July 29, 2019

3234 words 16 mins read

Paper Group ANR 138

Automated Cloud Provisioning on AWS using Deep Reinforcement Learning. Social Style Characterization from Egocentric Photo-streams. Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification. Memetic search for identifying critical nodes in sparse graphs. Biomedical Event Trigger Identification Using Bidirectional …

Automated Cloud Provisioning on AWS using Deep Reinforcement Learning


Title	Automated Cloud Provisioning on AWS using Deep Reinforcement Learning
Authors	Zhiguang Wang, Chul Gwon, Tim Oates, Adam Iezzi
Abstract	As the use of cloud computing continues to rise, controlling cost becomes increasingly important. Yet there is evidence that 30% - 45% of cloud spend is wasted. Existing tools for cloud provisioning typically rely on highly trained human experts to specify what to monitor, thresholds for triggering action, and actions. In this paper we explore the use of reinforcement learning (RL) to acquire policies to balance performance and spend, allowing humans to specify what they want as opposed to how to do it, minimizing the need for cloud expertise. Empirical results with tabular, deep, and dueling double deep Q-learning with the CloudSim simulator show the utility of RL and the relative merits of the approaches. We also demonstrate effective policy transfer learning from an extremely simple simulator to CloudSim, with the next step being transfer from CloudSim to an Amazon Web Services physical environment.
Tasks	Q-Learning, Transfer Learning
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04305v2
PDF	http://arxiv.org/pdf/1709.04305v2.pdf
PWC	https://paperswithcode.com/paper/automated-cloud-provisioning-on-aws-using
Repo
Framework


Title	Social Style Characterization from Egocentric Photo-streams
Authors	Maedeh Aghaei, Mariella Dimiccoli, Cristian Canton Ferrer, Petia Radeva
Abstract	This paper proposes a system for automatic social pattern characterization using a wearable photo-camera. The proposed pipeline consists of three major steps. First, detection of people with whom the camera wearer interacts and, second, categorization of the detected social interactions into formal and informal. These two steps act at event-level where each potential social event is modeled as a multi-dimensional time-series, whose dimensions correspond to a set of relevant features for each task, and a LSTM network is employed for time-series classification. In the last step, recurrences of the same person across the whole set of social interactions are clustered to achieve a comprehensive understanding of the diversity and frequency of the social relations of the user. Experiments over a dataset acquired by a user wearing a photo-camera during a month show promising results on the task of social pattern characterization from egocentric photo-streams.
Tasks	Time Series, Time Series Classification
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05775v1
PDF	http://arxiv.org/pdf/1709.05775v1.pdf
PWC	https://paperswithcode.com/paper/social-style-characterization-from-egocentric
Repo
Framework

Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification


Title	Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
Authors	Dangwei Li, Xiaotang Chen, Zhang Zhang, Kaiqi Huang
Abstract	Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a fundamental problem in ReID and is still an open problem today. In this paper, we design a Multi-Scale Context-Aware Network (MSCAN) to learn powerful features over full body and body parts, which can well capture the local context knowledge by stacking multi-scale convolutions in each layer. Moreover, instead of using predefined rigid parts, we propose to learn and localize deformable pedestrian parts using Spatial Transformer Networks (STN) with novel spatial constraints. The learned body parts can release some difficulties, eg pose variations and background clutters, in part-based representation. Finally, we integrate the representation learning processes of full body and body parts into a unified framework for person ReID through multi-class person identification tasks. Extensive evaluations on current challenging large-scale person ReID datasets, including the image-based Market1501, CUHK03 and sequence-based MARS datasets, show that the proposed method achieves the state-of-the-art results.
Tasks	Person Identification, Person Re-Identification, Representation Learning
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06555v1
PDF	http://arxiv.org/pdf/1710.06555v1.pdf
PWC	https://paperswithcode.com/paper/learning-deep-context-aware-features-over
Repo
Framework

Memetic search for identifying critical nodes in sparse graphs


Title	Memetic search for identifying critical nodes in sparse graphs
Authors	Yangming Zhou, Jin-Kao Hao, Fred Glover
Abstract	Critical node problems involve identifying a subset of critical nodes from an undirected graph whose removal results in optimizing a pre-defined measure over the residual graph. As useful models for a variety of practical applications, these problems are computational challenging. In this paper, we study the classic critical node problem (CNP) and introduce an effective memetic algorithm for solving CNP. The proposed algorithm combines a double backbone-based crossover operator (to generate promising offspring solutions), a component-based neighborhood search procedure (to find high-quality local optima) and a rank-based pool updating strategy (to guarantee a healthy population). Specially, the component-based neighborhood search integrates two key techniques, i.e., two-phase node exchange strategy and node weighting scheme. The double backbone-based crossover extends the idea of general backbone-based crossovers. Extensive evaluations on 42 synthetic and real-world benchmark instances show that the proposed algorithm discovers 21 new upper bounds and matches 18 previous best-known upper bounds. We also demonstrate the relevance of our algorithm for effectively solving a variant of the classic CNP, called the cardinality-constrained critical node problem. Finally, we investigate the usefulness of each key algorithmic component.
Tasks
Published	2017-05-11
URL	http://arxiv.org/abs/1705.04119v2
PDF	http://arxiv.org/pdf/1705.04119v2.pdf
PWC	https://paperswithcode.com/paper/memetic-search-for-identifying-critical-nodes
Repo
Framework

Biomedical Event Trigger Identification Using Bidirectional Recurrent Neural Network Based Models


Title	Biomedical Event Trigger Identification Using Bidirectional Recurrent Neural Network Based Models
Authors	Patchigolla V S S Rahul, Sunil Kumar Sahu, Ashish Anand
Abstract	Biomedical events describe complex interactions between various biomedical entities. Event trigger is a word or a phrase which typically signifies the occurrence of an event. Event trigger identification is an important first step in all event extraction methods. However many of the current approaches either rely on complex hand-crafted features or consider features only within a window. In this paper we propose a method that takes the advantage of recurrent neural network (RNN) to extract higher level features present across the sentence. Thus hidden state representation of RNN along with word and entity type embedding as features avoid relying on the complex hand-crafted features generated using various NLP toolkits. Our experiments have shown to achieve state-of-art F1-score on Multi Level Event Extraction (MLEE) corpus. We have also performed category-wise analysis of the result and discussed the importance of various features in trigger identification task.
Tasks
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09516v1
PDF	http://arxiv.org/pdf/1705.09516v1.pdf
PWC	https://paperswithcode.com/paper/biomedical-event-trigger-identification-using
Repo
Framework

Memory-augmented Neural Machine Translation


Title	Memory-augmented Neural Machine Translation
Authors	Yang Feng, Shiyue Zhang, Andi Zhang, Dong Wang, Andrew Abel
Abstract	Neural machine translation (NMT) has achieved notable success in recent times, however it is also widely recognized that this approach has limitations with handling infrequent words and word pairs. This paper presents a novel memory-augmented NMT (M-NMT) architecture, which stores knowledge about how words (usually infrequently encountered ones) should be translated in a memory and then utilizes them to assist the neural model. We use this memory mechanism to combine the knowledge learned from a conventional statistical machine translation system and the rules learned by an NMT system, and also propose a solution for out-of-vocabulary (OOV) words based on this framework. Our experiments on two Chinese-English translation tasks demonstrated that the M-NMT architecture outperformed the NMT baseline by $9.0$ and $2.7$ BLEU points on the two tasks, respectively. Additionally, we found this architecture resulted in a much more effective OOV treatment compared to competitive methods.
Tasks	Machine Translation
Published	2017-08-07
URL	http://arxiv.org/abs/1708.02005v1
PDF	http://arxiv.org/pdf/1708.02005v1.pdf
PWC	https://paperswithcode.com/paper/memory-augmented-neural-machine-translation
Repo
Framework

Deep Optical Flow Estimation Via Multi-Scale Correspondence Structure Learning


Title	Deep Optical Flow Estimation Via Multi-Scale Correspondence Structure Learning
Authors	Shanshan Zhao, Xi Li, Omar El Farouk Bourahla
Abstract	As an important and challenging problem in computer vision, learning based optical flow estimation aims to discover the intrinsic correspondence structure between two adjacent video frames through statistical learning. Therefore, a key issue to solve in this area is how to effectively model the multi-scale correspondence structure properties in an adaptive end-to-end learning fashion. Motivated by this observation, we propose an end-to-end multi-scale correspondence structure learning (MSCSL) approach for optical flow estimation. In principle, the proposed MSCSL approach is capable of effectively capturing the multi-scale inter-image-correlation correspondence structures within a multi-level feature space from deep learning. Moreover, the proposed MSCSL approach builds a spatial Conv-GRU neural network model to adaptively model the intrinsic dependency relationships among these multi-scale correspondence structures. Finally, the above procedures for correspondence structure learning and multi-scale dependency modeling are implemented in a unified end-to-end deep learning framework. Experimental results on several benchmark datasets demonstrate the effectiveness of the proposed approach.
Tasks	Optical Flow Estimation
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07301v1
PDF	http://arxiv.org/pdf/1707.07301v1.pdf
PWC	https://paperswithcode.com/paper/deep-optical-flow-estimation-via-multi-scale
Repo
Framework

Human Trajectory Prediction using Spatially aware Deep Attention Models


Title	Human Trajectory Prediction using Spatially aware Deep Attention Models
Authors	Daksh Varshneya, G. Srinivasaraghavan
Abstract	Trajectory Prediction of dynamic objects is a widely studied topic in the field of artificial intelligence. Thanks to a large number of applications like predicting abnormal events, navigation system for the blind, etc. there have been many approaches to attempt learning patterns of motion directly from data using a wide variety of techniques ranging from hand-crafted features to sophisticated deep learning models for unsupervised feature learning. All these approaches have been limited by problems like inefficient features in the case of hand crafted features, large error propagation across the predicted trajectory and no information of static artefacts around the dynamic moving objects. We propose an end to end deep learning model to learn the motion patterns of humans using different navigational modes directly from data using the much popular sequence to sequence model coupled with a soft attention mechanism. We also propose a novel approach to model the static artefacts in a scene and using these to predict the dynamic trajectories. The proposed method, tested on trajectories of pedestrians, consistently outperforms previously proposed state of the art approaches on a variety of large scale data sets. We also show how our architecture can be naturally extended to handle multiple modes of movement (say pedestrians, skaters, bikers and buses) simultaneously.
Tasks	Deep Attention, Trajectory Prediction
Published	2017-05-26
URL	http://arxiv.org/abs/1705.09436v1
PDF	http://arxiv.org/pdf/1705.09436v1.pdf
PWC	https://paperswithcode.com/paper/human-trajectory-prediction-using-spatially
Repo
Framework

Context-Aware Trajectory Prediction


Title	Context-Aware Trajectory Prediction
Authors	Federico Bartoli, Giuseppe Lisanti, Lamberto Ballan, Alberto Del Bimbo
Abstract	Human motion and behaviour in crowded spaces is influenced by several factors, such as the dynamics of other moving agents in the scene, as well as the static elements that might be perceived as points of attraction or obstacles. In this work, we present a new model for human trajectory prediction which is able to take advantage of both human-human and human-space interactions. The future trajectory of humans, are generated by observing their past positions and interactions with the surroundings. To this end, we propose a “context-aware” recurrent neural network LSTM model, which can learn and predict human motion in crowded spaces such as a sidewalk, a museum or a shopping mall. We evaluate our model on a public pedestrian datasets, and we contribute a new challenging dataset that collects videos of humans that navigate in a (real) crowded space such as a big museum. Results show that our approach can predict human trajectories better when compared to previous state-of-the-art forecasting models.
Tasks	Trajectory Prediction
Published	2017-05-06
URL	http://arxiv.org/abs/1705.02503v1
PDF	http://arxiv.org/pdf/1705.02503v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-trajectory-prediction
Repo
Framework

Fast Rates for Empirical Risk Minimization of Strict Saddle Problems


Title	Fast Rates for Empirical Risk Minimization of Strict Saddle Problems
Authors	Alon Gonen, Shai Shalev-Shwartz
Abstract	We derive bounds on the sample complexity of empirical risk minimization (ERM) in the context of minimizing non-convex risks that admit the strict saddle property. Recent progress in non-convex optimization has yielded efficient algorithms for minimizing such functions. Our results imply that these efficient algorithms are statistically stable and also generalize well. In particular, we derive fast rates which resemble the bounds that are often attained in the strongly convex setting. We specify our bounds to Principal Component Analysis and Independent Component Analysis. Our results and techniques may pave the way for statistical analyses of additional strict saddle problems.
Tasks
Published	2017-01-16
URL	http://arxiv.org/abs/1701.04271v4
PDF	http://arxiv.org/pdf/1701.04271v4.pdf
PWC	https://paperswithcode.com/paper/fast-rates-for-empirical-risk-minimization-of
Repo
Framework

Word Vector Enrichment of Low Frequency Words in the Bag-of-Words Model for Short Text Multi-class Classification Problems


Title	Word Vector Enrichment of Low Frequency Words in the Bag-of-Words Model for Short Text Multi-class Classification Problems
Authors	Bradford Heap, Michael Bain, Wayne Wobcke, Alfred Krzywicki, Susanne Schmeidl
Abstract	The bag-of-words model is a standard representation of text for many linear classifier learners. In many problem domains, linear classifiers are preferred over more complex models due to their efficiency, robustness and interpretability, and the bag-of-words text representation can capture sufficient information for linear classifiers to make highly accurate predictions. However in settings where there is a large vocabulary, large variance in the frequency of terms in the training corpus, many classes and very short text (e.g., single sentences or document titles) the bag-of-words representation becomes extremely sparse, and this can reduce the accuracy of classifiers. A particular issue in such settings is that short texts tend to contain infrequently occurring or rare terms which lack class-conditional evidence. In this work we introduce a method for enriching the bag-of-words model by complementing such rare term information with related terms from both general and domain-specific Word Vector models. By reducing sparseness in the bag-of-words models, our enrichment approach achieves improved classification over several baseline classifiers in a variety of text classification problems. Our approach is also efficient because it requires no change to the linear classifier before or during training, since bag-of-words enrichment applies only to text being classified.
Tasks	Text Classification
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05778v1
PDF	http://arxiv.org/pdf/1709.05778v1.pdf
PWC	https://paperswithcode.com/paper/word-vector-enrichment-of-low-frequency-words
Repo
Framework

Transfer Learning with Label Noise


Title	Transfer Learning with Label Noise
Authors	Xiyu Yu, Tongliang Liu, Mingming Gong, Kun Zhang, Kayhan Batmanghelich, Dacheng Tao
Abstract	Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and target domains, recent methods have focused on exploring invariant representations that have similar distributions across domains. However, when learning this invariant knowledge, existing methods assume that the labels in source domain are uncontaminated, while in reality, we often have access to source data with noisy labels. In this paper, we first show how label noise adversely affect the learning of invariant representations and the correcting of label shift in various transfer learning scenarios. To reduce the adverse effects, we propose a novel Denoising Conditional Invariant Component (DCIC) framework, which provably ensures (1) extracting invariant representations given examples with noisy labels in source domain and unlabeled examples in target domain; (2) estimating the label distribution in target domain with no bias. Experimental results on both synthetic and real-world data verify the effectiveness of the proposed method.
Tasks	Denoising, Transfer Learning
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09724v2
PDF	http://arxiv.org/pdf/1707.09724v2.pdf
PWC	https://paperswithcode.com/paper/transfer-learning-with-label-noise
Repo
Framework

One Model to Rule them all: Multitask and Multilingual Modelling for Lexical Analysis


Title	One Model to Rule them all: Multitask and Multilingual Modelling for Lexical Analysis
Authors	Johannes Bjerva
Abstract	When learning a new skill, you take advantage of your preexisting skills and knowledge. For instance, if you are a skilled violinist, you will likely have an easier time learning to play cello. Similarly, when learning a new language you take advantage of the languages you already speak. For instance, if your native language is Norwegian and you decide to learn Dutch, the lexical overlap between these two languages will likely benefit your rate of language acquisition. This thesis deals with the intersection of learning multiple tasks and learning multiple languages in the context of Natural Language Processing (NLP), which can be defined as the study of computational processing of human language. Although these two types of learning may seem different on the surface, we will see that they share many similarities. The traditional approach in NLP is to consider a single task for a single language at a time. However, recent advances allow for broadening this approach, by considering data for multiple tasks and languages simultaneously. This is an important approach to explore further as the key to improving the reliability of NLP, especially for low-resource languages, is to take advantage of all relevant data whenever possible. In doing so, the hope is that in the long term, low-resource languages can benefit from the advances made in NLP which are currently to a large extent reserved for high-resource languages. This, in turn, may then have positive consequences for, e.g., language preservation, as speakers of minority languages will have a lower degree of pressure to using high-resource languages. In the short term, answering the specific research questions posed should be of use to NLP researchers working towards the same goal.
Tasks	Language Acquisition, Lexical Analysis
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01100v1
PDF	http://arxiv.org/pdf/1711.01100v1.pdf
PWC	https://paperswithcode.com/paper/one-model-to-rule-them-all-multitask-and
Repo
Framework

Gold Standard Online Debates Summaries and First Experiments Towards Automatic Summarization of Online Debate Data


Title	Gold Standard Online Debates Summaries and First Experiments Towards Automatic Summarization of Online Debate Data
Authors	Nattapong Sanchan, Ahmet Aker, Kalina Bontcheva
Abstract	Usage of online textual media is steadily increasing. Daily, more and more news stories, blog posts and scientific articles are added to the online volumes. These are all freely accessible and have been employed extensively in multiple research areas, e.g. automatic text summarization, information retrieval, information extraction, etc. Meanwhile, online debate forums have recently become popular, but have remained largely unexplored. For this reason, there are no sufficient resources of annotated debate data available for conducting research in this genre. In this paper, we collected and annotated debate data for an automatic summarization task. Similar to extractive gold standard summary generation our data contains sentences worthy to include into a summary. Five human annotators performed this task. Inter-annotator agreement, based on semantic similarity, is 36% for Cohen’s kappa and 48% for Krippendorff’s alpha. Moreover, we also implement an extractive summarization system for online debates and discuss prominent features for the task of summarizing online debate data automatically.
Tasks	Information Retrieval, Semantic Similarity, Semantic Textual Similarity, Text Summarization
Published	2017-08-15
URL	http://arxiv.org/abs/1708.04592v1
PDF	http://arxiv.org/pdf/1708.04592v1.pdf
PWC	https://paperswithcode.com/paper/gold-standard-online-debates-summaries-and
Repo
Framework

Fast PET Scan Tumor Segmentation using Superpixels, Principal Component Analysis and K-means Clustering


Title	Fast PET Scan Tumor Segmentation using Superpixels, Principal Component Analysis and K-means Clustering
Authors	Yeman B. Hagos, Vu H. Minh, Saed Khawaldeh, Usama Pervaiz, Tajwar A. Aleef
Abstract	Positron Emission Tomography scan images are extensively used in radiotherapy planning, clinical diagnosis, assessment of growth and treatment of a tumor. These all rely on fidelity and speed of detection and delineation algorithm. Despite intensive research, segmentation remained a challenging problem due to the diverse image content, resolution, shape, and noise. This paper presents a fast positron emission tomography tumor segmentation method in which superpixels are extracted first from the input image. Principal component analysis is then applied on the superpixels and also on their average. Distance vector of each superpixel from the average is computed in principal components coordinate system. Finally, k-means clustering is applied on distance vector to recognize tumor and non-tumor superpixels. The proposed approach is implemented in MATLAB 2016 which resulted in an average Dice similarity of 84.2% on the dataset. Additionally, a very fast execution time was achieved as the number of superpixels and the size of distance vector on which clustering was done was very small compared to the number of raw pixels in dataset images.
Tasks
Published	2017-10-18
URL	http://arxiv.org/abs/1710.08798v1
PDF	http://arxiv.org/pdf/1710.08798v1.pdf
PWC	https://paperswithcode.com/paper/fast-pet-scan-tumor-segmentation-using
Repo
Framework