	2018-03-19
URL	http://arxiv.org/abs/1803.07427v2
PDF	http://arxiv.org/pdf/1803.07427v2.pdf
PWC	https://paperswithcode.com/paper/multimodal-sentiment-analysis-addressing-key
Repo
Framework

A CADe System for Gliomas in Brain MRI using Convolutional Neural Networks


Title	A CADe System for Gliomas in Brain MRI using Convolutional Neural Networks
Authors	Subhasis Banerjee, Sushmita Mitra, Anmol Sharma, B. Uma Shankar
Abstract	Inspired by the success of Convolutional Neural Networks (CNN), we develop a novel Computer Aided Detection (CADe) system using CNN for Glioblastoma Multiforme (GBM) detection and segmentation from multi channel MRI data. A two-stage approach first identifies the presence of GBM. This is followed by a GBM localization in each “abnormal” MR slice. As part of the CADe system, two CNN architectures viz. Classification CNN (C-CNN) and Detection CNN (D-CNN) are employed. The CADe system considers MRI data consisting of four sequences ($T_1$, $T_{1c},$ $T_2$, and $T_{2FLAIR}$) as input, and automatically generates the bounding boxes encompassing the tumor regions in each slice which is deemed abnormal. Experimental results demonstrate that the proposed CADe system, when used as a preliminary step before segmentation, can allow improved delineation of tumor region while reducing false positives arising in normal areas of the brain. The GrowCut method, employed for tumor segmentation, typically requires a foreground and background seed region for initialization. Here the algorithm is initialized with seeds automatically generated from the output of the proposed CADe system, thereby resulting in improved performance as compared to that using random seeds.
Tasks
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07589v1
PDF	http://arxiv.org/pdf/1806.07589v1.pdf
PWC	https://paperswithcode.com/paper/a-cade-system-for-gliomas-in-brain-mri-using
Repo
Framework

AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference


Title	AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference
Authors	Xin He, Liu Ke, Wenyan Lu, Guihai Yan, Xuan Zhang
Abstract	The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference. Conventional approximate computing focuses on balancing the efficiency-accuracy trade-off for existing pre-trained networks, which can lead to suboptimal solutions. In this paper, we propose AxTrain, a hardware-oriented training framework to facilitate approximate computing for NN inference. Specifically, AxTrain leverages the synergy between two orthogonal methods—one actively searches for a network parameters distribution with high error tolerance, and the other passively learns resilient weights by numerically incorporating the noise distributions of the approximate hardware in the forward pass during the training phase. Experimental results from various datasets with near-threshold computing and approximation multiplication strategies demonstrate AxTrain’s ability to obtain resilient neural network parameters and system energy efficiency improvement.
Tasks
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08309v1
PDF	http://arxiv.org/pdf/1805.08309v1.pdf
PWC	https://paperswithcode.com/paper/axtrain-hardware-oriented-neural-network
Repo
Framework

Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)


Title	Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)
Authors	Taco S. Cohen, Mario Geiger, Maurice Weiler
Abstract	Group equivariant and steerable convolutional neural networks (regular and steerable G-CNNs) have recently emerged as a very effective model class for learning from signal data such as 2D and 3D images, video, and other data where symmetries are present. In geometrical terms, regular G-CNNs represent data in terms of scalar fields (“feature channels”), whereas the steerable G-CNN can also use vector or tensor fields (“capsules”) to represent data. In algebraic terms, the feature spaces in regular G-CNNs transform according to a regular representation of the group G, whereas the feature spaces in Steerable G-CNNs transform according to the more general induced representations of G. In order to make the network equivariant, each layer in a G-CNN is required to intertwine between the induced representations associated with its input and output space. In this paper we present a general mathematical framework for G-CNNs on homogeneous spaces like Euclidean space or the sphere. We show, using elementary methods, that the layers of an equivariant network are convolutional if and only if the input and output feature spaces transform according to an induced representation. This result, which follows from G.W. Mackey’s abstract theory on induced representations, establishes G-CNNs as a universal class of equivariant network architectures, and generalizes the important recent work of Kondor & Trivedi on the intertwiners between regular representations.
Tasks
Published	2018-03-28
URL	http://arxiv.org/abs/1803.10743v2
PDF	http://arxiv.org/pdf/1803.10743v2.pdf
PWC	https://paperswithcode.com/paper/intertwiners-between-induced-representations
Repo
Framework

Simulator Calibration under Covariate Shift with Kernels


Title	Simulator Calibration under Covariate Shift with Kernels
Authors	Keiichi Kisamori, Motonobu Kanagawa, Keisuke Yamazaki
Abstract	We propose a novel calibration method for computer simulators, dealing with the problem of covariate shift. Covariate shift is the situation where input distributions for training and test are different, and ubiquitous in applications of simulations. Our approach is based on Bayesian inference with kernel mean embedding of distributions, and on the use of an importance-weighted reproducing kernel for covariate shift adaptation. We provide a theoretical analysis for the proposed method, including a novel theoretical result for conditional mean embedding, as well as empirical investigations suggesting its effectiveness in practice. The experiments include calibration of a widely used simulator for industrial manufacturing processes, where we also demonstrate how the proposed method may be useful for sensitivity analysis of model parameters.
Tasks	Bayesian Inference, Calibration
Published	2018-09-21
URL	https://arxiv.org/abs/1809.08159v4
PDF	https://arxiv.org/pdf/1809.08159v4.pdf
PWC	https://paperswithcode.com/paper/intractable-likelihood-regression-for
Repo
Framework

Fake news as we feel it: perception and conceptualization of the term “fake news” in the media


Title	Fake news as we feel it: perception and conceptualization of the term “fake news” in the media
Authors	Evandro Cunha, Gabriel Magno, Josemar Caetano, Douglas Teixeira, Virgilio Almeida
Abstract	In this article, we quantitatively analyze how the term “fake news” is being shaped in news media in recent years. We study the perception and the conceptualization of this term in the traditional media using eight years of data collected from news outlets based in 20 countries. Our results not only corroborate previous indications of a high increase in the usage of the expression “fake news”, but also show contextual changes around this expression after the United States presidential election of 2016. Among other results, we found changes in the related vocabulary, in the mentioned entities, in the surrounding topics and in the contextual polarity around the term “fake news”, suggesting that this expression underwent a change in perception and conceptualization after 2016. These outcomes expand the understandings on the usage of the term “fake news”, helping to comprehend and more accurately characterize this relevant social phenomenon linked to misinformation and manipulation.
Tasks
Published	2018-07-18
URL	http://arxiv.org/abs/1807.06926v1
PDF	http://arxiv.org/pdf/1807.06926v1.pdf
PWC	https://paperswithcode.com/paper/fake-news-as-we-feel-it-perception-and
Repo
Framework

Conditionals in Homomorphic Encryption and Machine Learning Applications


Title	Conditionals in Homomorphic Encryption and Machine Learning Applications
Authors	Diego Chialva, Ann Dooms
Abstract	Homomorphic encryption aims at allowing computations on encrypted data without decryption other than that of the final result. This could provide an elegant solution to the issue of privacy preservation in data-based applications, such as those using machine learning, but several open issues hamper this plan. In this work we assess the possibility for homomorphic encryption to fully implement its program without relying on other techniques, such as multiparty computation (SMPC), which may be impossible in many use cases (for instance due to the high level of communication required). We proceed in two steps: i) on the basis of the structured program theorem (Bohm-Jacopini theorem) we identify the relevant minimal set of operations homomorphic encryption must be able to perform to implement any algorithm; and ii) we analyse the possibility to solve – and propose an implementation for – the most fundamentally relevant issue as it emerges from our analysis, that is, the implementation of conditionals (requiring comparison and selection/jump operations). We show how this issue clashes with the fundamental requirements of homomorphic encryption and could represent a drawback for its use as a complete solution for privacy preservation in data-based applications, in particular machine learning ones. Our approach for comparisons is novel and entirely embedded in homomorphic encryption, while previous studies relied on other techniques, such as SMPC, demanding high level of communication among parties, and decryption of intermediate results from data-owners. Our protocol is also provably safe (sharing the same safety as the homomorphic encryption schemes), differently from other techniques such as Order-Preserving/Revealing-Encryption (OPE/ORE).
Tasks
Published	2018-10-29
URL	https://arxiv.org/abs/1810.12380v2
PDF	https://arxiv.org/pdf/1810.12380v2.pdf
PWC	https://paperswithcode.com/paper/conditionals-in-homomorphic-encryption-and
Repo
Framework

Solving the clustered traveling salesman problem with d-relaxed priority rule


Title	Solving the clustered traveling salesman problem with d-relaxed priority rule
Authors	Hoa Nguyen Phuong, Huyen Tran Ngoc Nhat, Minh Hoàng Hà, André Langevin, Martin Trépanier
Abstract	The Clustered Traveling Salesman Problem with a Prespecified Order on the Clusters, a variant of the well-known traveling salesman problem is studied in literature. In this problem, delivery locations are divided into clusters with different urgency levels and more urgent locations must be visited before less urgent ones. However, this could lead to an inefficient route in terms of traveling cost. This priority-oriented constraint can be relaxed by a rule called d-relaxed priority that provides a trade-off between transportation cost and emergency level. Our research proposes two approaches to solve the problem with d-relaxed priority rule. We improve the mathematical formulation proposed in the literature to construct an exact solution method. A meta-heuristic method based on the framework of Iterated Local Search with problem-tailored operators is also introduced to find approximate solutions. Experimental results show the effectiveness of our methods.
Tasks
Published	2018-10-06
URL	http://arxiv.org/abs/1810.03981v1
PDF	http://arxiv.org/pdf/1810.03981v1.pdf
PWC	https://paperswithcode.com/paper/solving-the-clustered-traveling-salesman
Repo
Framework

Generative Ratio Matching Networks


Title	Generative Ratio Matching Networks
Authors	Akash Srivastava, Kai Xu, Michael U. Gutmann, Charles Sutton
Abstract	Deep generative models can learn to generate realistic-looking images, but many of the most effective methods are adversarial and involve a saddlepoint optimization, which requires a careful balancing of training between a generator network and a critic network. Maximum mean discrepancy networks (MMD-nets) avoid this issue by using kernel as a fixed adversary, but unfortunately, they have not on their own been able to match the generative quality of adversarial training. In this work, we take their insight of using kernels as fixed adversaries further and present a novel method for training deep generative models that does not involve saddlepoint optimization. We call our method generative ratio matching or GRAM for short. In GRAM, the generator and the critic networks do not play a zero-sum game against each other, instead, they do so against a fixed kernel. Thus GRAM networks are not only stable to train like MMD-nets but they also match and beat the generative quality of adversarially trained generative networks.
Tasks
Published	2018-05-31
URL	https://arxiv.org/abs/1806.00101v3
PDF	https://arxiv.org/pdf/1806.00101v3.pdf
PWC	https://paperswithcode.com/paper/ratio-matching-mmd-nets-low-dimensional
Repo
Framework

Multi-user Communication Networks: A Coordinated Multi-armed Bandit Approach


Title	Multi-user Communication Networks: A Coordinated Multi-armed Bandit Approach
Authors	Orly Avner, Shie Mannor
Abstract	Communication networks shared by many users are a widespread challenge nowadays. In this paper we address several aspects of this challenge simultaneously: learning unknown stochastic network characteristics, sharing resources with other users while keeping coordination overhead to a minimum. The proposed solution combines Multi-Armed Bandit learning with a lightweight signalling-based coordination scheme, and ensures convergence to a stable allocation of resources. Our work considers single-user level algorithms for two scenarios: an unknown fixed number of users, and a dynamic number of users. Analytic performance guarantees, proving convergence to stable marriage configurations, are presented for both setups. The algorithms are designed based on a system-wide perspective, rather than focusing on single user welfare. Thus, maximal resource utilization is ensured. An extensive experimental analysis covers convergence to a stable configuration as well as reward maximization. Experiments are carried out over a wide range of setups, demonstrating the advantages of our approach over existing state-of-the-art methods.
Tasks
Published	2018-08-14
URL	http://arxiv.org/abs/1808.04875v1
PDF	http://arxiv.org/pdf/1808.04875v1.pdf
PWC	https://paperswithcode.com/paper/multi-user-communication-networks-a
Repo
Framework

Frank-Wolfe Splitting via Augmented Lagrangian Method


Title	Frank-Wolfe Splitting via Augmented Lagrangian Method
Authors	Gauthier Gidel, Fabian Pedregosa, Simon Lacoste-Julien
Abstract	Minimizing a function over an intersection of convex sets is an important task in optimization that is often much more challenging than minimizing it over each individual constraint set. While traditional methods such as Frank-Wolfe (FW) or proximal gradient descent assume access to a linear or quadratic oracle on the intersection, splitting techniques take advantage of the structure of each sets, and only require access to the oracle on the individual constraints. In this work, we develop and analyze the Frank-Wolfe Augmented Lagrangian (FW-AL) algorithm, a method for minimizing a smooth function over convex compact sets related by a “linear consistency” constraint that only requires access to a linear minimization oracle over the individual constraints. It is based on the Augmented Lagrangian Method (ALM), also known as Method of Multipliers, but unlike most existing splitting methods, it only requires access to linear (instead of quadratic) minimization oracles. We use recent advances in the analysis of Frank-Wolfe and the alternating direction method of multipliers algorithms to prove a sublinear convergence rate for FW-AL over general convex compact sets and a linear convergence rate for polytopes.
Tasks
Published	2018-04-09
URL	http://arxiv.org/abs/1804.03176v1
PDF	http://arxiv.org/pdf/1804.03176v1.pdf
PWC	https://paperswithcode.com/paper/frank-wolfe-splitting-via-augmented
Repo
Framework

Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping


Title	Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
Authors	Chuhui Xue, Shijian Lu, Fangneng Zhan
Abstract	This paper presents a scene text detection technique that exploits bootstrapping and text border semantics for accurate localization of texts in scenes. A novel bootstrapping technique is designed which samples multiple ‘subsections’ of a word or text line and accordingly relieves the constraint of limited training data effectively. At the same time, the repeated sampling of text ‘subsections’ improves the consistency of the predicted text feature maps which is critical in predicting a single complete instead of multiple broken boxes for long words or text lines. In addition, a semantics-aware text border detection technique is designed which produces four types of text border segments for each scene text. With semantics-aware text borders, scene texts can be localized more accurately by regressing text pixels around the ends of words or text lines instead of all text pixels which often leads to inaccurate localization while dealing with long words or text lines. Extensive experiments demonstrate the effectiveness of the proposed techniques, and superior performance is obtained over several public datasets, e. g. 80.1 f-score for the MSRA-TD500, 67.1 f-score for the ICDAR2017-RCTW, etc.
Tasks	Scene Text Detection
Published	2018-07-10
URL	http://arxiv.org/abs/1807.03547v3
PDF	http://arxiv.org/pdf/1807.03547v3.pdf
PWC	https://paperswithcode.com/paper/accurate-scene-text-detection-through-border
Repo
Framework

Non-Parametric Variational Inference with Graph Convolutional Networks for Gaussian Processes


Title	Non-Parametric Variational Inference with Graph Convolutional Networks for Gaussian Processes
Authors	Linfeng Liu, Liping Liu
Abstract	Inference for GP models with non-Gaussian noises is computationally expensive when dealing with large datasets. Many recent inference methods approximate the posterior distribution with a simpler distribution defined on a small number of inducing points. The inference is accurate only when data points have strong correlation with these inducing points. In this paper, we consider the inference problem in a different direction: GP function values in the posterior are mostly correlated in short distance. We construct a variational distribution such that the inference for a data point considers only its neighborhood. With this construction, the variational lower bound is highly decomposible, hence we can run stochastic optimization with very small batches. We then train Graph Convolutional Networks as a reusable model to identify variational parameters for each data point. Model reuse greatly reduces the number of parameters and the number of iterations needed in optimization. The proposed method significantly speeds up the inference and often gets more accurate results than previous methods.
Tasks	Gaussian Processes, Stochastic Optimization
Published	2018-09-08
URL	http://arxiv.org/abs/1809.02838v1
PDF	http://arxiv.org/pdf/1809.02838v1.pdf
PWC	https://paperswithcode.com/paper/non-parametric-variational-inference-with
Repo
Framework

PhD Dissertation: Generalized Independent Components Analysis Over Finite Alphabets


Title	PhD Dissertation: Generalized Independent Components Analysis Over Finite Alphabets
Authors	Amichai Painsky
Abstract	Independent component analysis (ICA) is a statistical method for transforming an observable multi-dimensional random vector into components that are as statistically independent as possible from each other. Usually the ICA framework assumes a model according to which the observations are generated (such as a linear transformation with additive noise). ICA over finite fields is a special case of ICA in which both the observations and the independent components are over a finite alphabet. In this thesis we consider a formulation of the finite-field case in which an observation vector is decomposed to its independent components (as much as possible) with no prior assumption on the way it was generated. This generalization is also known as Barlow’s minimal redundancy representation and is considered an open problem. We propose several theorems and show that this hard problem can be accurately solved with a branch and bound search tree algorithm, or tightly approximated with a series of linear problems. Moreover, we show that there exists a simple transformation (namely, order permutation) which provides a greedy yet very effective approximation of the optimal solution. We further show that while not every random vector can be efficiently decomposed into independent components, the vast majority of vectors do decompose very well (that is, within a small constant cost), as the dimension increases. In addition, we show that we may practically achieve this favorable constant cost with a complexity that is asymptotically linear in the alphabet size. Our contribution provides the first efficient set of solutions to Barlow’s problem with theoretical and computational guarantees. Finally, we demonstrate our suggested framework in multiple source coding applications.
Tasks
Published	2018-09-13
URL	http://arxiv.org/abs/1809.05043v4
PDF	http://arxiv.org/pdf/1809.05043v4.pdf
PWC	https://paperswithcode.com/paper/phd-dissertation-generalized-independent
Repo
Framework