October 17, 2019

3093 words 15 mins read

Paper Group ANR 964

Toward Performance Optimization in IoT-based Next-Gen Wireless Sensor Networks. COBRA: A Fast and Simple Method for Active Clustering with Pairwise Constraints. Unsupervised Data Selection for Supervised Learning. A Rapidly Deployable Classification System using Visual Data for the Application of Precision Weed Management. Semi-supervised Learning …

Toward Performance Optimization in IoT-based Next-Gen Wireless Sensor Networks


Title	Toward Performance Optimization in IoT-based Next-Gen Wireless Sensor Networks
Authors	Muzammil Behzad, Manal Abdullah, Muhammad Talal Hassan, Yao Ge, Mahmood Ashraf Khan
Abstract	In this paper, we propose a novel framework for performance optimization in Internet of Things (IoT)-based next-generation wireless sensor networks. In particular, a computationally-convenient system is presented to combat two major research problems in sensor networks. First is the conventionally-tackled resource optimization problem which triggers the drainage of battery at a faster rate within a network. Such drainage promotes inefficient resource usage thereby causing sudden death of the network. The second main bottleneck for such networks is that of data degradation. This is because the nodes in such networks communicate via a wireless channel, where the inevitable presence of noise corrupts the data making it unsuitable for practical applications. Therefore, we present a layer-adaptive method via 3-tier communication mechanism to ensure the efficient use of resources. This is supported with a mathematical coverage model that deals with the formation of coverage holes. We also present a transform-domain based robust algorithm to effectively remove the unwanted components from the data. Our proposed framework offers a handy algorithm that enjoys desirable complexity for real-time applications as shown by the extensive simulation results.
Tasks
Published	2018-06-23
URL	http://arxiv.org/abs/1806.09980v1
PDF	http://arxiv.org/pdf/1806.09980v1.pdf
PWC	https://paperswithcode.com/paper/toward-performance-optimization-in-iot-based
Repo
Framework

COBRA: A Fast and Simple Method for Active Clustering with Pairwise Constraints


Title	COBRA: A Fast and Simple Method for Active Clustering with Pairwise Constraints
Authors	Toon Van Craenendonck, Sebastijan Dumancic, Hendrik Blockeel
Abstract	Clustering is inherently ill-posed: there often exist multiple valid clusterings of a single dataset, and without any additional information a clustering system has no way of knowing which clustering it should produce. This motivates the use of constraints in clustering, as they allow users to communicate their interests to the clustering system. Active constraint-based clustering algorithms select the most useful constraints to query, aiming to produce a good clustering using as few constraints as possible. We propose COBRA, an active method that first over-clusters the data by running K-means with a $K$ that is intended to be too large, and subsequently merges the resulting small clusters into larger ones based on pairwise constraints. In its merging step, COBRA is able to keep the number of pairwise queries low by maximally exploiting constraint transitivity and entailment. We experimentally show that COBRA outperforms the state of the art in terms of clustering quality and runtime, without requiring the number of clusters in advance.
Tasks
Published	2018-01-30
URL	http://arxiv.org/abs/1801.09955v1
PDF	http://arxiv.org/pdf/1801.09955v1.pdf
PWC	https://paperswithcode.com/paper/cobra-a-fast-and-simple-method-for-active
Repo
Framework

Unsupervised Data Selection for Supervised Learning


Title	Unsupervised Data Selection for Supervised Learning
Authors	Gabriele Valvano, Andrea Leo, Daniele Della Latta, Nicola Martini, Gianmarco Santini, Dante Chiappino, Emiliano Ricciardi
Abstract	Recent research put a big effort in the development of deep learning architectures and optimizers obtaining impressive results in areas ranging from vision to language processing. However little attention has been addressed to the need of a methodological process of data collection. In this work we hypothesize that high quality data for supervised learning can be selected in an unsupervised manner and that by doing so one can obtain models capable to generalize better than in the case of random training set construction. However, preliminary results are not robust and further studies on the subject should be carried out.
Tasks
Published	2018-10-29
URL	http://arxiv.org/abs/1810.12142v2
PDF	http://arxiv.org/pdf/1810.12142v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-data-selection-for-supervised
Repo
Framework

A Rapidly Deployable Classification System using Visual Data for the Application of Precision Weed Management


Title	A Rapidly Deployable Classification System using Visual Data for the Application of Precision Weed Management
Authors	David Hall, Feras Dayoub, Tristan Perez, Chris McCool
Abstract	In this work we demonstrate a rapidly deployable weed classification system that uses visual data to enable autonomous precision weeding without making prior assumptions about which weed species are present in a given field. Previous work in this area relies on having prior knowledge of the weed species present in the field. This assumption cannot always hold true for every field, and thus limits the use of weed classification systems based on this assumption. In this work, we obviate this assumption and introduce a rapidly deployable approach able to operate on any field without any weed species assumptions prior to deployment. We present a three stage pipeline for the implementation of our weed classification system consisting of initial field surveillance, offline processing and selective labelling, and automated precision weeding. The key characteristic of our approach is the combination of plant clustering and selective labelling which is what enables our system to operate without prior weed species knowledge. Testing using field data we are able to label 12.3 times fewer images than traditional full labelling whilst reducing classification accuracy by only 14%.
Tasks
Published	2018-01-25
URL	http://arxiv.org/abs/1801.08613v2
PDF	http://arxiv.org/pdf/1801.08613v2.pdf
PWC	https://paperswithcode.com/paper/a-rapidly-deployable-classification-system
Repo
Framework

Semi-supervised Learning on Graphs with Generative Adversarial Nets


Title	Semi-supervised Learning on Graphs with Generative Adversarial Nets
Authors	Ming Ding, Jie Tang, Jie Zhang
Abstract	We investigate how generative adversarial nets (GANs) can help semi-supervised learning on graphs. We first provide insights on working principles of adversarial learning over graphs and then present GraphSGAN, a novel approach to semi-supervised learning on graphs. In GraphSGAN, generator and classifier networks play a novel competitive game. At equilibrium, generator generates fake samples in low-density areas between subgraphs. In order to discriminate fake samples from the real, classifier implicitly takes the density property of subgraph into consideration. An efficient adversarial learning algorithm has been developed to improve traditional normalized graph Laplacian regularization with a theoretical guarantee. Experimental results on several different genres of datasets show that the proposed GraphSGAN significantly outperforms several state-of-the-art methods. GraphSGAN can be also trained using mini-batch, thus enjoys the scalability advantage.
Tasks
Published	2018-09-01
URL	http://arxiv.org/abs/1809.00130v1
PDF	http://arxiv.org/pdf/1809.00130v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-on-graphs-with
Repo
Framework

Active Learning in Recommendation Systems with Multi-level User Preferences


Title	Active Learning in Recommendation Systems with Multi-level User Preferences
Authors	Yuheng Bu, Kevin Small
Abstract	While recommendation systems generally observe user behavior passively, there has been an increased interest in directly querying users to learn their specific preferences. In such settings, considering queries at different levels of granularity to optimize user information acquisition is crucial to efficiently providing a good user experience. In this work, we study the active learning problem with multi-level user preferences within the collective matrix factorization (CMF) framework. CMF jointly captures multi-level user preferences with respect to items and relations between items (e.g., book genre, cuisine type), generally resulting in improved predictions. Motivated by finite-sample analysis of the CMF model, we propose a theoretically optimal active learning strategy based on the Fisher information matrix and use this to derive a realizable approximation algorithm for practical recommendations. Experiments are conducted using both the Yelp dataset directly and an illustrative synthetic dataset in the three settings of personalized active learning, cold-start recommendations, and noisy data – demonstrating strong improvements over several widely used active learning methods.
Tasks	Active Learning, Recommendation Systems
Published	2018-11-30
URL	http://arxiv.org/abs/1811.12591v1
PDF	http://arxiv.org/pdf/1811.12591v1.pdf
PWC	https://paperswithcode.com/paper/active-learning-in-recommendation-systems
Repo
Framework

Search Based Code Generation for Machine Learning Programs


Title	Search Based Code Generation for Machine Learning Programs
Authors	Muhammad Zubair Malik, Muhammad Nawaz, Nimrah Mustafa, Junaid Haroon Siddiqui
Abstract	Machine Learning (ML) has revamped every domain of life as it provides powerful tools to build complex systems that learn and improve from experience and data. Our key insight is that to solve a machine learning problem, data scientists do not invent a new algorithm each time, but evaluate a range of existing models with different configurations and select the best one. This task is laborious, error-prone, and drains a large chunk of project budget and time. In this paper we present a novel framework inspired by programming by Sketching and Partial Evaluation to minimize human intervention in developing ML solutions. We templatize machine learning algorithms to expose configuration choices as holes to be searched. We share code and computation between different algorithms, and only partially evaluate configuration space of algorithms based on information gained from initial algorithm evaluations. We also employ hierarchical and heuristic based pruning to reduce the search space. Our initial findings indicate that our approach can generate highly accurate ML models. Interviews with data scientists show that they feel our framework can eliminate sources of common errors and significantly reduce development time.
Tasks	Code Generation
Published	2018-01-29
URL	http://arxiv.org/abs/1801.09373v2
PDF	http://arxiv.org/pdf/1801.09373v2.pdf
PWC	https://paperswithcode.com/paper/search-based-code-generation-for-machine
Repo
Framework

A Multi-Task Learning Approach for Meal Assessment


Title	A Multi-Task Learning Approach for Meal Assessment
Authors	Ya Lu, Dario Allegra, Marios Anthimopoulos, Filippo Stanco, Giovanni Maria Farinella, Stavroula Mougiakakou
Abstract	Key role in the prevention of diet-related chronic diseases plays the balanced nutrition together with a proper diet. The conventional dietary assessment methods are time-consuming, expensive and prone to errors. New technology-based methods that provide reliable and convenient dietary assessment, have emerged during the last decade. The advances in the field of computer vision permitted the use of meal image to assess the nutrient content usually through three steps: food segmentation, recognition and volume estimation. In this paper, we propose a use one RGB meal image as input to a multi-task learning based Convolutional Neural Network (CNN). The proposed approach achieved outstanding performance, while a comparison with state-of-the-art methods indicated that the proposed approach exhibits clear advantage in accuracy, along with a massive reduction of processing time.
Tasks	Multi-Task Learning
Published	2018-06-27
URL	http://arxiv.org/abs/1806.10343v1
PDF	http://arxiv.org/pdf/1806.10343v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-task-learning-approach-for-meal
Repo
Framework


Title	Preparation of Improved Turkish DataSet for Sentiment Analysis in Social Media
Authors	Semiha Makinist, Ibrahim Riza Hallac, Betul Ay Karakus, Galip Aydin
Abstract	A public dataset, with a variety of properties suitable for sentiment analysis [1], event prediction, trend detection and other text mining applications, is needed in order to be able to successfully perform analysis studies. The vast majority of data on social media is text-based and it is not possible to directly apply machine learning processes into these raw data, since several different processes are required to prepare the data before the implementation of the algorithms. For example, different misspellings of same word enlarge the word vector space unnecessarily, thereby it leads to reduce the success of the algorithm and increase the computational power requirement. This paper presents an improved Turkish dataset with an effective spelling correction algorithm based on Hadoop [2]. The collected data is recorded on the Hadoop Distributed File System and the text based data is processed by MapReduce programming model. This method is suitable for the storage and processing of large sized text based social media data. In this study, movie reviews have been automatically recorded with Apache ManifoldCF (MCF) [3] and data clusters have been created. Various methods compared such as Levenshtein and Fuzzy String Matching have been proposed to create a public dataset from collected data. Experimental results show that the proposed algorithm, which can be used as an open source dataset in sentiment analysis studies, have been performed successfully to the detection and correction of spelling errors.
Tasks	Sentiment Analysis, Spelling Correction
Published	2018-01-30
URL	http://arxiv.org/abs/1801.09975v2
PDF	http://arxiv.org/pdf/1801.09975v2.pdf
PWC	https://paperswithcode.com/paper/preparation-of-improved-turkish-dataset-for
Repo
Framework

Generative Adversarial Network for Medical Images (MI-GAN)


Title	Generative Adversarial Network for Medical Images (MI-GAN)
Authors	Talha Iqbal, Hazrat Ali
Abstract	Deep learning algorithms produces state-of-the-art results for different machine learning and computer vision tasks. To perform well on a given task, these algorithms require large dataset for training. However, deep learning algorithms lack generalization and suffer from over-fitting whenever trained on small dataset, especially when one is dealing with medical images. For supervised image analysis in medical imaging, having image data along with their corresponding annotated ground-truths is costly as well as time consuming since annotations of the data is done by medical experts manually. In this paper, we propose a new Generative Adversarial Network for Medical Imaging (MI-GAN). The MI-GAN generates synthetic medical images and their segmented masks, which can then be used for the application of supervised analysis of medical images. Particularly, we present MI-GAN for synthesis of retinal images. The proposed method generates precise segmented images better than the existing techniques. The proposed model achieves a dice coefficient of 0.837 on STARE dataset and 0.832 on DRIVE dataset which is state-of-the-art performance on both the datasets.
Tasks
Published	2018-10-01
URL	http://arxiv.org/abs/1810.00551v1
PDF	http://arxiv.org/pdf/1810.00551v1.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-network-for-medical
Repo
Framework

Clustering by latent dimensions


Title	Clustering by latent dimensions
Authors	Shohei Hidaka, Neeraj Kashyap
Abstract	This paper introduces a new clustering technique, called {\em dimensional clustering}, which clusters each data point by its latent {\em pointwise dimension}, which is a measure of the dimensionality of the data set local to that point. Pointwise dimension is invariant under a broad class of transformations. As a result, dimensional clustering can be usefully applied to a wide range of datasets. Concretely, we present a statistical model which estimates the pointwise dimension of a dataset around the points in that dataset using the distance of each point from its $n^{\text{th}}$ nearest neighbor. We demonstrate the applicability of our technique to the analysis of dynamical systems, images, and complex human movements.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.10759v1
PDF	http://arxiv.org/pdf/1805.10759v1.pdf
PWC	https://paperswithcode.com/paper/clustering-by-latent-dimensions
Repo
Framework

Same but Different: Distant Supervision for Predicting and Understanding Entity Linking Difficulty


Title	Same but Different: Distant Supervision for Predicting and Understanding Entity Linking Difficulty
Authors	Renato Stoffalette João, Pavlos Fafalios, Stefan Dietze
Abstract	Entity Linking (EL) is the task of automatically identifying entity mentions in a piece of text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. There is a large number of EL tools available for different types of documents and domains, yet EL remains a challenging task where the lack of precision on particularly ambiguous mentions often spoils the usefulness of automated disambiguation results in real applications. A priori approximations of the difficulty to link a particular entity mention can facilitate flagging of critical cases as part of semi-automated EL systems, while detecting latent factors that affect the EL performance, like corpus-specific features, can provide insights on how to improve a system based on the special characteristics of the underlying corpus. In this paper, we first introduce a consensus-based method to generate difficulty labels for entity mentions on arbitrary corpora. The difficulty labels are then exploited as training data for a supervised classification task able to predict the EL difficulty of entity mentions using a variety of features. Experiments over a corpus of news articles show that EL difficulty can be estimated with high accuracy, revealing also latent features that affect EL performance. Finally, evaluation results demonstrate the effectiveness of the proposed method to inform semi-automated EL pipelines.
Tasks	Entity Linking
Published	2018-12-13
URL	http://arxiv.org/abs/1812.10387v1
PDF	http://arxiv.org/pdf/1812.10387v1.pdf
PWC	https://paperswithcode.com/paper/same-but-different-distant-supervision-for
Repo
Framework

Creativity and Artificial Intelligence: A Digital Art Perspective


Title	Creativity and Artificial Intelligence: A Digital Art Perspective
Authors	Bo Xing, Tshilidzi Marwala
Abstract	This paper describes the application of artificial intelligence to the creation of digital art. AI is a computational paradigm that codifies intelligence into machines. There are generally three types of artificial intelligence and these are machine learning, evolutionary programming and soft computing. Machine learning is the statistical approach to building intelligent systems. Evolutionary programming is the use of natural evolutionary systems to design intelligent machines. Some of the evolutionary programming systems include genetic algorithm which is inspired by the principles of evolution and swarm optimization which is inspired by the swarming of birds, fish, ants etc. Soft computing includes techniques such as agent based modelling and fuzzy logic. Opportunities on the applications of these to digital art are explored.
Tasks
Published	2018-07-21
URL	http://arxiv.org/abs/1807.08195v1
PDF	http://arxiv.org/pdf/1807.08195v1.pdf
PWC	https://paperswithcode.com/paper/creativity-and-artificial-intelligence-a
Repo
Framework

Why Comparing Single Performance Scores Does Not Allow to Draw Conclusions About Machine Learning Approaches


Title	Why Comparing Single Performance Scores Does Not Allow to Draw Conclusions About Machine Learning Approaches
Authors	Nils Reimers, Iryna Gurevych
Abstract	Developing state-of-the-art approaches for specific tasks is a major driving force in our research community. Depending on the prestige of the task, publishing it can come along with a lot of visibility. The question arises how reliable are our evaluation methodologies to compare approaches? One common methodology to identify the state-of-the-art is to partition data into a train, a development and a test set. Researchers can train and tune their approach on some part of the dataset and then select the model that worked best on the development set for a final evaluation on unseen test data. Test scores from different approaches are compared, and performance differences are tested for statistical significance. In this publication, we show that there is a high risk that a statistical significance in this type of evaluation is not due to a superior learning approach. Instead, there is a high risk that the difference is due to chance. For example for the CoNLL 2003 NER dataset we observed in up to 26% of the cases type I errors (false positives) with a threshold of p < 0.05, i.e., falsely concluding a statistically significant difference between two identical approaches. We prove that this evaluation setup is unsuitable to compare learning approaches. We formalize alternative evaluation setups based on score distributions.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09578v1
PDF	http://arxiv.org/pdf/1803.09578v1.pdf
PWC	https://paperswithcode.com/paper/why-comparing-single-performance-scores-does
Repo
Framework

Image Captioning as Neural Machine Translation Task in SOCKEYE


Title	Image Captioning as Neural Machine Translation Task in SOCKEYE
Authors	Loris Bazzani, Tobias Domhan, Felix Hieber
Abstract	Image captioning is an interdisciplinary research problem that stands between computer vision and natural language processing. The task is to generate a textual description of the content of an image. The typical model used for image captioning is an encoder-decoder deep network, where the encoder captures the essence of an image while the decoder is responsible for generating a sentence describing the image. Attention mechanisms can be used to automatically focus the decoder on parts of the image which are relevant to predict the next word. In this paper, we explore different decoders and attentional models popular in neural machine translation, namely attentional recurrent neural networks, self-attentional transformers, and fully-convolutional networks, which represent the current state of the art of neural machine translation. The image captioning module is available as part of SOCKEYE at https://github.com/awslabs/sockeye which tutorial can be found at https://awslabs.github.io/sockeye/image_captioning.html .
Tasks	Image Captioning, Machine Translation
Published	2018-10-09
URL	http://arxiv.org/abs/1810.04101v3
PDF	http://arxiv.org/pdf/1810.04101v3.pdf
PWC	https://paperswithcode.com/paper/image-captioning-as-neural-machine
Repo
Framework