January 31, 2020

3241 words 16 mins read

Paper Group ANR 88

Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorization. Asymmetric Random Projections. Non-Intrusive Electrical Appliances Monitoring and Classification using K-Nearest Neighbors. Slack Channels Ecology in Enterprises: How Employees Collaborate Through Group Chat. Alleviation of Gradient Exploding in GANs: Fake Can Be Real. Non-Intrusi …

Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorization


Title	Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorization
Authors	Ting Huang, Gehui Shen, Zhi-Hong Deng
Abstract	Recurrent Neural Networks (RNNs) are widely used in the field of natural language processing (NLP), ranging from text categorization to question answering and machine translation. However, RNNs generally read the whole text from beginning to end or vice versa sometimes, which makes it inefficient to process long texts. When reading a long document for a categorization task, such as topic categorization, large quantities of words are irrelevant and can be skipped. To this end, we propose Leap-LSTM, an LSTM-enhanced model which dynamically leaps between words while reading texts. At each step, we utilize several feature encoders to extract messages from preceding texts, following texts and the current word, and then determine whether to skip the current word. We evaluate Leap-LSTM on several text categorization tasks: sentiment analysis, news categorization, ontology classification and topic classification, with five benchmark data sets. The experimental results show that our model reads faster and predicts better than standard LSTM. Compared to previous models which can also skip words, our model achieves better trade-offs between performance and efficiency.
Tasks	Machine Translation, Question Answering, Sentiment Analysis, Text Categorization
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11558v1
PDF	https://arxiv.org/pdf/1905.11558v1.pdf
PWC	https://paperswithcode.com/paper/leap-lstm-enhancing-long-short-term-memory
Repo
Framework

Asymmetric Random Projections


Title	Asymmetric Random Projections
Authors	Nick Ryder, Zohar Karnin, Edo Liberty
Abstract	Random projections (RP) are a popular tool for reducing dimensionality while preserving local geometry. In many applications the data set to be projected is given to us in advance, yet the current RP techniques do not make use of information about the data. In this paper, we provide a computationally light way to extract statistics from the data that allows designing a data dependent RP with superior performance compared to data-oblivious RP. We tackle scenarios such as matrix multiplication and linear regression/classification in which we wish to estimate inner products between pairs of vectors from two possibly different sources. Our technique takes advantage of the difference between the sources and is provably superior to oblivious RPs. Additionally, we provide extensive experiments comparing RPs with our approach showing significant performance lifts in fast matrix multiplication, regression and classification problems.
Tasks
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09489v1
PDF	https://arxiv.org/pdf/1906.09489v1.pdf
PWC	https://paperswithcode.com/paper/asymmetric-random-projections
Repo
Framework

Non-Intrusive Electrical Appliances Monitoring and Classification using K-Nearest Neighbors


Title	Non-Intrusive Electrical Appliances Monitoring and Classification using K-Nearest Neighbors
Authors	Mohammad Mahmudur Rahman Khan, Md. Abu Bakr Siddique, Shadman Sakib
Abstract	Non-Intrusive Load Monitoring (NILM) is the method of detecting an individual device’s energy signal from an aggregated energy consumption signature [1]. As existing energy meters provide very little to no information regarding the energy consumption of individual appliances apart from the aggregated power rating, the spotting of individual appliances’ energy usages by NILM will not only provide consumers the feedback of appliance-specific energy usage but also lead to the changes of their consumption behavior which facilitate energy conservation. B Neenan et al. [2] have demonstrated that direct individual appliance-specific energy usage signals lead to consumers’ behavioral changes which improves energy efficiency by as much as 15%. Upon disaggregation of an energy signal, the signal needs to be classified according to the appropriate appliance. Hence, the goal of this paper is to disaggregate total energy consumption data to individual appliance signature and then classify appliance-specific energy loads using a prominent supervised classification method known as K-Nearest Neighbors (KNN). To perform this operation we have used a publicly accessible dataset of power signals from several houses known as the REDD dataset. Before applying KNN, data is preprocessed for each device. Then KNN is applied to check whether their energy consumption signature is separable or not. KNN is applied with K=5.
Tasks	Non-Intrusive Load Monitoring
Published	2019-11-22
URL	https://arxiv.org/abs/1911.13257v1
PDF	https://arxiv.org/pdf/1911.13257v1.pdf
PWC	https://paperswithcode.com/paper/non-intrusive-electrical-appliances
Repo
Framework

Slack Channels Ecology in Enterprises: How Employees Collaborate Through Group Chat


Title	Slack Channels Ecology in Enterprises: How Employees Collaborate Through Group Chat
Authors	Dakuo Wang, Haoyu Wang, Mo Yu, Zahra Ashktorab, Ming Tan
Abstract	Despite the long history of studying instant messaging usage in organizations, we know very little about how today’s people participate in group chat channels and interact with others. In this short note, we aim to update the existing knowledge on how group chat is used in the context of today’s organizations. We have the privilege of collecting a total of 4300 publicly available group chat channels in Slack from an R&D department in a multinational IT company. Through qualitative coding of 100 channels, we identified 9 channel categories such as project based channels and event channels. We further defined a feature metric with 21 features to depict the group communication style for these group chat channels, with which we successfully trained a machine learning model that can automatically classify a given group channel into one of the 9 categories. In addition, we illustrated how these communication metrics could be used for analyzing teams’ collaboration activities. We focused on 117 project teams as we have their performance data, and further collected 54 out of the 117 teams’ Slack group data and generated the communication style metrics for each of them. With these data, we are able to build a regression model to reveal the relationship between these group communication styles and one indicator of the project team performance.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01756v2
PDF	https://arxiv.org/pdf/1906.01756v2.pdf
PWC	https://paperswithcode.com/paper/slack-channels-ecology-in-enterprises-how
Repo
Framework

Alleviation of Gradient Exploding in GANs: Fake Can Be Real


Title	Alleviation of Gradient Exploding in GANs: Fake Can Be Real
Authors	Song Tao, Jia Wang
Abstract	In order to alleviate the notorious mode collapse phenomenon in generative adversarial networks (GANs), we propose a novel training method of GANs in which certain fake samples are considered as real ones during the training process. This strategy can reduce the gradient value that generator receives in the region where gradient exploding happens. We show the process of an unbalanced generation and a vicious circle issue resulted from gradient exploding in practical training, which explains the instability of GANs. We also theoretically prove that gradient exploding can be alleviated by penalizing the difference between discriminator outputs and fake-as-real consideration for very close real and fake samples. Accordingly, Fake-As-Real GAN (FARGAN) is proposed with a more stable training process and a more faithful generated distribution. Experiments on different datasets verify our theoretical analysis.
Tasks
Published	2019-12-28
URL	https://arxiv.org/abs/1912.12485v2
PDF	https://arxiv.org/pdf/1912.12485v2.pdf
PWC	https://paperswithcode.com/paper/alleviation-for-gradient-exploding-in-gans
Repo
Framework

Non-Intrusive Load Monitoring with an Attention-based Deep Neural Network


Title	Non-Intrusive Load Monitoring with an Attention-based Deep Neural Network
Authors	Antonio Maria Sudoso, Veronica Piccialli
Abstract	Energy disaggregation, also referred to as a Non-Intrusive Load Monitoring (NILM), is the task of using an aggregate energy signal, for example coming from a whole-home power monitor, to make inferences about the different individual loads of the system. In this paper, we present a novel approach based on the encoder-decoder deep learning framework with an attention mechanism for solving NILM. The attention mechanism is inspired by the temporal attention mechanism that has been recently applied to get state-of-the-art results in neural machine translation, text summarization and speech recognition. The experiments have been conducted on two publicly available datasets AMPds and UK-DALE in seen and unseen conditions. The results show that our proposed deep neural network outperforms the state-of-the-art Denoising Auto-Encoder (DAE) proposed initially by Kelly and Knottenbely (2015) and its extended and improved architecture by Bonfigli et al. (2018), in all the addressed experimental conditions. We also show that modeling attention translates into the ability to correctly detect the state change of each appliance, that is of extreme interest in the field of energy disaggregation.
Tasks	Denoising, Machine Translation, Non-Intrusive Load Monitoring, Speech Recognition, Text Summarization
Published	2019-11-15
URL	https://arxiv.org/abs/1912.00759v1
PDF	https://arxiv.org/pdf/1912.00759v1.pdf
PWC	https://paperswithcode.com/paper/non-intrusive-load-monitoring-with-an
Repo
Framework

Can I teach a robot to replicate a line art


Title	Can I teach a robot to replicate a line art
Authors	Raghav Brahmadesam Venkataramaiyer, Subham Kumar, Vinay P. Namboodiri
Abstract	Line art is arguably one of the fundamental and versatile modes of expression. We propose a pipeline for a robot to look at a grayscale line art and redraw it. The key novel elements of our pipeline are: a) we propose a novel task of mimicking line drawings, b) to solve the pipeline we modify the Quick-draw dataset to obtain supervised training for converting a line drawing into a series of strokes c) we propose a multi-stage segmentation and graph interpretation pipeline for solving the problem. The resultant method has also been deployed on a CNC plotter as well as a robotic arm. We have trained several variations of the proposed methods and evaluate these on a dataset obtained from Quick-draw. Through the best methods we observe an accuracy of around 98% for this task, which is a significant improvement over the baseline architecture we adapted from. This therefore allows for deployment of the method on robots for replicating line art in a reliable manner. We also show that while the rule-based vectorization methods do suffice for simple drawings, it fails for more complicated sketches, unlike our method which generalizes well to more complicated distributions.
Tasks
Published	2019-10-17
URL	https://arxiv.org/abs/1910.07860v1
PDF	https://arxiv.org/pdf/1910.07860v1.pdf
PWC	https://paperswithcode.com/paper/can-i-teach-a-robot-to-replicate-a-line-art
Repo
Framework

Long and Short Memory Balancing in Visual Co-Tracking using Q-Learning


Title	Long and Short Memory Balancing in Visual Co-Tracking using Q-Learning
Authors	Kourosh Meshgi, Maryam Sadat Mirzaei, Shigeyuki Oba
Abstract	Employing one or more additional classifiers to break the self-learning loop in tracing-by-detection has gained considerable attention. Most of such trackers merely utilize the redundancy to address the accumulating label error in the tracking loop, and suffer from high computational complexity as well as tracking challenges that may interrupt all classifiers (e.g. temporal occlusions). We propose the active co-tracking framework, in which the main classifier of the tracker labels samples of the video sequence, and only consults auxiliary classifier when it is uncertain. Based on the source of the uncertainty and the differences of two classifiers (e.g. accuracy, speed, update frequency, etc.), different policies should be taken to exchange the information between two classifiers. Here, we introduce a reinforcement learning approach to find the appropriate policy by considering the state of the tracker in a specific sequence. The proposed method yields promising results in comparison to the best tracking-by-detection approaches.
Tasks	Q-Learning
Published	2019-02-14
URL	http://arxiv.org/abs/1902.05211v1
PDF	http://arxiv.org/pdf/1902.05211v1.pdf
PWC	https://paperswithcode.com/paper/long-and-short-memory-balancing-in-visual-co
Repo
Framework

Hierarchical Policy Learning is Sensitive to Goal Space Design


Title	Hierarchical Policy Learning is Sensitive to Goal Space Design
Authors	Zach Dwiel, Madhavun Candadai, Mariano Phielipp, Arjun K. Bansal
Abstract	Hierarchy in reinforcement learning agents allows for control at multiple time scales yielding improved sample efficiency, the ability to deal with long time horizons and transferability of sub-policies to tasks outside the training distribution. It is often implemented as a master policy providing goals to a sub-policy. Ideally, we would like the goal-spaces to be learned, however, properties of optimal goal spaces still remain unknown and consequently there is no method yet to learn optimal goal spaces. Motivated by this, we systematically analyze how various modifications to the ground-truth goal-space affect learning in hierarchical models with the aim of identifying important properties of optimal goal spaces. Our results show that, while rotation of ground-truth goal spaces and noise had no effect, having additional unnecessary factors significantly impaired learning in hierarchical models.
Tasks
Published	2019-05-04
URL	https://arxiv.org/abs/1905.01537v2
PDF	https://arxiv.org/pdf/1905.01537v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-policy-learning-is-sensitive-to
Repo
Framework

Towards Flops-constrained Face Recognition


Title	Towards Flops-constrained Face Recognition
Authors	Yu Liu, Guanglu Song, Manyuan Zhang, Jihao Liu, Yucong Zhou, Junjie Yan
Abstract	Large scale face recognition is challenging especially when the computational budget is limited. Given a \textit{flops} upper bound, the key is to find the optimal neural network architecture and optimization method. In this article, we briefly introduce the solutions of team ‘trojans’ for the ICCV19 - Lightweight Face Recognition Challenge~\cite{lfr}. The challenge requires each submission to be one single model with the computational budget no higher than 30 GFlops. We introduce a searched network architecture `Efficient PolyFace' based on the Flops constraint, a novel loss function` ArcNegFace’, a novel frame aggregation method `QAN++', together with a bag of useful tricks in our implementation (augmentations, regular face, label smoothing, anchor finetuning, etc.). Our basic model,` Efficient PolyFace’, takes 28.25 Gflops for the `deepglint-large' image-based track, and the` PolyFace+QAN++’ solution takes 24.12 Gflops for the `iQiyi-large’ video-based track. These two solutions achieve 94.198% @ 1e-8 and 72.981% @ 1e-4 in the two tracks respectively, which are the state-of-the-art results. \|
Tasks	Face Recognition
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00632v1
PDF	https://arxiv.org/pdf/1909.00632v1.pdf
PWC	https://paperswithcode.com/paper/towards-flops-constrained-face-recognition
Repo
Framework

AI2D-RST: A multimodal corpus of 1000 primary school science diagrams


Title	AI2D-RST: A multimodal corpus of 1000 primary school science diagrams
Authors	Tuomo Hiippala, Malihe Alikhani, Jonas Haverinen, Timo Kalliokoski, Evanfiya Logacheva, Serafina Orekhova, Aino Tuomainen, Matthew Stone, John A. Bateman
Abstract	This article introduces AI2D-RST, a multimodal corpus of 1000 English-language diagrams that represent topics in primary school natural sciences, such as food webs, life cycles, moon phases and human physiology. The corpus is based on the Allen Institute for Artificial Intelligence Diagrams (AI2D) dataset, a collection of diagrams with crowd-sourced descriptions, which was originally developed to support research on automatic diagram understanding and visual question answering. Building on the segmentation of diagram layouts in AI2D, the AI2D-RST corpus presents a new multi-layer annotation schema that provides a rich description of their multimodal structure. Annotated by trained experts, the layers describe (1) the grouping of diagram elements into perceptual units, (2) the connections set up by diagrammatic elements such as arrows and lines, and (3) the discourse relations between diagram elements, which are described using Rhetorical Structure Theory (RST). Each annotation layer in AI2D-RST is represented using a graph. The corpus is freely available for research and teaching.
Tasks	Question Answering, Visual Question Answering
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03879v2
PDF	https://arxiv.org/pdf/1912.03879v2.pdf
PWC	https://paperswithcode.com/paper/ai2d-rst-a-multimodal-corpus-of-1000-primary
Repo
Framework

Online Gaussian LDA for Unsupervised Pattern Mining from Utility Usage Data


Title	Online Gaussian LDA for Unsupervised Pattern Mining from Utility Usage Data
Authors	Saad Mohamad, Abdelhamid Bouchachia
Abstract	Non-intrusive load monitoring (NILM) aims at separating a whole-home energy signal into its appliance components. Such method can be harnessed to provide various services to better manage and control energy consumption (optimal planning and saving). NILM has been traditionally approached from signal processing and electrical engineering perspectives. Recently, machine learning has started to play an important role in NILM. While most work has focused on supervised algorithms, unsupervised approaches can be more interesting and of practical use in real case scenarios. Specifically, they do not require labelled training data to be acquired from individual appliances and the algorithm can be deployed to operate on the measured aggregate data directly. In this paper, we propose a fully unsupervised NILM framework based on Bayesian hierarchical mixture models. In particular, we develop a new method based on Gaussian Latent Dirichlet Allocation (GLDA) in order to extract global components that summarise the energy signal. These components provide a representation of the consumption patterns. Designed to cope with big data, our algorithm, unlike existing NILM ones, does not focus on appliance recognition. To handle this massive data, GLDA works online. Another novelty of this work compared to the existing NILM is that the data involves different utilities (e.g, electricity, water and gas) as well as some sensors measurements. Finally, we propose different evaluation methods to analyse the results which show that our algorithm finds useful patterns.
Tasks	Non-Intrusive Load Monitoring
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11599v1
PDF	https://arxiv.org/pdf/1910.11599v1.pdf
PWC	https://paperswithcode.com/paper/online-gaussian-lda-for-unsupervised-pattern
Repo
Framework

Robust Gaussian Process Regression for Real-Time High Precision GPS Signal Enhancement


Title	Robust Gaussian Process Regression for Real-Time High Precision GPS Signal Enhancement
Authors	Ming Lin, Xiaomin Song, Qi Qian, Hao Li, Liang Sun, Shenghuo Zhu, Rong Jin
Abstract	Satellite-based positioning system such as GPS often suffers from large amount of noise that degrades the positioning accuracy dramatically especially in real-time applications. In this work, we consider a data-mining approach to enhance the GPS signal. We build a large-scale high precision GPS receiver grid system to collect real-time GPS signals for training. The Gaussian Process (GP) regression is chosen to model the vertical Total Electron Content (vTEC) distribution of the ionosphere of the Earth. Our experiments show that the noise in the real-time GPS signals often exceeds the breakdown point of the conventional robust regression methods resulting in sub-optimal system performance. We propose a three-step approach to address this challenge. In the first step we perform a set of signal validity tests to separate the signals into clean and dirty groups. In the second step, we train an initial model on the clean signals and then reweigting the dirty signals based on the residual error. A final model is retrained on both the clean signals and the reweighted dirty signals. In the theoretical analysis, we prove that the proposed three-step approach is able to tolerate much higher noise level than the vanilla robust regression methods if two reweighting rules are followed. We validate the superiority of the proposed method in our real-time high precision positioning system against several popular state-of-the-art robust regression methods. Our method achieves centimeter positioning accuracy in the benchmark region with probability $78.4%$ , outperforming the second best baseline method by a margin of $8.3%$. The benchmark takes 6 hours on 20,000 CPU cores or 14 years on a single CPU.
Tasks
Published	2019-06-03
URL	https://arxiv.org/abs/1906.01095v1
PDF	https://arxiv.org/pdf/1906.01095v1.pdf
PWC	https://paperswithcode.com/paper/robust-gaussian-process-regression-for-real
Repo
Framework

Better Character Language Modeling Through Morphology


Title	Better Character Language Modeling Through Morphology
Authors	Terra Blevins, Luke Zettlemoyer
Abstract	We incorporate morphological supervision into character language models (CLMs) via multitasking and show that this addition improves bits-per-character (BPC) performance across 24 languages, even when the morphology data and language modeling data are disjoint. Analyzing the CLMs shows that inflected words benefit more from explicitly modeling morphology than uninflected words, and that morphological supervision improves performance even as the amount of language modeling data grows. We then transfer morphological supervision across languages to improve language modeling performance in the low-resource setting.
Tasks	Language Modelling
Published	2019-06-03
URL	https://arxiv.org/abs/1906.01037v2
PDF	https://arxiv.org/pdf/1906.01037v2.pdf
PWC	https://paperswithcode.com/paper/better-character-language-modeling-through
Repo
Framework

Multi Label Restricted Boltzmann Machine for Non-Intrusive Load Monitoring


Title	Multi Label Restricted Boltzmann Machine for Non-Intrusive Load Monitoring
Authors	Sagar Verma, Shikha Singh, Angshul Majumdar
Abstract	Increasing population indicates that energy demands need to be managed in the residential sector. Prior studies have reflected that the customers tend to reduce a significant amount of energy consumption if they are provided with appliance-level feedback. This observation has increased the relevance of load monitoring in today’s tech-savvy world. Most of the previously proposed solutions claim to perform load monitoring without intrusion, but they are not completely non-intrusive. These methods require historical appliance-level data for training the model for each of the devices. This data is gathered by putting a sensor on each of the appliances present in the home which causes intrusion in the building. Some recent studies have proposed that if we frame Non-Intrusive Load Monitoring (NILM) as a multi-label classification problem, the need for appliance-level data can be avoided. In this paper, we propose Multi-label Restricted Boltzmann Machine(ML-RBM) for NILM and report an experimental evaluation of proposed and state-of-the-art techniques.
Tasks	Multi-Label Classification, Non-Intrusive Load Monitoring
Published	2019-10-17
URL	https://arxiv.org/abs/1910.08149v1
PDF	https://arxiv.org/pdf/1910.08149v1.pdf
PWC	https://paperswithcode.com/paper/multi-label-restricted-boltzmann-machine-for
Repo
Framework