January 31, 2020

3194 words 15 mins read

Paper Group ANR 98

Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification. Deep Model Predictive Control with Online Learning for Complex Physical Systems. SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks. Asynchronous Online Federated Learning for Edge Devices. A Temporal Modul …

Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification


Title	Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification
Authors	Cheng Deng, Xianglong Liu, Chao Li, Dacheng Tao
Abstract	Recent years have witnessed the quick progress of the hyperspectral images (HSI) classification. Most of existing studies either heavily rely on the expensive label information using the supervised learning or can hardly exploit the discriminative information borrowed from related domains. To address this issues, in this paper we show a novel framework addressing HSI classification based on the domain adaptation (DA) with active learning (AL). The main idea of our method is to retrain the multi-kernel classifier by utilizing the available labeled samples from source domain, and adding minimum number of the most informative samples with active queries in the target domain. The proposed method adaptively combines multiple kernels, forming a DA classifier that minimizes the bias between the source and target domains. Further equipped with the nested actively updating process, it sequentially expands the training set and gradually converges to a satisfying level of classification performance. We study this active adaptation framework with the Margin Sampling (MS) strategy in the HSI classification task. Our experimental results on two popular HSI datasets demonstrate its effectiveness.
Tasks	Active Learning, Domain Adaptation, Hyperspectral Image Classification, Image Classification
Published	2019-04-10
URL	http://arxiv.org/abs/1904.05200v1
PDF	http://arxiv.org/pdf/1904.05200v1.pdf
PWC	https://paperswithcode.com/paper/active-multi-kernel-domain-adaptation-for
Repo
Framework

Deep Model Predictive Control with Online Learning for Complex Physical Systems


Title	Deep Model Predictive Control with Online Learning for Complex Physical Systems
Authors	Katharina Bieker, Sebastian Peitz, Steven L. Brunton, J. Nathan Kutz, Michael Dellnitz
Abstract	The control of complex systems is of critical importance in many branches of science, engineering, and industry. Controlling an unsteady fluid flow is particularly important, as flow control is a key enabler for technologies in energy (e.g., wind, tidal, and combustion), transportation (e.g., planes, trains, and automobiles), security (e.g., tracking airborne contamination), and health (e.g., artificial hearts and artificial respiration). However, the high-dimensional, nonlinear, and multi-scale dynamics make real-time feedback control infeasible. Fortunately, these high-dimensional systems exhibit dominant, low-dimensional patterns of activity that can be exploited for effective control in the sense that knowledge of the entire state of a system is not required. Advances in machine learning have the potential to revolutionize flow control given its ability to extract principled, low-rank feature spaces characterizing such complex systems. We present a novel deep learning model predictive control (DeepMPC) framework that exploits low-rank features of the flow in order to achieve considerable improvements to control performance. Instead of predicting the entire fluid state, we use a recurrent neural network (RNN) to accurately predict the control relevant quantities of the system. The RNN is then embedded into a MPC framework to construct a feedback loop, and incoming sensor data is used to perform online updates to improve prediction accuracy. The results are validated using varying fluid flow examples of increasing complexity.
Tasks
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10094v1
PDF	https://arxiv.org/pdf/1905.10094v1.pdf
PWC	https://paperswithcode.com/paper/deep-model-predictive-control-with-online
Repo
Framework

SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks


Title	SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks
Authors	Alex Lamb, Sherjil Ozair, Vikas Verma, David Ha
Abstract	Deep networks have achieved excellent results in perceptual tasks, yet their ability to generalize to variations not seen during training has come under increasing scrutiny. In this work we focus on their ability to have invariance towards the presence or absence of details. For example, humans are able to watch cartoons, which are missing many visual details, without being explicitly trained to do so. As another example, 3D rendering software is a relatively recent development, yet people are able to understand such rendered scenes even though they are missing details (consider a film like Toy Story). The failure of machine learning algorithms to do this indicates a significant gap in generalization between human abilities and the abilities of deep networks. We propose a dataset that will make it easier to study the detail-invariance problem concretely. We produce a concrete task for this: SketchTransfer, and we show that state-of-the-art domain transfer algorithms still struggle with this task. The state-of-the-art technique which achieves over 95% on MNIST $\xrightarrow{}$ SVHN transfer only achieves 59% accuracy on the SketchTransfer task, which is much better than random (11% accuracy) but falls short of the 87% accuracy of a classifier trained directly on labeled sketches. This indicates that this task is approachable with today’s best methods but has substantial room for improvement.
Tasks
Published	2019-12-25
URL	https://arxiv.org/abs/1912.11570v1
PDF	https://arxiv.org/pdf/1912.11570v1.pdf
PWC	https://paperswithcode.com/paper/sketchtransfer-a-challenging-new-task-for
Repo
Framework

Asynchronous Online Federated Learning for Edge Devices


Title	Asynchronous Online Federated Learning for Edge Devices
Authors	Yujing Chen, Yue Ning, Huzefa Rangwala
Abstract	Federated learning (FL) is a machine learning paradigm where a shared central model is learned across multiple distributed client devices while the training data remains on edge devices or local clients. Most prior work on federated learning uses Federated Averaging (FedAvg) as an optimization method for training in a synchronized fashion. This involves independent training at multiple edge devices with synchronous aggregation steps. However, the assumptions made by FedAvg are not realistic given the heterogeneity of devices. In particular, the volume and distribution of collected data vary in the training process due to different sampling rates of edge devices. The edge devices themselves also vary in their available communication bandwidth and system configurations, such as memory, processor speed, and power requirements. This leads to vastly different training times as well as model/data transfer times. Furthermore, availability issues at edge devices can lead to a lack of contribution from specific edge devices to the federated model. In this paper, we present an Asynchronous Online Federated Learning (ASO- fed) framework, where the edge devices perform online learning with continuous streaming local data and a central server aggregates model parameters from local clients. Our framework updates the central model in an asynchronous manner to tackle the challenges associated with both varying computational loads at heterogeneous edge devices and edge devices that lag behind or dropout. Experiments on three real-world datasets show the effectiveness of ASO-fed on lowering the overall training cost and maintaining good prediction performance.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.02134v1
PDF	https://arxiv.org/pdf/1911.02134v1.pdf
PWC	https://paperswithcode.com/paper/asynchronous-online-federated-learning-for
Repo
Framework

A Temporal Module for Logical Frameworks


Title	A Temporal Module for Logical Frameworks
Authors	Valentina Pitoni, Stefania Costantini
Abstract	In artificial intelligence, multi agent systems constitute an interesting typology of society modeling, and have in this regard vast fields of application, which extend to the human sciences. Logic is often used to model such kind of systems as it is easier to verify than other approaches, and provides explainability and potential validation. In this paper we define a time module suitable to add time to many logic representations of agents.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08256v1
PDF	https://arxiv.org/pdf/1909.08256v1.pdf
PWC	https://paperswithcode.com/paper/a-temporal-module-for-logical-frameworks
Repo
Framework

Reinforcement Learning with Convex Constraints


Title	Reinforcement Learning with Convex Constraints
Authors	Sobhan Miryoosefi, Kianté Brantley, Hal Daumé III, Miroslav Dudik, Robert Schapire
Abstract	In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the use of unsafe actions, increase the diversity of trajectories to enable exploration, or approximate expert trajectories when rewards are sparse. In this paper, we propose an algorithmic scheme that can handle a wide class of constraints in RL tasks: specifically, any constraints that require expected values of some vector measurements (such as the use of an action) to lie in a convex set. This captures previously studied constraints (such as safety and proximity to an expert), but also enables new classes of constraints (such as diversity). Our approach comes with rigorous theoretical guarantees and only relies on the ability to approximately solve standard RL tasks. As a result, it can be easily adapted to work with any model-free or model-based RL. In our experiments, we show that it matches previous algorithms that enforce safety via constraints, but can also enforce new properties that these algorithms do not incorporate, such as diversity.
Tasks
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09323v2
PDF	https://arxiv.org/pdf/1906.09323v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-with-convex
Repo
Framework

Superpixel Contracted Graph-Based Learning for Hyperspectral Image Classification


Title	Superpixel Contracted Graph-Based Learning for Hyperspectral Image Classification
Authors	Philip Sellars, Angelica Aviles-Rivero, Carola-Bibiane Schönlieb
Abstract	A central problem in hyperspectral image classification is obtaining high classification accuracy when using a limited amount of labelled data. In this paper we present a novel graph-based framework, which aims to tackle this problem in the presence of large scale data input. Our approach utilises a novel superpixel method, specifically designed for hyperspectral data, to define meaningful local regions in an image, which with high probability share the same classification label. We then extract spectral and spatial features from these regions and use these to produce a contracted weighted graph-representation, where each node represents a region rather than a pixel. Our graph is then fed into a graph-based semi-supervised classifier which gives the final classification. We show that using superpixels in a graph representation is an effective tool for speeding up graphical classifiers applied to hyperspectral images. We demonstrate through exhaustive quantitative and qualitative results that our proposed method produces accurate classifications when an incredibly small amount of labelled data is used. We show that our approach mitigates the major drawbacks of existing approaches, resulting in our approach outperforming several comparative state-of-the-art techniques.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2019-03-14
URL	http://arxiv.org/abs/1903.06548v3
PDF	http://arxiv.org/pdf/1903.06548v3.pdf
PWC	https://paperswithcode.com/paper/superpixel-contracted-graph-based-learning
Repo
Framework


Title	A Comparative Study of Pretrained Language Models on Thai Social Text Categorization
Authors	Thanapapas Horsuwan, Kasidis Kanwatchara, Peerapon Vateekul, Boonserm Kijsirikul
Abstract	The ever-growing volume of data of user-generated content on social media provides a nearly unlimited corpus of unlabeled data even in languages where resources are scarce. In this paper, we demonstrate that state-of-the-art results on two Thai social text categorization tasks can be realized by pretraining a language model on a large noisy Thai social media corpus of over 1.26 billion tokens and later fine-tuned on the downstream classification tasks. Due to the linguistically noisy and domain-specific nature of the content, our unique data preprocessing steps designed for Thai social media were utilized to ease the training comprehension of the model. We compared four modern language models: ULMFiT, ELMo with biLSTM, OpenAI GPT, and BERT. We systematically compared the models across different dimensions including speed of pretraining and fine-tuning, perplexity, downstream classification benchmarks, and performance in limited pretraining data.
Tasks	Language Modelling, Text Categorization
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01580v2
PDF	https://arxiv.org/pdf/1912.01580v2.pdf
PWC	https://paperswithcode.com/paper/a-comparative-study-of-pretrained-language
Repo
Framework

Cascaded Recurrent Neural Networks for Hyperspectral Image Classification


Title	Cascaded Recurrent Neural Networks for Hyperspectral Image Classification
Authors	Renlong Hang, Qingshan Liu, Danfeng Hong, Pedram Ghamisi
Abstract	By considering the spectral signature as a sequence, recurrent neural networks (RNNs) have been successfully used to learn discriminative features from hyperspectral images (HSIs) recently. However, most of these models only input the whole spectral bands into RNNs directly, which may not fully explore the specific properties of HSIs. In this paper, we propose a cascaded RNN model using gated recurrent units (GRUs) to explore the redundant and complementary information of HSIs. It mainly consists of two RNN layers. The first RNN layer is used to eliminate redundant information between adjacent spectral bands, while the second RNN layer aims to learn the complementary information from non-adjacent spectral bands. To improve the discriminative ability of the learned features, we design two strategies for the proposed model. Besides, considering the rich spatial information contained in HSIs, we further extend the proposed model to its spectral-spatial counterpart by incorporating some convolutional layers. To test the effectiveness of our proposed models, we conduct experiments on two widely used HSIs. The experimental results show that our proposed models can achieve better results than the compared models.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2019-02-28
URL	http://arxiv.org/abs/1902.10858v1
PDF	http://arxiv.org/pdf/1902.10858v1.pdf
PWC	https://paperswithcode.com/paper/cascaded-recurrent-neural-networks-for
Repo
Framework

Ontology Based Information Integration: A Survey


Title	Ontology Based Information Integration: A Survey
Authors	Maryam Alizadeh, Maliheh Heydarpour Shahrezaei, Farajollah Tahernezhad-Javazm
Abstract	An ontology makes a special vocabulary which describes the domain of interest and the meaning of the term on that vocabulary. Based on the precision of the specification, the concept of the ontology contains several data and conceptual models. The notion of ontology has emerged into wide ranges of applications including database integration, peer-to-peer systems, e-commerce, semantic web, etc. It can be considered as a practical tool for conceptualizing things which are expressed in computer format. This paper is devoted to ontology matching as a mean or information integration. Several matching solutions have been presented from various areas such as databases, information systems and artificial intelligence. All of them take advantages of different attributes of ontology like, structures, data instances, semantics and labels and its other valuable properties. The solutions have some common techniques and cope with similar problems, but use different methods for combining and exploiting their results. Information integration is among the first classes of applications at which matching was considered as a probable solution. Information integration contains many fields including, data integration, schema integration, catalogue integration and semantic integration. We cover these notions in term of ontology in our proposed paper.
Tasks
Published	2019-09-26
URL	https://arxiv.org/abs/1909.13762v1
PDF	https://arxiv.org/pdf/1909.13762v1.pdf
PWC	https://paperswithcode.com/paper/ontology-based-information-integration-a
Repo
Framework

Quantifying the presence of graffiti in urban environments


Title	Quantifying the presence of graffiti in urban environments
Authors	Eric K. Tokuda, Claudio T. Silva, Roberto M. Cesar-Jr
Abstract	Graffiti is a common phenomenon in urban scenarios. Differently from urban art, graffiti tagging is a vandalism act and many local governments are putting great effort to combat it. The graffiti map of a region can be a very useful resource because it may allow one to potentially combat vandalism in locations with high level of graffiti and also to cleanup saturated regions to discourage future acts. There is currently no automatic way of obtaining a graffiti map of a region and it is obtained by manual inspection by the police or by popular participation. In this sense, we describe an ongoing work where we propose an automatic way of obtaining a graffiti map of a neighbourhood. It consists of the systematic collection of street view images followed by the identification of graffiti tags in the collected dataset and finally, in the calculation of the proposed graffiti level of that location. We validate the proposed method by evaluating the geographical distribution of graffiti in a city known to have high concentration of graffiti – Sao Paulo, Brazil.
Tasks
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04336v1
PDF	http://arxiv.org/pdf/1904.04336v1.pdf
PWC	https://paperswithcode.com/paper/quantifying-the-presence-of-graffiti-in-urban
Repo
Framework

Techniques for Automated Machine Learning


Title	Techniques for Automated Machine Learning
Authors	Yi-Wei Chen, Qingquan Song, Xia Hu
Abstract	Automated machine learning (AutoML) aims to find optimal machine learning solutions automatically given a machine learning problem. It could release the burden of data scientists from the multifarious manual tuning process and enable the access of domain experts to the off-the-shelf machine learning solutions without extensive experience. In this paper, we review the current developments of AutoML in terms of three categories, automated feature engineering (AutoFE), automated model and hyperparameter learning (AutoMHL), and automated deep learning (AutoDL). State-of-the-art techniques adopted in the three categories are presented, including Bayesian optimization, reinforcement learning, evolutionary algorithm, and gradient-based approaches. We summarize popular AutoML frameworks and conclude with current open challenges of AutoML.
Tasks	Automated Feature Engineering, AutoML, Feature Engineering
Published	2019-07-21
URL	https://arxiv.org/abs/1907.08908v1
PDF	https://arxiv.org/pdf/1907.08908v1.pdf
PWC	https://paperswithcode.com/paper/techniques-for-automated-machine-learning
Repo
Framework

Learning to Generate Questions with Adaptive Copying Neural Networks


Title	Learning to Generate Questions with Adaptive Copying Neural Networks
Authors	Xinyuan Lu, Yuhong Guo
Abstract	Automatic question generation is an important problem in natural language processing. In this paper we propose a novel adaptive copying recurrent neural network model to tackle the problem of question generation from sentences and paragraphs. The proposed model adds a copying mechanism component onto a bidirectional LSTM architecture to generate more suitable questions adaptively from the input data. Our experimental results show the proposed model can outperform the state-of-the-art question generation methods in terms of BLEU and ROUGE evaluation scores.
Tasks	Question Generation
Published	2019-09-17
URL	https://arxiv.org/abs/1909.08187v1
PDF	https://arxiv.org/pdf/1909.08187v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-generate-questions-with-adaptive
Repo
Framework

Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction


Title	Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction
Authors	Sammy Christen, Stefan Stevsic, Otmar Hilliges
Abstract	In this paper, we propose a method for training control policies for human-robot interactions such as handshakes or hand claps via Deep Reinforcement Learning. The policy controls a humanoid Shadow Dexterous Hand, attached to a robot arm. We propose a parameterizable multi-objective reward function that allows learning of a variety of interactions without changing the reward structure. The parameters of the reward function are estimated directly from motion capture data of human-human interactions in order to produce policies that are perceived as being natural and human-like by observers. We evaluate our method on three significantly different hand interactions: handshake, hand clap and finger touch. We provide detailed analysis of the proposed reward function and the resulting policies and conduct a large-scale user study, indicating that our policy produces natural looking motions.
Tasks	Motion Capture
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11695v2
PDF	https://arxiv.org/pdf/1906.11695v2.pdf
PWC	https://paperswithcode.com/paper/demonstration-guided-deep-reinforcement
Repo
Framework

Gaussian Conditional Random Fields for Classification


Title	Gaussian Conditional Random Fields for Classification
Authors	Andrija Petrović, Mladen Nikolić, Miloš Jovanović, Boris Delibašić
Abstract	Gaussian conditional random fields (GCRF) are a well-known used structured model for continuous outputs that uses multiple unstructured predictors to form its features and at the same time exploits dependence structure among outputs, which is provided by a similarity measure. In this paper, a Gaussian conditional random fields model for structured binary classification (GCRFBC) is proposed. The model is applicable to classification problems with undirected graphs, intractable for standard classification CRFs. The model representation of GCRFBC is extended by latent variables which yield some appealing properties. Thanks to the GCRF latent structure, the model becomes tractable, efficient and open to improvements previously applied to GCRF regression models. In addition, the model allows for reduction of noise, that might appear if structures were defined directly between discrete outputs. Additionally, two different forms of the algorithm are presented: GCRFBCb (GCRGBC - Bayesian) and GCRFBCnb (GCRFBC - non Bayesian). The extended method of local variational approximation of sigmoid function is used for solving empirical Bayes in Bayesian GCRFBCb variant, whereas MAP value of latent variables is the basis for learning and inference in the GCRFBCnb variant. The inference in GCRFBCb is solved by Newton-Cotes formulas for one-dimensional integration. Both models are evaluated on synthetic data and real-world data. It was shown that both models achieve better prediction performance than unstructured predictors. Furthermore, computational and memory complexity is evaluated. Advantages and disadvantages of the proposed GCRFBCb and GCRFBCnb are discussed in detail.
Tasks
Published	2019-01-31
URL	http://arxiv.org/abs/1902.00045v1
PDF	http://arxiv.org/pdf/1902.00045v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-conditional-random-fields-for
Repo
Framework