October 19, 2019

3139 words 15 mins read

Paper Group ANR 162

A Summary of Adaptation of Techniques from Search-based Optimal Multi-Agent Path Finding Solvers to Compilation-based Approach. Automatic Generation of Language-Independent Features for Cross-Lingual Classification. Development of ICA and IVA Algorithms with Application to Medical Image Analysis. Improving Clinical Predictions through Unsupervised …

A Summary of Adaptation of Techniques from Search-based Optimal Multi-Agent Path Finding Solvers to Compilation-based Approach


Title	A Summary of Adaptation of Techniques from Search-based Optimal Multi-Agent Path Finding Solvers to Compilation-based Approach
Authors	Pavel Surynek
Abstract	In the multi-agent path finding problem (MAPF) we are given a set of agents each with respective start and goal positions. The task is to find paths for all agents while avoiding collisions aiming to minimize an objective function. Two such common objective functions is the sum-of-costs and the makespan. Many optimal solvers were introduced in the past decade - two prominent categories of solvers can be distinguished: search-based solvers and compilation-based solvers. Search-based solvers were developed and tested for the sum-of-costs objective while the most prominent compilation-based solvers that are built around Boolean satisfiability (SAT) were designed for the makespan objective. Very little was known on the performance and relevance of the compilation-based approach on the sum-of-costs objective. In this paper we show how to close the gap between these cost functions in the compilation-based approach. Moreover we study applicability of various techniques developed for search-based solvers in the compilation-based approach. A part of this paper introduces a SAT-solver that is directly aimed to solve the sum-of-costs objective function. Using both a lower bound on the sum-of-costs and an upper bound on the makespan, we are able to have a reasonable number of variables in our SAT encoding. We then further improve the encoding by borrowing ideas from ICTS, a search-based solver. Experimental evaluation on several domains show that there are many scenarios where our new SAT-based methods outperforms the best variants of previous sum-of-costs search solvers - the ICTS, CBS algorithms, and ICBS algorithms.
Tasks	Multi-Agent Path Finding
Published	2018-12-28
URL	http://arxiv.org/abs/1812.10851v1
PDF	http://arxiv.org/pdf/1812.10851v1.pdf
PWC	https://paperswithcode.com/paper/a-summary-of-adaptation-of-techniques-from
Repo
Framework

Automatic Generation of Language-Independent Features for Cross-Lingual Classification


Title	Automatic Generation of Language-Independent Features for Cross-Lingual Classification
Authors	Sarai Duek, Shaul Markovitch
Abstract	Many applications require categorization of text documents using predefined categories. The main approach to performing text categorization is learning from labeled examples. For many tasks, it may be difficult to find examples in one language but easy in others. The problem of learning from examples in one or more languages and classifying (categorizing) in another is called cross-lingual learning. In this work, we present a novel approach that solves the general cross-lingual text categorization problem. Our method generates, for each training document, a set of language-independent features. Using these features for training yields a language-independent classifier. At the classification stage, we generate language-independent features for the unlabeled document, and apply the classifier on the new representation. To build the feature generator, we utilize a hierarchical language-independent ontology, where each concept has a set of support documents for each language involved. In the preprocessing stage, we use the support documents to build a set of language-independent feature generators, one for each language. The collection of these generators is used to map any document into the language-independent feature space. Our methodology works on the most general cross-lingual text categorization problems, being able to learn from any mix of languages and classify documents in any other language. We also present a method for exploiting the hierarchical structure of the ontology to create virtual supporting documents for languages that do not have them. We tested our method, using Wikipedia as our ontology, on the most commonly used test collections in cross-lingual text categorization, and found that it outperforms existing methods.
Tasks	Text Categorization
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04028v1
PDF	http://arxiv.org/pdf/1802.04028v1.pdf
PWC	https://paperswithcode.com/paper/automatic-generation-of-language-independent
Repo
Framework

Development of ICA and IVA Algorithms with Application to Medical Image Analysis


Title	Development of ICA and IVA Algorithms with Application to Medical Image Analysis
Authors	Zois Boukouvalas
Abstract	Independent component analysis (ICA) is a widely used BSS method that can uniquely achieve source recovery, subject to only scaling and permutation ambiguities, through the assumption of statistical independence on the part of the latent sources. Independent vector analysis (IVA) extends the applicability of ICA by jointly decomposing multiple datasets through the exploitation of the dependencies across datasets. Though both ICA and IVA algorithms cast in the maximum likelihood (ML) framework enable the use of all available statistical information in reality, they often deviate from their theoretical optimality properties due to improper estimation of the probability density function (PDF). This motivates the development of flexible ICA and IVA algorithms that closely adhere to the underlying statistical description of the data. Although it is attractive minimize the assumptions, important prior information about the data, such as sparsity, is usually available. If incorporated into the ICA model, use of this additional information can relax the independence assumption, resulting in an improvement in the overall separation performance. Therefore, the development of a unified mathematical framework that can take into account both statistical independence and sparsity is of great interest. In this work, we first introduce a flexible ICA algorithm that uses an effective PDF estimator to accurately capture the underlying statistical properties of the data. We then discuss several techniques to accurately estimate the parameters of the multivariate generalized Gaussian distribution, and how to integrate them into the IVA model. Finally, we provide a mathematical framework that enables direct control over the influence of statistical independence and sparsity, and use this framework to develop an effective ICA algorithm that can jointly exploit these two forms of diversity.
Tasks
Published	2018-01-25
URL	http://arxiv.org/abs/1801.08600v1
PDF	http://arxiv.org/pdf/1801.08600v1.pdf
PWC	https://paperswithcode.com/paper/development-of-ica-and-iva-algorithms-with
Repo
Framework

Improving Clinical Predictions through Unsupervised Time Series Representation Learning


Title	Improving Clinical Predictions through Unsupervised Time Series Representation Learning
Authors	Xinrui Lyu, Matthias Hueser, Stephanie L. Hyland, George Zerveas, Gunnar Raetsch
Abstract	In this work, we investigate unsupervised representation learning on medical time series, which bears the promise of leveraging copious amounts of existing unlabeled data in order to eventually assist clinical decision making. By evaluating on the prediction of clinically relevant outcomes, we show that in a practical setting, unsupervised representation learning can offer clear performance benefits over end-to-end supervised architectures. We experiment with using sequence-to-sequence (Seq2Seq) models in two different ways, as an autoencoder and as a forecaster, and show that the best performance is achieved by a forecasting Seq2Seq model with an integrated attention mechanism, proposed here for the first time in the setting of unsupervised learning for medical time series.
Tasks	Decision Making, Representation Learning, Time Series, Unsupervised Representation Learning
Published	2018-12-02
URL	http://arxiv.org/abs/1812.00490v1
PDF	http://arxiv.org/pdf/1812.00490v1.pdf
PWC	https://paperswithcode.com/paper/improving-clinical-predictions-through
Repo
Framework

Line Artist: A Multiple Style Sketch to Painting Synthesis Scheme


Title	Line Artist: A Multiple Style Sketch to Painting Synthesis Scheme
Authors	Jinning Li, Siqi Liu, Mengyao Cao
Abstract	Drawing a beautiful painting is a dream of many people since childhood. In this paper, we propose a novel scheme, Line Artist, to synthesize artistic style paintings with freehand sketch images, leveraging the power of deep learning and advanced algorithms. Our scheme includes three models. The Sketch Image Extraction (SIE) model is applied to generate the training data. It includes smoothing reality images and pencil sketch extraction. The Detailed Image Synthesis (DIS) model trains a conditional generative adversarial network to generate detailed real-world information. The Adaptively Weighted Artistic Style Transfer (AWAST) model is capable to combine multiple style images with a content with the VGG19 network and PageRank algorithm. The appealing artistic images are then generated by optimization iterations. Experiments are operated on the Kaggle Cats dataset and The Oxford Buildings Dataset. Our synthesis results are proved to be artistic, beautiful and robust.
Tasks	Image Generation, Style Transfer
Published	2018-03-18
URL	http://arxiv.org/abs/1803.06647v1
PDF	http://arxiv.org/pdf/1803.06647v1.pdf
PWC	https://paperswithcode.com/paper/line-artist-a-multiple-style-sketch-to
Repo
Framework

Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem


Title	Stochastically Controlled Stochastic Gradient for the Convex and Non-convex Composition problem
Authors	Liu Liu, Ji Liu, Cho-Jui Hsieh, Dacheng Tao
Abstract	In this paper, we consider the convex and non-convex composition problem with the structure $\frac{1}{n}\sum\nolimits_{i = 1}^n {{F_i}( {G( x )} )}$, where $G( x )=\frac{1}{n}\sum\nolimits_{j = 1}^n {{G_j}( x )} $ is the inner function, and $F_i(\cdot)$ is the outer function. We explore the variance reduction based method to solve the composition optimization. Due to the fact that when the number of inner function and outer function are large, it is not reasonable to estimate them directly, thus we apply the stochastically controlled stochastic gradient (SCSG) method to estimate the gradient of the composition function and the value of the inner function. The query complexity of our proposed method for the convex and non-convex problem is equal to or better than the current method for the composition problem. Furthermore, we also present the mini-batch version of the proposed method, which has the improved the query complexity with related to the size of the mini-batch.
Tasks
Published	2018-09-06
URL	http://arxiv.org/abs/1809.02505v1
PDF	http://arxiv.org/pdf/1809.02505v1.pdf
PWC	https://paperswithcode.com/paper/stochastically-controlled-stochastic-gradient
Repo
Framework

Bridging Cognitive Programs and Machine Learning


Title	Bridging Cognitive Programs and Machine Learning
Authors	Amir Rosenfeld, John K. Tsotsos
Abstract	While great advances are made in pattern recognition and machine learning, the successes of such fields remain restricted to narrow applications and seem to break down when training data is scarce, a shift in domain occurs, or when intelligent reasoning is required for rapid adaptation to new environments. In this work, we list several of the shortcomings of modern machine-learning solutions, specifically in the contexts of computer vision and in reinforcement learning and suggest directions to explore in order to try to ameliorate these weaknesses.
Tasks
Published	2018-02-16
URL	http://arxiv.org/abs/1802.06091v1
PDF	http://arxiv.org/pdf/1802.06091v1.pdf
PWC	https://paperswithcode.com/paper/bridging-cognitive-programs-and-machine
Repo
Framework

Deep Feature Pyramid Reconfiguration for Object Detection


Title	Deep Feature Pyramid Reconfiguration for Object Detection
Authors	Tao Kong, Fuchun Sun, Wenbing Huang, Huaping Liu
Abstract	State-of-the-art object detectors usually learn multi-scale representations to get better results by employing feature pyramids. However, the current designs for feature pyramids are still inefficient to integrate the semantic information over different scales. In this paper, we begin by investigating current feature pyramids solutions, and then reformulate the feature pyramid construction as the feature reconfiguration process. Finally, we propose a novel reconfiguration architecture to combine low-level representations with high-level semantic features in a highly-nonlinear yet efficient way. In particular, our architecture which consists of global attention and local reconfigurations, is able to gather task-oriented features across different spatial locations and scales, globally and locally. Both the global attention and local reconfiguration are lightweight, in-place, and end-to-end trainable. Using this method in the basic SSD system, our models achieve consistent and significant boosts compared with the original model and its other variations, without losing real-time processing speed.
Tasks	Object Detection
Published	2018-08-24
URL	http://arxiv.org/abs/1808.07993v1
PDF	http://arxiv.org/pdf/1808.07993v1.pdf
PWC	https://paperswithcode.com/paper/deep-feature-pyramid-reconfiguration-for
Repo
Framework

Enhancing Selection Hyper-heuristics via Feature Transformations


Title	Enhancing Selection Hyper-heuristics via Feature Transformations
Authors	I. Amaya, J. C. Ortiz-Bayliss, A. Rosales-Pérez, A. E. Gutiérrez-Rodríguez, S. E. Conant-Pablos, H. Terashima-Marín, C. A. Coello Coello
Abstract	Hyper-heuristics are a novel tool. They deal with complex optimization problems where standalone solvers exhibit varied performance. Among such a tool reside selection hyper-heuristics. By combining the strengths of each solver, this kind of hyper-heuristic offers a more robust tool. However, their effectiveness is highly dependent on the ‘features’ used to link them with the problem that is being solved. Aiming at enhancing selection hyper-heuristics, in this paper we propose two types of transformation: explicit and implicit. The first one directly changes the distribution of critical points within the feature domain while using a Euclidean distance to measure proximity. The second one operates indirectly by preserving the distribution of critical points but changing the distance metric through a kernel function. We focus on analyzing the effect of each kind of transformation, and of their combinations. We test our ideas in the domain of constraint satisfaction problems because of their popularity and many practical applications. In this work, we compare the performance of our proposals against those of previously published data. Furthermore, we expand on previous research by increasing the number of analyzed features. We found that, by incorporating transformations into the model of selection hyper-heuristics, overall performance can be improved, yielding more stable results. However, combining implicit and explicit transformations was not as fruitful. Additionally, we ran some confirmatory tests on the domain of knapsack problems. Again, we observed improved stability, leading to the generation of hyper-heuristics whose profit had a standard deviation between 20% and 30% smaller.
Tasks
Published	2018-12-12
URL	http://arxiv.org/abs/1812.05070v1
PDF	http://arxiv.org/pdf/1812.05070v1.pdf
PWC	https://paperswithcode.com/paper/enhancing-selection-hyper-heuristics-via
Repo
Framework

Two view constraints on the epipoles from few correspondences


Title	Two view constraints on the epipoles from few correspondences
Authors	Yoni Kasten, Michael Werman
Abstract	In general it requires at least 7 point correspondences to compute the fundamental matrix between views. We use the cross ratio invariance between corresponding epipolar lines, stemming from epipolar line homography, to derive a simple formulation for the relationship between epipoles and corresponding points. We show how it can be used to reduce the number of required points for the epipolar geometry when some information about the epipoles is available and demonstrate this with a buddy search app.
Tasks
Published	2018-10-22
URL	http://arxiv.org/abs/1810.09496v1
PDF	http://arxiv.org/pdf/1810.09496v1.pdf
PWC	https://paperswithcode.com/paper/two-view-constraints-on-the-epipoles-from-few
Repo
Framework

Polynomial-time probabilistic reasoning with partial observations via implicit learning in probability logics


Title	Polynomial-time probabilistic reasoning with partial observations via implicit learning in probability logics
Authors	Brendan Juba
Abstract	Standard approaches to probabilistic reasoning require that one possesses an explicit model of the distribution in question. But, the empirical learning of models of probability distributions from partial observations is a problem for which efficient algorithms are generally not known. In this work we consider the use of bounded-degree fragments of the “sum-of-squares” logic as a probability logic. Prior work has shown that we can decide refutability for such fragments in polynomial-time. We propose to use such fragments to answer queries about whether a given probability distribution satisfies a given system of constraints and bounds on expected values. We show that in answering such queries, such constraints and bounds can be implicitly learned from partial observations in polynomial-time as well. It is known that this logic is capable of deriving many bounds that are useful in probabilistic analysis. We show here that it furthermore captures useful polynomial-time fragments of resolution. Thus, these fragments are also quite expressive.
Tasks
Published	2018-06-28
URL	http://arxiv.org/abs/1806.11204v1
PDF	http://arxiv.org/pdf/1806.11204v1.pdf
PWC	https://paperswithcode.com/paper/polynomial-time-probabilistic-reasoning-with
Repo
Framework

MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices


Title	MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices
Authors	Chi Nhan Duong, Kha Gia Quach, Ibsa Jalata, Ngan Le, Khoa Luu
Abstract	Deep neural networks have been widely used in numerous computer vision applications, particularly in face recognition. However, deploying deep neural network face recognition on mobile devices has recently become a trend but still limited since most high-accuracy deep models are both time and GPU consumption in the inference stage. Therefore, developing a lightweight deep neural network is one of the most practical solutions to deploy face recognition on mobile devices. Such the lightweight deep neural network requires efficient memory with small number of weights representation and low cost operators. In this paper, a novel deep neural network named MobiFace, a simple but effective approach, is proposed for productively deploying face recognition on mobile devices. The experimental results have shown that our lightweight MobiFace is able to achieve high performance with 99.73% on LFW database and 91.3% on large-scale challenging Megaface database. It is also eventually competitive against large-scale deep-networks face recognition while significant reducing computational time and memory consumption.
Tasks	Face Recognition
Published	2018-11-27
URL	http://arxiv.org/abs/1811.11080v2
PDF	http://arxiv.org/pdf/1811.11080v2.pdf
PWC	https://paperswithcode.com/paper/mobiface-a-lightweight-deep-learning-face
Repo
Framework

Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices


Title	Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices
Authors	Jie Zhang, Xiaolong Wang, Dawei Li, Yalin Wang
Abstract	Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems. However, due to their high computational and memory demands, deploying RNNs on resource constrained mobile devices is a challenging task. To guarantee minimum accuracy loss with higher compression rate and driven by the mobile resource requirement, we introduce a novel model compression approach DirNet based on an optimized fast dictionary learning algorithm, which 1) dynamically mines the dictionary atoms of the projection dictionary matrix within layer to adjust the compression rate 2) adaptively changes the sparsity of sparse codes cross the hierarchical layers. Experimental results on language model and an ASR model trained with a 1000h speech dataset demonstrate that our method significantly outperforms prior approaches. Evaluated on off-the-shelf mobile devices, we are able to reduce the size of original model by eight times with real-time model inference and negligible accuracy loss.
Tasks	Dictionary Learning, Language Modelling, Model Compression
Published	2018-06-04
URL	http://arxiv.org/abs/1806.01248v2
PDF	http://arxiv.org/pdf/1806.01248v2.pdf
PWC	https://paperswithcode.com/paper/dynamically-hierarchy-revolution-dirnet-for
Repo
Framework

Lipschitz Networks and Distributional Robustness


Title	Lipschitz Networks and Distributional Robustness
Authors	Zac Cranko, Simon Kornblith, Zhan Shi, Richard Nock
Abstract	Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. We bound the distributionally robust risk for a model class rich enough to include deep neural networks by a regularised empirical risk involving the Lipschitz constant of the model. This allows us to interpretand quantify the robustness properties of a deep neural network. As an application we show the distributionally robust risk upperbounds the adversarial training risk.
Tasks
Published	2018-09-04
URL	http://arxiv.org/abs/1809.01129v1
PDF	http://arxiv.org/pdf/1809.01129v1.pdf
PWC	https://paperswithcode.com/paper/lipschitz-networks-and-distributional
Repo
Framework

Sememe Prediction: Learning Semantic Knowledge from Unstructured Textual Wiki Descriptions


Title	Sememe Prediction: Learning Semantic Knowledge from Unstructured Textual Wiki Descriptions
Authors	Wei Li, Xuancheng Ren, Damai Dai, Yunfang Wu, Houfeng Wang, Xu Sun
Abstract	Huge numbers of new words emerge every day, leading to a great need for representing them with semantic meaning that is understandable to NLP systems. Sememes are defined as the minimum semantic units of human languages, the combination of which can represent the meaning of a word. Manual construction of sememe based knowledge bases is time-consuming and labor-intensive. Fortunately, communities are devoted to composing the descriptions of words in the wiki websites. In this paper, we explore to automatically predict lexical sememes based on the descriptions of the words in the wiki websites. We view this problem as a weakly ordered multi-label task and propose a Label Distributed seq2seq model (LD-seq2seq) with a novel soft loss function to solve the problem. In the experiments, we take a real-world sememe knowledge base HowNet and the corresponding descriptions of the words in Baidu Wiki for training and evaluation. The results show that our LD-seq2seq model not only beats all the baselines significantly on the test set, but also outperforms amateur human annotators in a random subset of the test set.
Tasks
Published	2018-08-16
URL	http://arxiv.org/abs/1808.05437v1
PDF	http://arxiv.org/pdf/1808.05437v1.pdf
PWC	https://paperswithcode.com/paper/sememe-prediction-learning-semantic-knowledge
Repo
Framework