January 30, 2020

3197 words 16 mins read

Paper Group ANR 366

Corpus-Level End-to-End Exploration for Interactive Systems. Automatic Driver Identification from In-Vehicle Network Logs. Aspect Detection using Word and Char Embeddings with (Bi)LSTM and CRF. Decentralised Multi-Demic Evolutionary Approach to the Dynamic Multi-Agent Travelling Salesman Problem. TG-PSM: Tunable Greedy Packet Sequence Morphing Base …

Corpus-Level End-to-End Exploration for Interactive Systems


Title	Corpus-Level End-to-End Exploration for Interactive Systems
Authors	Zhiwen Tang, Grace Hui Yang
Abstract	A core interest in building Artificial Intelligence (AI) agents is to let them interact with and assist humans. One example is Dynamic Search (DS), which models the process that a human works with a search engine agent to accomplish a complex and goal-oriented task. Early DS agents using Reinforcement Learning (RL) have only achieved limited success for (1) their lack of direct control over which documents to return and (2) the difficulty to recover from wrong search trajectories. In this paper, we present a novel corpus-level end-to-end exploration (CE3) method to address these issues. In our method, an entire text corpus is compressed into a global low-dimensional representation, which enables the agent to gain access to the full state and action spaces, including the under-explored areas. We also propose a new form of retrieval function, whose linear approximation allows end-to-end manipulation of documents. Experiments on the Text REtrieval Conference (TREC) Dynamic Domain (DD) Track show that CE3 outperforms the state-of-the-art DS systems.
Tasks
Published	2019-11-23
URL	https://arxiv.org/abs/1912.00753v1
PDF	https://arxiv.org/pdf/1912.00753v1.pdf
PWC	https://paperswithcode.com/paper/corpus-level-end-to-end-exploration-for
Repo
Framework

Automatic Driver Identification from In-Vehicle Network Logs


Title	Automatic Driver Identification from In-Vehicle Network Logs
Authors	Mina Remeli, Szilvia Lestyan, Gergely Acs, Gergely Biczok
Abstract	Data generated by cars is growing at an unprecedented scale. As cars gradually become part of the Internet of Things (IoT) ecosystem, several stakeholders discover the value of in-vehicle network logs containing the measurements of the multitude of sensors deployed within the car. This wealth of data is also expected to be exploitable by third parties for the purpose of profiling drivers in order to provide personalized, valueadded services. Although several prior works have successfully demonstrated the feasibility of driver re-identification using the in-vehicle network data captured on the vehicle’s CAN (Controller Area Network) bus, they inferred the identity of the driver only from known sensor signals (such as the vehicle’s speed, brake pedal position, steering wheel angle, etc.) extracted from the CAN messages. However, car manufacturers intentionally do not reveal exact signal location and semantics within CAN logs. We show that the inference of driver identity is possible even with off-the-shelf machine learning techniques without reverse-engineering the CAN protocol. We demonstrate our approach on a dataset of 33 drivers and show that a driver can be re-identified and distinguished from other drivers with an accuracy of 75-85%.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1911.09508v1
PDF	https://arxiv.org/pdf/1911.09508v1.pdf
PWC	https://paperswithcode.com/paper/automatic-driver-identification-from-in
Repo
Framework

Aspect Detection using Word and Char Embeddings with (Bi)LSTM and CRF


Title	Aspect Detection using Word and Char Embeddings with (Bi)LSTM and CRF
Authors	Łukasz Augustyniak, Tomasz Kajdanowicz, Przemysław Kazienko
Abstract	We proposed a~new accurate aspect extraction method that makes use of both word and character-based embeddings. We have conducted experiments of various models of aspect extraction using LSTM and BiLSTM including CRF enhancement on five different pre-trained word embeddings extended with character embeddings. The results revealed that BiLSTM outperforms regular LSTM, but also word embedding coverage in train and test sets profoundly impacted aspect detection performance. Moreover, the additional CRF layer consistently improves the results across different models and text embeddings. Summing up, we obtained state-of-the-art F-score results for SemEval Restaurants (85%) and Laptops (80%).
Tasks	Aspect Extraction, Word Embeddings
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01276v1
PDF	https://arxiv.org/pdf/1909.01276v1.pdf
PWC	https://paperswithcode.com/paper/aspect-detection-using-word-and-char
Repo
Framework

Decentralised Multi-Demic Evolutionary Approach to the Dynamic Multi-Agent Travelling Salesman Problem


Title	Decentralised Multi-Demic Evolutionary Approach to the Dynamic Multi-Agent Travelling Salesman Problem
Authors	Thomas E. Kent, Arthur G. Richards
Abstract	The Travelling Salesman and its variations are some of the most well known NP hard optimisation problems. This paper looks to use both centralised and decentralised implementations of Evolutionary Algorithms (EA) to solve a dynamic variant of the Multi-Agent Travelling Salesman Problem (MATSP). The problem is dynamic, requiring an on-line solution, whereby tasks are completed during simulation with new tasks added and completed ones removed. The problem is allocating an active set of tasks to a set of agents whilst simultaneously planning the route for each agent. The allocation and routing are closely coupled parts of the same problem making it difficult to decompose, instead this paper uses multiple populations with well defined interactions to exploit the problem structure. This work attempts to align the real world implementation demands of a decentralised solution, where agents are far apart and have communication limits, to that of the structure of the multi-demic EA solution process, ultimately allowing decentralised parts of the problem to be solved `on board’ agents and allow for robust communication and exchange of tasks. \|
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05616v1
PDF	https://arxiv.org/pdf/1906.05616v1.pdf
PWC	https://paperswithcode.com/paper/decentralised-multi-demic-evolutionary
Repo
Framework

TG-PSM: Tunable Greedy Packet Sequence Morphing Based on Trace Clustering


Title	TG-PSM: Tunable Greedy Packet Sequence Morphing Based on Trace Clustering
Authors	Farzam Fanitabasi
Abstract	Common privacy enhancing technologies fail to effectively hide certain statistical aspects of encrypted traffic, namely individual packets length, packets direction and, packets timing. Recent researches have shown that using such attributes, an adversary is able to extract various information from the encrypted traffic such as the visited website and used protocol. Such attacks are called traffic analysis. Proposed countermeasures attempt to change the distribution of such features. however, either they fail to effectively reduce attacker’s accuracy or do so while enforcing high bandwidth overhead and timing delay. In this paper, through the use of a predefined set of clustered traces of websites and a greedy packet morphing algorithm, we introduce a website fingerprinting countermeasure called TG-PSM. Firstly, this method clusters websites based on their behavior in different phases of loading. Secondly, it finds a suitable target site for any visiting website based on user indicated importance degree; thus providing dynamic tunability. Thirdly, this method morphs the given website to the target website using a greedy algorithm considering the distance and the resulted overhead. Our evaluations show that TG-PSM outperforms previous countermeasures regarding attacker accuracy reduction and enforced bandwidth, e.g., reducing bandwidth overhead over 40% while maintaining attacker’s accuracy.
Tasks
Published	2019-04-01
URL	http://arxiv.org/abs/1904.05738v1
PDF	http://arxiv.org/pdf/1904.05738v1.pdf
PWC	https://paperswithcode.com/paper/tg-psm-tunable-greedy-packet-sequence
Repo
Framework

High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processors


Title	High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processors
Authors	Siqi Wang, Gayathri Ananthanarayanan, Yifan Zeng, Neeraj Goel, Anuj Pathania, Tulika Mitra
Abstract	IoT Edge intelligence requires Convolutional Neural Network (CNN) inference to take place in the edge devices itself. ARM big.LITTLE architecture is at the heart of prevalent commercial edge devices. It comprises of single-ISA heterogeneous cores grouped into multiple homogeneous clusters that enable power and performance trade-offs. All cores are expected to be simultaneously employed in inference to attain maximal throughput. However, high communication overhead involved in parallelization of computations from convolution kernels across clusters is detrimental to throughput. We present an alternative framework called Pipe-it that employs pipelined design to split convolutional layers across clusters while limiting parallelization of their respective kernels to the assigned cluster. We develop a performance-prediction model that utilizes only the convolutional layer descriptors to predict the execution time of each layer individually on all permitted core configurations (type and count). Pipe-it then exploits the predictions to create a balanced pipeline using an efficient design space exploration algorithm. Pipe-it on average results in a 39% higher throughput than the highest antecedent throughput.
Tasks
Published	2019-03-14
URL	https://arxiv.org/abs/1903.05898v3
PDF	https://arxiv.org/pdf/1903.05898v3.pdf
PWC	https://paperswithcode.com/paper/high-throughput-cnn-inference-on-embedded-arm
Repo
Framework

Emergence of functional and structural properties of the head direction system by optimization of recurrent neural networks


Title	Emergence of functional and structural properties of the head direction system by optimization of recurrent neural networks
Authors	Christopher J. Cueva, Peter Y. Wang, Matthew Chin, Xue-Xin Wei
Abstract	Recent work suggests goal-driven training of neural networks can be used to model neural activity in the brain. While response properties of neurons in artificial neural networks bear similarities to those in the brain, the network architectures are often constrained to be different. Here we ask if a neural network can recover both neural representations and, if the architecture is unconstrained and optimized, the anatomical properties of neural circuits. We demonstrate this in a system where the connectivity and the functional organization have been characterized, namely, the head direction circuits of the rodent and fruit fly. We trained recurrent neural networks (RNNs) to estimate head direction through integration of angular velocity. We found that the two distinct classes of neurons observed in the head direction system, the Ring neurons and the Shifter neurons, emerged naturally in artificial neural networks as a result of training. Furthermore, connectivity analysis and in-silico neurophysiology revealed structural and mechanistic similarities between artificial networks and the head direction system. Overall, our results show that optimization of RNNs in a goal-driven task can recapitulate the structure and function of biological circuits, suggesting that artificial neural networks can be used to study the brain at the level of both neural activity and anatomical organization.
Tasks
Published	2019-12-21
URL	https://arxiv.org/abs/1912.10189v1
PDF	https://arxiv.org/pdf/1912.10189v1.pdf
PWC	https://paperswithcode.com/paper/emergence-of-functional-and-structural-1
Repo
Framework

A Study of Data Pre-processing Techniques for Imbalanced Biomedical Data Classification


Title	A Study of Data Pre-processing Techniques for Imbalanced Biomedical Data Classification
Authors	Shigang Liu, Jun Zhang, Yang Xiang, Wanlei Zhou, Dongxi Xiang
Abstract	Biomedical data are widely accepted in developing prediction models for identifying a specific tumor, drug discovery and classification of human cancers. However, previous studies usually focused on different classifiers, and overlook the class imbalance problem in real-world biomedical datasets. There are a lack of studies on evaluation of data pre-processing techniques, such as resampling and feature selection, on imbalanced biomedical data learning. The relationship between data pre-processing techniques and the data distributions has never been analysed in previous studies. This article mainly focuses on reviewing and evaluating some popular and recently developed resampling and feature selection methods for class imbalance learning. We analyse the effectiveness of each technique from data distribution perspective. Extensive experiments have been done based on five classifiers, four performance measures, eight learning techniques across twenty real-world datasets. Experimental results show that: (1) resampling and feature selection techniques exhibit better performance using support vector machine (SVM) classifier. However, resampling and Feature Selection techniques perform poorly when using C4.5 decision tree and Linear discriminant analysis classifiers; (2) for datasets with different distributions, techniques such as Random undersampling and Feature Selection perform better than other data pre-processing methods with T Location-Scale distribution when using SVM and KNN (K-nearest neighbours) classifiers. Random oversampling outperforms other methods on Negative Binomial distribution using Random Forest classifier with lower level of imbalance ratio; (3) Feature Selection outperforms other data pre-processing methods in most cases, thus, Feature Selection with SVM classifier is the best choice for imbalanced biomedical data learning.
Tasks	Drug Discovery, Feature Selection
Published	2019-11-04
URL	https://arxiv.org/abs/1911.00996v1
PDF	https://arxiv.org/pdf/1911.00996v1.pdf
PWC	https://paperswithcode.com/paper/a-study-of-data-pre-processing-techniques-for
Repo
Framework

Tackling Climate Change with Machine Learning


Title	Tackling Climate Change with Machine Learning
Authors	David Rolnick, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, Nikola Milojevic-Dupont, Natasha Jaques, Anna Waldman-Brown, Alexandra Luccioni, Tegan Maharaj, Evan D. Sherwin, S. Karthik Mukkavilli, Konrad P. Kording, Carla Gomes, Andrew Y. Ng, Demis Hassabis, John C. Platt, Felix Creutzig, Jennifer Chayes, Yoshua Bengio
Abstract	Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.05433v2
PDF	https://arxiv.org/pdf/1906.05433v2.pdf
PWC	https://paperswithcode.com/paper/tackling-climate-change-with-machine-learning
Repo
Framework

Video Depth Estimation by Fusing Flow-to-Depth Proposals


Title	Video Depth Estimation by Fusing Flow-to-Depth Proposals
Authors	Jiaxin Xie, Chenyang Lei, Zhuwen Li, Li Erran Li, Qifeng Chen
Abstract	Depth from a monocular video can enable billions of devices and robots with a single camera to see the world in 3D. In this paper, we present an approach with a differentiable flow-to-depth layer for video depth estimation. The model consists of a flow-to-depth layer, a camera pose refinement module, and a depth fusion network. Given optical flow and camera pose, our flow-to-depth layer generates depth proposals and the corresponding confidence maps by explicitly solving an epipolar geometry optimization problem. Our flow-to-depth layer is differentiable, and thus we can refine camera poses by maximizing the aggregated confidence in the camera pose refinement module. Our depth fusion network can utilize depth proposals and their confidence maps inferred from different adjacent frames to produce the final depth map. Furthermore, the depth fusion network can additionally take the depth proposals generated by other methods to improve the results further. The experiments on three public datasets show that our approach outperforms state-of-the-art depth estimation methods, and has reasonable cross dataset generalization capability: our model trained on KITTI still performs well on the unseen Waymo dataset.
Tasks	Depth Estimation, Optical Flow Estimation
Published	2019-12-30
URL	https://arxiv.org/abs/1912.12874v2
PDF	https://arxiv.org/pdf/1912.12874v2.pdf
PWC	https://paperswithcode.com/paper/video-depth-estimation-by-fusing-flow-to
Repo
Framework

Path Design for Cellular-Connected UAV with Reinforcement Learning


Title	Path Design for Cellular-Connected UAV with Reinforcement Learning
Authors	Yong Zeng, Xiaoli Xu
Abstract	This paper studies the path design problem for cellular-connected unmanned aerial vehicle (UAV), which aims to minimize its mission completion time while maintaining good connectivity with the cellular network. We first argue that the conventional path design approach via formulating and solving optimization problems faces several practical challenges, and then propose a new reinforcement learning-based UAV path design algorithm by applying \emph{temporal-difference} method to directly learn the \emph{state-value function} of the corresponding Markov Decision Process. The proposed algorithm is further extended by using linear function approximation with tile coding to deal with large state space. The proposed algorithms only require the raw measured or simulation-generated signal strength as the input and are suitable for both online and offline implementations. Numerical results show that the proposed path designs can successfully avoid the coverage holes of cellular networks even in the complex urban environment.
Tasks
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03440v1
PDF	https://arxiv.org/pdf/1905.03440v1.pdf
PWC	https://paperswithcode.com/paper/190503440
Repo
Framework

A deep learning based tool for automatic brain extraction from functional magnetic resonance images in rodents


Title	A deep learning based tool for automatic brain extraction from functional magnetic resonance images in rodents
Authors	Sidney Pontes-Filho, Annelene Gulden Dahl, Stefano Nichele, Gustavo Borges Moreno e Mello
Abstract	Removing skull artifacts from functional magnetic images (fMRI) is a well understood and frequently encountered problem. Because the fMRI field has grown mostly due to human studies, many new tools were developed to handle human data. Nonetheless, these tools are not equally useful to handle the data derived from animal studies, especially from rodents. This represents a major problem to the field because rodent studies generate larger datasets from larger populations, which implies that preprocessing these images manually to remove the skull becomes a bottleneck in the data analysis pipeline. In this study, we address this problem by implementing a neural network based method that uses a U-Net architecture to segment the brain area into a mask and removing the skull and other tissues from the image. We demonstrate several strategies to speed up the process of generating the training dataset using watershedding and several strategies for data augmentation that allowed to train faster the U-Net to perform the segmentation. Finally, we deployed the trained network freely available.
Tasks	Data Augmentation
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01359v2
PDF	https://arxiv.org/pdf/1912.01359v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-based-tool-for-automatic
Repo
Framework

The Five Elements of Flow


Title	The Five Elements of Flow
Authors	Markus Hofinger, Samuel Rota Bulò, Lorenzo Porzi, Arno Knapitsch, Thomas Pock, Peter Kontschieder
Abstract	In this work we propose five concrete steps to improve the performance of optical flow algorithms. We carefully reviewed recently introduced innovations and well-established techniques in deep learning-based flow methods including i) pyramidal feature representations, ii) flow-based consistency checks, iii) cost volume construction practices or iv) distillation, and present extensions or alternatives to inhibiting factors we identified therein. We also show how changing the way gradients propagate in modern flow networks can lead to surprising boosts in performance. Finally, we contribute a novel feature that adaptively guides the learning process towards improving on under-performing flow predictions. Our findings are conceptually simple and easy to implement, yet result in compelling improvements on relevant error measures that we demonstrate via exhaustive ablations on datasets like Flying Chairs2, Flying Things, Sintel and KITTI. We establish new state-of-the-art results on the challenging Sintel and Kitti 2015 test datasets, and even show the portability of our findings to different optical flow and depth from stereo approaches.
Tasks	Optical Flow Estimation
Published	2019-12-23
URL	https://arxiv.org/abs/1912.10739v1
PDF	https://arxiv.org/pdf/1912.10739v1.pdf
PWC	https://paperswithcode.com/paper/the-five-elements-of-flow
Repo
Framework

Modeling Conversation Structure and Temporal Dynamics for Jointly Predicting Rumor Stance and Veracity


Title	Modeling Conversation Structure and Temporal Dynamics for Jointly Predicting Rumor Stance and Veracity
Authors	Penghui Wei, Nan Xu, Wenji Mao
Abstract	Automatically verifying rumorous information has become an important and challenging task in natural language processing and social media analytics. Previous studies reveal that people’s stances towards rumorous messages can provide indicative clues for identifying the veracity of rumors, and thus determining the stances of public reactions is a crucial preceding step for rumor veracity prediction. In this paper, we propose a hierarchical multi-task learning framework for jointly predicting rumor stance and veracity on Twitter, which consists of two components. The bottom component of our framework classifies the stances of tweets in a conversation discussing a rumor via modeling the structural property based on a novel graph convolutional network. The top component predicts the rumor veracity by exploiting the temporal dynamics of stance evolution. Experimental results on two benchmark datasets show that our method outperforms previous methods in both rumor stance classification and veracity prediction.
Tasks	Multi-Task Learning
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08211v1
PDF	https://arxiv.org/pdf/1909.08211v1.pdf
PWC	https://paperswithcode.com/paper/modeling-conversation-structure-and-temporal
Repo
Framework

ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization


Title	ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization
Authors	Felix Ott, Tobias Feigl, Christoffer Löffler, Christopher Mutschler
Abstract	Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of features, and poor textures or visual information. While recent approaches estimate a 6DoF pose either directly from (a series of) images or by merging depth maps with the optical flow (OF), research that combines absolute pose regression with OF is limited. We propose ViPR, a novel architecture for long-term 6DoF VO that leverages synergies between absolute pose estimates (from PoseNet-like architectures) and relative pose estimates (from FlowNet-based architectures) by combining both through recurrent layers. Experiments with known publicly available datasets and with our own Industry dataset show that our novel design outperforms existing techniques in long-term navigation tasks.
Tasks	Camera Localization, Optical Flow Estimation, Robot Navigation, Visual Odometry
Published	2019-12-17
URL	https://arxiv.org/abs/1912.08263v2
PDF	https://arxiv.org/pdf/1912.08263v2.pdf
PWC	https://paperswithcode.com/paper/vipr-visual-odometry-aided-pose-regression
Repo
Framework