January 28, 2020

3540 words 17 mins read

Paper Group ANR 818

Semantic Source Code Search: A Study of the Past and a Glimpse at the Future. Short-term prediction of Electricity Outages Caused by Convective Storms. Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering. It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution. Mental Task C …

Semantic Source Code Search: A Study of the Past and a Glimpse at the Future


Title	Semantic Source Code Search: A Study of the Past and a Glimpse at the Future
Authors	Muhammad Khalifa
Abstract	With the recent explosion in the size and complexity of source codebases and software projects, the need for efficient source code search engines has increased dramatically. Unfortunately, existing information retrieval-based methods fail to capture the query semantics and perform well only when the query contains syntax-based keywords. Consequently, such methods will perform poorly when given high-level natural language queries. In this paper, we review existing methods for building code search engines. We also outline the open research directions and the various obstacles that stand in the way of having a universal source code search engine.
Tasks	Code Search, Information Retrieval
Published	2019-08-15
URL	https://arxiv.org/abs/1908.06738v1
PDF	https://arxiv.org/pdf/1908.06738v1.pdf
PWC	https://paperswithcode.com/paper/semantic-source-code-search-a-study-of-the
Repo
Framework

Short-term prediction of Electricity Outages Caused by Convective Storms


Title	Short-term prediction of Electricity Outages Caused by Convective Storms
Authors	Roope Tervo, Joonas Karjalainen, Alexander Jung
Abstract	Prediction of power outages caused by convective storms which are highly localised in space and time is of crucial importance to power grid operators. We propose a new machine learning approach to predict the damage caused by storms. This approach hinges identifying and tracking of storm cells using weather radar images on the application of machine learning techniques. Overall prediction process consists of identifying storm cells from CAPPI weather radar images by contouring them with a solid 35 dBZ threshold, predicting a track of storm cells and classifying them based on their damage potential to power grid operators. Tracked storm cells are then classified by combining data obtained from weather radar, ground weather observations and lightning detectors. We compare random forest classifiers and deep neural networks as alternative methods to classify storm cells. The main challenge is that the training data are heavily imbalanced as extreme weather events are rare.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00662v1
PDF	https://arxiv.org/pdf/1907.00662v1.pdf
PWC	https://paperswithcode.com/paper/short-term-prediction-of-electricity-outages
Repo
Framework

Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering


Title	Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering
Authors	Manuel Fernandez, David P. Woodruff, Taisuke Yasuda
Abstract	We present tight lower bounds on the number of kernel evaluations required to approximately solve kernel ridge regression (KRR) and kernel $k$-means clustering (KKMC) on $n$ input points. For KRR, our bound for relative error approximation to the minimizer of the objective function is $\Omega(nd_{\mathrm{eff}}^\lambda/\varepsilon)$ where $d_{\mathrm{eff}}^\lambda$ is the effective statistical dimension, which is tight up to a $\log(d_{\mathrm{eff}}^\lambda/\varepsilon)$ factor. For KKMC, our bound for finding a $k$-clustering achieving a relative error approximation of the objective function is $\Omega(nk/\varepsilon)$, which is tight up to a $\log(k/\varepsilon)$ factor. Our KRR result resolves a variant of an open question of El Alaoui and Mahoney, asking whether the effective statistical dimension is a lower bound on the sampling complexity or not. Furthermore, for the important practical case when the input is a mixture of Gaussians, we provide a KKMC algorithm which bypasses the above lower bound.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06394v1
PDF	https://arxiv.org/pdf/1905.06394v1.pdf
PWC	https://paperswithcode.com/paper/tight-kernel-query-complexity-of-kernel-ridge
Repo
Framework

It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution


Title	It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution
Authors	Rowan Hall Maudslay, Hila Gonen, Ryan Cotterell, Simone Teufel
Abstract	This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA), in which a corpus is duplicated and augmented to remove bias, e.g. by swapping all inherently-gendered words in the copy. We perform an empirical comparison of these approaches on the English Gigaword and Wikipedia, and find that whilst both successfully reduce direct bias and perform well in tasks which quantify embedding quality, CDA variants outperform projection-based methods at the task of drawing non-biased gender analogies by an average of 19% across both corpora. We propose two improvements to CDA: Counterfactual Data Substitution (CDS), a variant of CDA in which potentially biased text is randomly substituted to avoid duplication, and the Names Intervention, a novel name-pairing technique that vastly increases the number of words being treated. CDA/S with the Names Intervention is the only approach which is able to mitigate indirect gender bias: following debiasing, previously biased words are significantly less clustered according to gender (cluster purity is reduced by 49%), thus improving on the state-of-the-art for bias mitigation.
Tasks	Data Augmentation, Word Embeddings
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00871v3
PDF	https://arxiv.org/pdf/1909.00871v3.pdf
PWC	https://paperswithcode.com/paper/its-all-in-the-name-mitigating-gender-bias
Repo
Framework

Mental Task Classification Using Electroencephalogram Signal


Title	Mental Task Classification Using Electroencephalogram Signal
Authors	Zeyu Bai, Ruizhi Yang, Youzhi Liang
Abstract	This paper studies the classification problem on electroencephalogram (EEG) data of mental tasks, using standard architecture of three-layer CNN, stacked LSTM, stacked GRU. We further propose a novel classifier - a mixed LSTM model with a CNN decoder. A hyperparameter optimization on CNN shows validation accuracy of 72% and testing accuracy of 62%. The stacked LSTM and GRU models with FFT preprocessing and downsampling on data achieve 55% and 51% testing accuracy respectively. As for the mixed LSTM model with CNN decoder, validation accuracy of 75% and testing accuracy of 70% are obtained. We believe the mixed model is more robust and accurate than both CNN and LSTM individually, by using the CNN layer as a decoder for following LSTM layers. The code is completed in the framework of Pytorch and Keras. Results and code can be found at https://github.com/theyou21/BigProject.
Tasks	EEG, Hyperparameter Optimization
Published	2019-10-02
URL	https://arxiv.org/abs/1910.03023v1
PDF	https://arxiv.org/pdf/1910.03023v1.pdf
PWC	https://paperswithcode.com/paper/mental-task-classification-using
Repo
Framework

Using Deep Learning Neural Networks and Candlestick Chart Representation to Predict Stock Market


Title	Using Deep Learning Neural Networks and Candlestick Chart Representation to Predict Stock Market
Authors	Rosdyana Mangir Irawan Kusuma, Trang-Thi Ho, Wei-Chun Kao, Yu-Yen Ou, Kai-Lung Hua
Abstract	Stock market prediction is still a challenging problem because there are many factors effect to the stock market price such as company news and performance, industry performance, investor sentiment, social media sentiment and economic factors. This work explores the predictability in the stock market using Deep Convolutional Network and candlestick charts. The outcome is utilized to design a decision support framework that can be used by traders to provide suggested indications of future stock price direction. We perform this work using various types of neural networks like convolutional neural network, residual network and visual geometry group network. From stock market historical data, we converted it to candlestick charts. Finally, these candlestick charts will be feed as input for training a Convolutional Neural Network model. This Convolutional Neural Network model will help us to analyze the patterns inside the candlestick chart and predict the future movements of stock market. The effectiveness of our method is evaluated in stock market prediction with a promising results 92.2% and 92.1% accuracy for Taiwan and Indonesian stock market dataset respectively. The constructed model have been implemented as a web-based system freely available at http://140.138.155.216/deepcandle/ for predicting stock market using candlestick chart and deep learning neural networks.
Tasks	Stock Market Prediction
Published	2019-02-26
URL	http://arxiv.org/abs/1903.12258v1
PDF	http://arxiv.org/pdf/1903.12258v1.pdf
PWC	https://paperswithcode.com/paper/using-deep-learning-neural-networks-and
Repo
Framework

HyMER: A Hybrid Machine Learning Framework for Energy Efficient Routing in SDN


Title	HyMER: A Hybrid Machine Learning Framework for Energy Efficient Routing in SDN
Authors	Beakal Gizachew Assefa, Oznur Ozkasap
Abstract	Combining the capabilities of the programmability of networks by SDN and discovering patterns by machine learning are utilized in security, traffic classification, QoS prediction, and network performance and has attracted the attention of researchers. In this work, we propose HyMER: a novel hybrid machine learning framework for traffic aware energy efficient routing in SDN which has supervised and reinforcement learning components. The supervised learning component consists of feature extraction, training, and testing. The reinforcement learning component learns from existing data or from scratch by iteratively interacting with the network environment. The framework is developed on POX controller and is evaluated on Mininet using Abiline, GEANT, and Nobel-Germany real-world topologies and dynamic traffic traces. Experimental results show that the supervised component achieves up to 70% feature size reduction and more than 80% accuracy in parameter prediction. The refine heuristics algorithm increases the accuracy of the prediction to 100% with 14X to 25X speedup as compared to the brute force method. The reinforcement learning module converges from 100 to 275 iterations and converges twice faster if applied on top of the supervised component. Moreover, HyMER achieves up to 10 watts per switch power saving, 30% link saving, 2 hops decrease in average path length.
Tasks
Published	2019-08-27
URL	https://arxiv.org/abs/1909.08074v1
PDF	https://arxiv.org/pdf/1909.08074v1.pdf
PWC	https://paperswithcode.com/paper/hymer-a-hybrid-machine-learning-framework-for
Repo
Framework

AttKGCN: Attribute Knowledge Graph Convolutional Network for Person Re-identification


Title	AttKGCN: Attribute Knowledge Graph Convolutional Network for Person Re-identification
Authors	Bo Jiang, Xixi Wang, Jin Tang
Abstract	Discriminative feature representation of person image is important for person re-identification (Re-ID) task. Recently, attributes have been demonstrated beneficially in guiding for learning more discriminative feature representations for Re-ID. As attributes normally co-occur in person images, it is desirable to model the attribute dependencies to improve the attribute prediction and thus Re-ID results. In this paper, we propose to model these attribute dependencies via a novel attribute knowledge graph (AttKG), and propose a novel Attribute Knowledge Graph Convolutional Network (AttKGCN) to solve Re-ID problem. AttKGCN integrates both attribute prediction and Re-ID learning together in a unified end-to-end framework which can boost their performances, respectively. AttKGCN first builds a directed attribute KG whose nodes denote attributes and edges encode the co-occurrence relationships of different attributes. Then, AttKGCN learns a set of inter-dependent attribute classifiers which are combined with person visual descriptors for attribute prediction. Finally, AttKGCN integrates attribute description and deeply visual representation together to construct a more discriminative feature representation for Re-ID task. Extensive experiments on several benchmark datasets demonstrate the effectiveness of AttKGCN on attribute prediction and Re-ID tasks.
Tasks	Person Re-Identification
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10544v1
PDF	https://arxiv.org/pdf/1911.10544v1.pdf
PWC	https://paperswithcode.com/paper/attkgcn-attribute-knowledge-graph
Repo
Framework

Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensors


Title	Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensors
Authors	Manu Airaksinen, Okko Räsänen, Elina Ilén, Taru Häyrinen, Anna Kivi, Viviana Marchi, Anastasia Gallen, Sonja Blom, Anni Varhe, Nico Kaartinen, Leena Haataja, Sampsa Vanhatalo
Abstract	Infants’ spontaneous and voluntary movements mirror developmental integrity of brain networks since they require coordinated activation of multiple sites in the central nervous system. Accordingly, early detection of infants with atypical motor development holds promise for recognizing those infants who are at risk for a wide range of neurodevelopmental disorders (e.g., cerebral palsy, autism spectrum disorders). Previously, novel wearable technology has shown promise for offering efficient, scalable and automated methods for movement assessment in adults. Here, we describe the development of an infant wearable, a multi-sensor smart jumpsuit that allows mobile accelerometer and gyroscope data collection during movements. Using this suit, we first recorded play sessions of 22 typically developing infants of approximately 7 months of age. These data were manually annotated for infant posture and movement based on video recordings of the sessions, and using a novel annotation scheme specifically designed to assess the overall movement pattern of infants in the given age group. A machine learning algorithm, based on deep convolutional neural networks (CNNs) was then trained for automatic detection of posture and movement classes using the data and annotations. Our experiments show that the setup can be used for quantitative tracking of infant movement activities with a human equivalent accuracy, i.e., it meets the human inter-rater agreement levels in infant posture and movement classification. We also quantify the ambiguity of human observers in analyzing infant movements, and propose a method for utilizing this uncertainty for performance improvements in training of the automated classifier. Comparison of different sensor configurations also shows that four-limb recording leads to the best performance in posture and movement classification.
Tasks
Published	2019-09-21
URL	https://arxiv.org/abs/1909.09823v2
PDF	https://arxiv.org/pdf/1909.09823v2.pdf
PWC	https://paperswithcode.com/paper/190909823
Repo
Framework

GF + MMT = GLF – From Language to Semantics through LF


Title	GF + MMT = GLF – From Language to Semantics through LF
Authors	Michael Kohlhase, Jan Frederik Schaefer
Abstract	These days, vast amounts of knowledge are available online, most of it in written form. Search engines help us access this knowledge, but aggregating, relating and reasoning with it is still a predominantly human effort. One of the key challenges for automated reasoning based on natural-language texts is the need to extract meaning (semantics) from texts. Natural language understanding (NLU) systems describe the conversion from a set of natural language utterances to terms in a particular logic. Tools for the co-development of grammar and target logic are currently largely missing. We will describe the Grammatical Logical Framework (GLF), a combination of two existing frameworks, in which large parts of a symbolic, rule-based NLU system can be developed and implemented: the Grammatical Framework (GF) and MMT. GF is a tool for syntactic analysis, generation, and translation with complex natural language grammars and MMT can be used to specify logical systems and to represent knowledge in them. Combining these tools is possible, because they are based on compatible logical frameworks: Martin-L"of type theory and LF. The flexibility of logical frameworks is needed, as NLU research has not settled on a particular target logic for meaning representation. Instead, new logics are developed all the time to handle various language phenomena. GLF allows users to develop the logic and the language parsing components in parallel, and to connect them for experimentation with the entire pipeline.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10849v1
PDF	https://arxiv.org/pdf/1910.10849v1.pdf
PWC	https://paperswithcode.com/paper/gf-mmt-glf-from-language-to-semantics-through
Repo
Framework

Zero-Shot Crowd Behavior Recognition


Title	Zero-Shot Crowd Behavior Recognition
Authors	Xun Xu, Shaogang Gong, Timothy Hospedales
Abstract	Understanding crowd behavior in video is challenging for computer vision. There have been increasing attempts on modeling crowded scenes by introducing ever larger property ontologies (attributes) and annotating ever larger training datasets. However, in contrast to still images, manually annotating video attributes needs to consider spatiotemporal evolution which is inherently much harder and more costly. Critically, the most interesting crowd behaviors captured in surveillance videos (e.g., street fighting, flash mobs) are either rare, thus have few examples for model training, or unseen previously. Existing crowd analysis techniques are not readily scalable to recognize novel (unseen) crowd behaviors. To address this problem, we investigate and develop methods for recognizing visual crowd behavioral attributes without any training samples, i.e., zero-shot learning crowd behavior recognition. To that end, we relax the common assumption that each individual crowd video instance is only associated with a single crowd attribute. Instead, our model learns to jointly recognize multiple crowd behavioral attributes in each video instance by exploring multiattribute cooccurrence as contextual knowledge for optimizing individual crowd attribute recognition. Joint multilabel attribute prediction in zero-shot learning is inherently nontrivial because cooccurrence statistics does not exist for unseen attributes. To solve this problem, we learn to predict cross-attribute cooccurrence from both online text corpus and multilabel annotation of videos with known attributes. Our experiments show that this approach to modeling multiattribute context not only improves zero-shot crowd behavior recognition on the WWW crowd video dataset, but also generalizes to novel behavior (violence) detection cross-domain in the Violence Flow video dataset.
Tasks	Zero-Shot Learning
Published	2019-08-16
URL	https://arxiv.org/abs/1908.05877v1
PDF	https://arxiv.org/pdf/1908.05877v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-crowd-behavior-recognition
Repo
Framework

Relation Network for Person Re-identification


Title	Relation Network for Person Re-identification
Authors	Hyunjong Park, Bumsub Ham
Abstract	Person re-identification (reID) aims at retrieving an image of the person of interest from a set of images typically captured by multiple cameras. Recent reID methods have shown that exploiting local features describing body parts, together with a global feature of a person image itself, gives robust feature representations, even in the case of missing body parts. However, using the individual part-level features directly, without considering relations between body parts, confuses differentiating identities of different persons having similar attributes in corresponding parts. To address this issue, we propose a new relation network for person reID that considers relations between individual body parts and the rest of them. Our model makes a single part-level feature incorporate partial information of other body parts as well, supporting it to be more discriminative. We also introduce a global contrastive pooling (GCP) method to obtain a global feature of a person image. We propose to use contrastive features for GCP to complement conventional max and averaging pooling techniques. We show that our model outperforms the state of the art on the Market1501, DukeMTMC-reID and CUHK03 datasets, demonstrating the effectiveness of our approach on discriminative person representations.
Tasks	Person Re-Identification
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09318v2
PDF	https://arxiv.org/pdf/1911.09318v2.pdf
PWC	https://paperswithcode.com/paper/relation-network-for-person-re-identification
Repo
Framework

Leveraging User Engagement Signals For Entity Labeling in a Virtual Assistant


Title	Leveraging User Engagement Signals For Entity Labeling in a Virtual Assistant
Authors	Deepak Muralidharan, Justine Kao, Xiao Yang, Lin Li, Lavanya Viswanathan, Mubarak Seyed Ibrahim, Kevin Luikens, Stephen Pulman, Ashish Garg, Atish Kothari, Jason Williams
Abstract	Personal assistant AI systems such as Siri, Cortana, and Alexa have become widely used as a means to accomplish tasks through natural language commands. However, components in these systems generally rely on supervised machine learning algorithms that require large amounts of hand-annotated training data, which is expensive and time consuming to collect. The ability to incorporate unsupervised, weakly supervised, or distantly supervised data holds significant promise in overcoming this bottleneck. In this paper, we describe a framework that leverages user engagement signals (user behaviors that demonstrate a positive or negative response to content) to automatically create granular entity labels for training data augmentation. Strategies such as multi-task learning and validation using an external knowledge base are employed to incorporate the engagement annotated data and to boost the model’s accuracy on a sequence labeling task. Our results show that learning from data automatically labeled by user engagement signals achieves significant accuracy gains in a production deep learning system, when measured on both the sequence labeling task as well as on user facing results produced by the system end-to-end. We believe this is the first use of user engagement signals to help generate training data for a sequence labeling task on a large scale, and can be applied in practical settings to speed up new feature deployment when little human annotated data is available.
Tasks	Data Augmentation, Multi-Task Learning
Published	2019-09-18
URL	https://arxiv.org/abs/1909.09143v1
PDF	https://arxiv.org/pdf/1909.09143v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-user-engagement-signals-for-entity
Repo
Framework

Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image


Title	Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image
Authors	Xiaoguang Han, Zhaoxuan Zhang, Dong Du, Mingdai Yang, Jingming Yu, Pan Pan, Xin Yang, Ligang Liu, Zixiang Xiong, Shuguang Cui
Abstract	We present a deep reinforcement learning method of progressive view inpainting for 3D point scene completion under volume guidance, achieving high-quality scene reconstruction from only a single depth image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D depth map inpainting, and multi-view selection for completion. Given a single depth image, our method first goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view depth, and integrating all depth into the point cloud. Since the occluded areas are unavailable, we resort to a deep Q-Network to glance around and pick the next best view for large hole completion progressively until a scene is adequately reconstructed while guaranteeing validity. All steps are learned jointly to achieve robust and consistent results. We perform qualitative and quantitative evaluations with extensive experiments on the SUNCG data, obtaining better results than the state of the art.
Tasks
Published	2019-03-10
URL	http://arxiv.org/abs/1903.04019v2
PDF	http://arxiv.org/pdf/1903.04019v2.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-of-volume-guided
Repo
Framework

Abstractive Document Summarization without Parallel Data


Title	Abstractive Document Summarization without Parallel Data
Authors	Nikola I. Nikolov, Richard H. R. Hahnloser
Abstract	Abstractive summarization typically relies on large collections of paired articles and summaries. However, in many cases, parallel data is scarce and costly to obtain. We develop an abstractive summarization system that relies only on large collections of example summaries and non-matching articles. Our approach consists of an unsupervised sentence extractor that selects salient sentences to include in the final summary, as well as a sentence abstractor that is trained on pseudo-parallel and synthetic data, that paraphrases each of the extracted sentences. We perform an extensive evaluation of our method: on the CNN/DailyMail benchmark, on which we compare our approach to fully supervised baselines, as well as on the novel task of automatically generating a press release from a scientific journal article, which is well suited for our system. We show promising performance on both tasks, without relying on any article-summary pairs.
Tasks	Abstractive Text Summarization, Document Summarization
Published	2019-07-30
URL	https://arxiv.org/abs/1907.12951v2
PDF	https://arxiv.org/pdf/1907.12951v2.pdf
PWC	https://paperswithcode.com/paper/abstractive-document-summarization-without
Repo
Framework