January 29, 2020

3158 words 15 mins read

Paper Group ANR 550

Is it a Fruit, an Apple or a Granny Smith? Predicting the Basic Level in a Concept Hierarchy. Multi-Objective Pruning for CNNs Using Genetic Algorithm. Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition. Exploration via Sample-Efficient Subgoal Design. Multi-Channel Graph Convolutional Networks. Coloring gra …

Is it a Fruit, an Apple or a Granny Smith? Predicting the Basic Level in a Concept Hierarchy


Title	Is it a Fruit, an Apple or a Granny Smith? Predicting the Basic Level in a Concept Hierarchy
Authors	Laura Hollink, Aysenur Bilgin, Jacco van Ossenbruggen
Abstract	The “basic level”, according to experiments in cognitive psychology, is the level of abstraction in a hierarchy of concepts at which humans perform tasks quicker and with greater accuracy than at other levels. We argue that applications that use concept hierarchies - such as knowledge graphs, ontologies or taxonomies - could significantly improve their user interfaces if they `knew’ which concepts are the basic level concepts. This paper examines to what extent the basic level can be learned from data. We test the utility of three types of concept features, that were inspired by the basic level theory: lexical features, structural features and frequency features. We evaluate our approach on WordNet, and create a training set of manually labelled examples that includes concepts from different domains. Our findings include that the basic level concepts can be accurately identified within one domain. Concepts that are difficult to label for humans are also harder to classify automatically. Our experiments provide insight into how classification performance across domains could be improved, which is necessary for identification of basic level concepts on a larger scale. \|
Tasks	Knowledge Graphs
Published	2019-10-25
URL	https://arxiv.org/abs/1910.12619v1
PDF	https://arxiv.org/pdf/1910.12619v1.pdf
PWC	https://paperswithcode.com/paper/is-it-a-fruit-an-apple-or-a-granny-smith
Repo
Framework

Multi-Objective Pruning for CNNs Using Genetic Algorithm


Title	Multi-Objective Pruning for CNNs Using Genetic Algorithm
Authors	Chuanguang Yang, Zhulin An, Chao Li, Boyu Diao, Yongjun Xu
Abstract	In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity. In our experiments, we apply our approach to prune pre-trained LeNet across the MNIST dataset, which reduces 95.42% parameter size and achieves 16$\times$ speedups of convolutional layer computation with tiny accuracy loss by laying emphasis on sparsity and computation, respectively. Our empirical study suggests that GA is an alternative pruning approach for obtaining a competitive compression performance. Additionally, compared with state-of-the-art approaches, GA is capable of automatically pruning CNNs based on the multi-objective importance by a pre-defined fitness function.
Tasks
Published	2019-06-02
URL	https://arxiv.org/abs/1906.00399v2
PDF	https://arxiv.org/pdf/1906.00399v2.pdf
PWC	https://paperswithcode.com/paper/190600399
Repo
Framework

Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition


Title	Data augmentation with Symbolic-to-Real Image Translation GANs for Traffic Sign Recognition
Authors	Nour Soufi, Matias Valdenegro-Toro
Abstract	Traffic sign recognition is an important component of many advanced driving assistance systems, and it is required for full autonomous driving. Computational performance is usually the bottleneck in using large scale neural networks for this purpose. SqueezeNet is a good candidate for efficient image classification of traffic signs, but in our experiments it does not reach high accuracy, and we believe this is due to lack of data, requiring data augmentation. Generative adversarial networks can learn the high dimensional distribution of empirical data, allowing the generation of new data points. In this paper we apply pix2pix GANs architecture to generate new traffic sign images and evaluate the use of these images in data augmentation. We were motivated to use pix2pix to translate symbolic sign images to real ones due to the mode collapse in Conditional GANs. Through our experiments we found that data augmentation using GAN can increase classification accuracy for circular traffic signs from 92.1% to 94.0%, and for triangular traffic signs from 93.8% to 95.3%, producing an overall improvement of 2%. However some traditional augmentation techniques can outperform GAN data augmentation, for example contrast variation in circular traffic signs (95.5%) and displacement on triangular traffic signs (96.7 %). Our negative results shows that while GANs can be naively used for data augmentation, they are not always the best choice, depending on the problem and variability in the data.
Tasks	Autonomous Driving, Data Augmentation, Image Classification, Traffic Sign Recognition
Published	2019-07-17
URL	https://arxiv.org/abs/1907.12902v1
PDF	https://arxiv.org/pdf/1907.12902v1.pdf
PWC	https://paperswithcode.com/paper/data-augmentation-with-symbolic-to-real-image
Repo
Framework

Exploration via Sample-Efficient Subgoal Design


Title	Exploration via Sample-Efficient Subgoal Design
Authors	Yijia Wang, Matthias Poloczek, Daniel R. Jiang
Abstract	The problem of exploration in unknown environments continues to pose a challenge for reinforcement learning algorithms, as interactions with the environment are usually expensive or limited. The technique of setting subgoals with an intrinsic shaped reward allows for the use of supplemental feedback to aid an agent in environment with sparse and delayed rewards. In fact, it can be an effective tool in directing the exploration behavior of the agent toward useful parts of the state space. In this paper, we consider problems where an agent faces an unknown task in the future and is given prior opportunities to “practice” on related tasks where the interactions are still expensive. We propose a one-step Bayes-optimal algorithm for selecting subgoal designs, along with the number of episodes and the episode length, to efficiently maximize the expected performance of an agent. We demonstrate its excellent performance on a variety of tasks and also prove an asymptotic optimality guarantee.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09143v1
PDF	https://arxiv.org/pdf/1910.09143v1.pdf
PWC	https://paperswithcode.com/paper/exploration-via-sample-efficient-subgoal
Repo
Framework

Multi-Channel Graph Convolutional Networks


Title	Multi-Channel Graph Convolutional Networks
Authors	Kaixiong Zhou, Qingquan Song, Xiao Huang, Daochen Zha, Na Zou, Xia Hu
Abstract	Graph neural networks (GNN) has been demonstrated to be effective in classifying graph structures. To further improve the graph representation learning ability, hierarchical GNN has been explored. It leverages the differentiable pooling to cluster nodes into fixed groups, and generates a coarse-grained structure accompanied with the shrinking of the original graph. However, such clustering would discard some graph information and achieve the suboptimal results. It is because the node inherently has different characteristics or roles, and two non-isomorphic graphs may have the same coarse-grained structure that cannot be distinguished after pooling. To compensate the loss caused by coarse-grained clustering and further advance GNN, we propose a multi-channel graph convolutional networks (MuchGCN). It is motivated by the convolutional neural networks, at which a series of channels are encoded to preserve the comprehensive characteristics of the input image. Thus, we define the specific graph convolutions to learn a series of graph channels at each layer, and pool graphs iteratively to encode the hierarchical structures. Experiments have been carefully carried out to demonstrate the superiority of MuchGCN over the state-of-the-art graph classification algorithms.
Tasks	Graph Classification, Graph Representation Learning, Representation Learning
Published	2019-12-17
URL	https://arxiv.org/abs/1912.08306v1
PDF	https://arxiv.org/pdf/1912.08306v1.pdf
PWC	https://paperswithcode.com/paper/multi-channel-graph-convolutional-networks
Repo
Framework

Coloring graph neural networks for node disambiguation


Title	Coloring graph neural networks for node disambiguation
Authors	George Dasoulas, Ludovic Dos Santos, Kevin Scaman, Aladin Virmaux
Abstract	In this paper, we show that a simple coloring scheme can improve, both theoretically and empirically, the expressive power of Message Passing Neural Networks(MPNNs). More specifically, we introduce a graph neural network called Colored Local Iterative Procedure (CLIP) that uses colors to disambiguate identical node attributes, and show that this representation is a universal approximator of continuous functions on graphs with node attributes. Our method relies on separability , a key topological characteristic that allows to extend well-chosen neural networks into universal representations. Finally, we show experimentally that CLIP is capable of capturing structural characteristics that traditional MPNNs fail to distinguish,while being state-of-the-art on benchmark graph classification datasets.
Tasks	Graph Classification
Published	2019-12-12
URL	https://arxiv.org/abs/1912.06058v1
PDF	https://arxiv.org/pdf/1912.06058v1.pdf
PWC	https://paperswithcode.com/paper/coloring-graph-neural-networks-for-node-1
Repo
Framework

Characterizing and Detecting Money Laundering Activities on the Bitcoin Network


Title	Characterizing and Detecting Money Laundering Activities on the Bitcoin Network
Authors	Yining Hu, Suranga Seneviratne, Kanchana Thilakarathna, Kensuke Fukuda, Aruna Seneviratne
Abstract	Bitcoin is by far the most popular crypto-currency solution enabling peer-to-peer payments. Despite some studies highlighting the network does not provide full anonymity, it is still being heavily used for a wide variety of dubious financial activities such as money laundering, ponzi schemes, and ransom-ware payments. In this paper, we explore the landscape of potential money laundering activities occurring across the Bitcoin network. Using data collected over three years, we create transaction graphs and provide an in-depth analysis on various graph characteristics to differentiate money laundering transactions from regular transactions. We found that the main difference between laundering and regular transactions lies in their output values and neighbourhood information. Then, we propose and evaluate a set of classifiers based on four types of graph features: immediate neighbours, curated features, deepwalk embeddings, and node2vec embeddings to classify money laundering and regular transactions. Results show that the node2vec-based classifier outperforms other classifiers in binary classification reaching an average accuracy of 92.29% and an F1-measure of 0.93 and high robustness over a 2.5-year time span. Finally, we demonstrate how effective our classifiers are in discovering unknown laundering services. The classifier performance dropped compared to binary classification, however, the prediction can be improved with simple ensemble techniques for some services.
Tasks
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12060v1
PDF	https://arxiv.org/pdf/1912.12060v1.pdf
PWC	https://paperswithcode.com/paper/characterizing-and-detecting-money-laundering
Repo
Framework

Affect in Tweets Using Experts Model


Title	Affect in Tweets Using Experts Model
Authors	Subba Reddy Oota, Adithya Avvaru, Mounika Marreddy, Radhika Mamidi
Abstract	Estimating the intensity of emotion has gained significance as modern textual inputs in potential applications like social media, e-retail markets, psychology, advertisements etc., carry a lot of emotions, feelings, expressions along with its meaning. However, the approaches of traditional sentiment analysis primarily focuses on classifying the sentiment in general (positive or negative) or at an aspect level(very positive, low negative, etc.) and cannot exploit the intensity information. Moreover, automatically identifying emotions like anger, fear, joy, sadness, disgust etc., from text introduces challenging scenarios where single tweet may contain multiple emotions with different intensities and some emotions may even co-occur in some of the tweets. In this paper, we propose an architecture, Experts Model, inspired from the standard Mixture of Experts (MoE) model. The key idea here is each expert learns different sets of features from the feature vector which helps in better emotion detection from the tweet. We compared the results of our Experts Model with both baseline results and top five performers of SemEval-2018 Task-1, Affect in Tweets (AIT). The experimental results show that our proposed approach deals with the emotion detection problem and stands at top-5 results.
Tasks	Sentiment Analysis
Published	2019-03-20
URL	http://arxiv.org/abs/1904.00762v1
PDF	http://arxiv.org/pdf/1904.00762v1.pdf
PWC	https://paperswithcode.com/paper/affect-in-tweets-using-experts-model
Repo
Framework

A Comparative Analysis of Forecasting Financial Time Series Using ARIMA, LSTM, and BiLSTM


Title	A Comparative Analysis of Forecasting Financial Time Series Using ARIMA, LSTM, and BiLSTM
Authors	Sima Siami-Namini, Neda Tavakoli, Akbar Siami Namin
Abstract	Machine and deep learning-based algorithms are the emerging approaches in addressing prediction problems in time series. These techniques have been shown to produce more accurate results than conventional regression-based modeling. It has been reported that artificial Recurrent Neural Networks (RNN) with memory, such as Long Short-Term Memory (LSTM), are superior compared to Autoregressive Integrated Moving Average (ARIMA) with a large margin. The LSTM-based models incorporate additional “gates” for the purpose of memorizing longer sequences of input data. The major question is that whether the gates incorporated in the LSTM architecture already offers a good prediction and whether additional training of data would be necessary to further improve the prediction. Bidirectional LSTMs (BiLSTMs) enable additional training by traversing the input data twice (i.e., 1) left-to-right, and 2) right-to-left). The research question of interest is then whether BiLSTM, with additional training capability, outperforms regular unidirectional LSTM. This paper reports a behavioral analysis and comparison of BiLSTM and LSTM models. The objective is to explore to what extend additional layers of training of data would be beneficial to tune the involved parameters. The results show that additional training of data and thus BiLSTM-based modeling offers better predictions than regular LSTM-based models. More specifically, it was observed that BiLSTM models provide better predictions compared to ARIMA and LSTM models. It was also observed that BiLSTM models reach the equilibrium much slower than LSTM-based models.
Tasks	Time Series
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09512v1
PDF	https://arxiv.org/pdf/1911.09512v1.pdf
PWC	https://paperswithcode.com/paper/a-comparative-analysis-of-forecasting
Repo
Framework

Making Predictive Coding Networks Generative


Title	Making Predictive Coding Networks Generative
Authors	Jeff Orchard, Wei Sun
Abstract	Predictive coding (PC) networks are a biologically interesting class of neural networks. Their layered hierarchy mimics the reciprocal connectivity pattern observed in the mammalian cortex, and they can be trained using local learning rules that approximate backpropagation [Bogacz, 2017]. However, despite having feedback connections that enable information to flow down the network hierarchy, discriminative PC networks are not generative. Clamping the output class and running the network to equilibrium yields an input sample that typically does not resemble the training input. This paper studies this phenomenon, and proposes a simple solution that promotes the generation of input samples that resemble the training inputs. Simple decay, a technique already in wide use in neural networks, pushes the PC network toward a unique minimum 2-norm solution, and that unique solution provably (for linear networks) matches the training inputs. The method also vastly improves the samples generated for nonlinear networks, as we demonstrate on MNIST.
Tasks
Published	2019-10-26
URL	https://arxiv.org/abs/1910.12151v1
PDF	https://arxiv.org/pdf/1910.12151v1.pdf
PWC	https://paperswithcode.com/paper/making-predictive-coding-networks-generative
Repo
Framework

Deep Sensor Fusion for Real-Time Odometry Estimation


Title	Deep Sensor Fusion for Real-Time Odometry Estimation
Authors	Michelle Valente, Cyril Joly, Arnaud de La Fortelle
Abstract	Cameras and 2D laser scanners, in combination, are able to provide low-cost, light-weight and accurate solutions, which make their fusion well-suited for many robot navigation tasks. However, correct data fusion depends on precise calibration of the rigid body transform between the sensors. In this paper we present the first framework that makes use of Convolutional Neural Networks (CNNs) for odometry estimation fusing 2D laser scanners and mono-cameras. The use of CNNs provides the tools to not only extract the features from the two sensors, but also to fuse and match them without needing a calibration between the sensors. We transform the odometry estimation into an ordinal classification problem in order to find accurate rotation and translation values between consecutive frames. Results on a real road dataset show that the fusion network runs in real-time and is able to improve the odometry estimation of a single sensor alone by learning how to fuse two different types of data information.
Tasks	Calibration, Robot Navigation, Sensor Fusion
Published	2019-07-31
URL	https://arxiv.org/abs/1908.00524v1
PDF	https://arxiv.org/pdf/1908.00524v1.pdf
PWC	https://paperswithcode.com/paper/deep-sensor-fusion-for-real-time-odometry
Repo
Framework

Pretraining Methods for Dialog Context Representation Learning


Title	Pretraining Methods for Dialog Context Representation Learning
Authors	Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao, Maxine Eskenazi
Abstract	This paper examines various unsupervised pretraining objectives for learning dialog context representations. Two novel methods of pretraining dialog context encoders are proposed, and a total of four methods are examined. Each pretraining objective is fine-tuned and evaluated on a set of downstream dialog tasks using the MultiWoz dataset and strong performance improvement is observed. Further evaluation shows that our pretraining objectives result in not only better performance, but also better convergence, models that are less data hungry and have better domain generalizability.
Tasks	Representation Learning
Published	2019-06-02
URL	https://arxiv.org/abs/1906.00414v2
PDF	https://arxiv.org/pdf/1906.00414v2.pdf
PWC	https://paperswithcode.com/paper/190600414
Repo
Framework

Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning


Title	Instance Segmentation of Fibers from Low Resolution CT Scans via 3D Deep Embedding Learning
Authors	Tomasz Konopczyński, Thorben Kröger, Lei Zheng, Jürgen Hesser
Abstract	We propose a novel approach for automatic extraction (instance segmentation) of fibers from low resolution 3D X-ray computed tomography scans of short glass fiber reinforced polymers. We have designed a 3D instance segmentation architecture built upon a deep fully convolutional network for semantic segmentation with an extra output for embedding learning. We show that the embedding learning is capable of learning a mapping of voxels to an embedded space in which a standard clustering algorithm can be used to distinguish between different instances of an object in a volume. In addition, we discuss a merging post-processing method which makes it possible to process volumes of any size. The proposed 3D instance segmentation network together with our merging algorithm is the first known to authors knowledge procedure that produces results good enough, that they can be used for further analysis of low resolution fiber composites CT scans.
Tasks	3D Instance Segmentation, Instance Segmentation, Semantic Segmentation
Published	2019-01-04
URL	http://arxiv.org/abs/1901.01034v1
PDF	http://arxiv.org/pdf/1901.01034v1.pdf
PWC	https://paperswithcode.com/paper/instance-segmentation-of-fibers-from-low
Repo
Framework

Detection of Review Abuse via Semi-Supervised Binary Multi-Target Tensor Decomposition


Title	Detection of Review Abuse via Semi-Supervised Binary Multi-Target Tensor Decomposition
Authors	Anil R. Yelundur, Vineet Chaoji, Bamdev Mishra
Abstract	Product reviews and ratings on e-commerce websites provide customers with detailed insights about various aspects of the product such as quality, usefulness, etc. Since they influence customers’ buying decisions, product reviews have become a fertile ground for abuse by sellers (colluding with reviewers) to promote their own products or to tarnish the reputation of competitor’s products. In this paper, our focus is on detecting such abusive entities (both sellers and reviewers) by applying tensor decomposition on the product reviews data. While tensor decomposition is mostly unsupervised, we formulate our problem as a semi-supervised binary multi-target tensor decomposition, to take advantage of currently known abusive entities. We empirically show that our multi-target semi-supervised model achieves higher precision and recall in detecting abusive entities as compared to unsupervised techniques. Finally, we show that our proposed stochastic partial natural gradient inference for our model empirically achieves faster convergence than stochastic gradient and Online-EM with sufficient statistics.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06246v2
PDF	https://arxiv.org/pdf/1905.06246v2.pdf
PWC	https://paperswithcode.com/paper/detection-of-review-abuse-via-semi-supervised
Repo
Framework

Improved cross-validation for classifiers that make algorithmic choices to minimise runtime without compromising output correctness


Title	Improved cross-validation for classifiers that make algorithmic choices to minimise runtime without compromising output correctness
Authors	Dorian Florescu, Matthew England
Abstract	Our topic is the use of machine learning to improve software by making choices which do not compromise the correctness of the output, but do affect the time taken to produce such output. We are particularly concerned with computer algebra systems (CASs), and in particular, our experiments are for selecting the variable ordering to use when performing a cylindrical algebraic decomposition of $n$-dimensional real space with respect to the signs of a set of polynomials. In our prior work we explored the different ML models that could be used, and how to identify suitable features of the input polynomials. In the present paper we both repeat our prior experiments on problems which have more variables (and thus exponentially more possible orderings), and examine the metric which our ML classifiers targets. The natural metric is computational runtime, with classifiers trained to pick the ordering which minimises this. However, this leads to the situation were models do not distinguish between any of the non-optimal orderings, whose runtimes may still vary dramatically. In this paper we investigate a modification to the cross-validation algorithms of the classifiers so that they do distinguish these cases, leading to improved results.
Tasks
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12672v1
PDF	https://arxiv.org/pdf/1911.12672v1.pdf
PWC	https://paperswithcode.com/paper/improved-cross-validation-for-classifiers
Repo
Framework