January 28, 2020

3303 words 16 mins read

Paper Group ANR 840

Analysis of Chinese Tourists in Japan by Text Mining of a Hotel Portal Site. Spatial and Temporal Consistency-Aware Dynamic Adaptive Streaming for 360-Degree Videos. Eigen Artificial Neural Networks. Data Poisoning Attacks on Stochastic Bandits. Regularization Shortcomings for Continual Learning. Sensor Fusion for Joint 3D Object Detection and Sema …

Analysis of Chinese Tourists in Japan by Text Mining of a Hotel Portal Site


Title	Analysis of Chinese Tourists in Japan by Text Mining of a Hotel Portal Site
Authors	Elisa Claire Alemán Carreón, Hirofumi Nonaka, Toru Hiraoka
Abstract	With an increasingly large number of Chinese tourists in Japan, the hotel industry is in need of an affordable market research tool that does not rely on expensive and time-consuming surveys or interviews. Because this problem is real and relevant to the hotel industry in Japan, and otherwise completely unexplored in other studies, we have extracted a list of potential keywords from Chinese reviews of Japanese hotels in the hotel portal site Ctrip1 using a mathematical model to then use them in a sentiment analysis with a machine learning classifier. While most studies that use information collected from the internet use pre-existing data analysis tools, in our study, we designed the mathematical model to have the highest possible performing results in classification, while also exploring on the potential business implications these may have.
Tasks	Sentiment Analysis
Published	2019-04-24
URL	http://arxiv.org/abs/1904.13214v2
PDF	http://arxiv.org/pdf/1904.13214v2.pdf
PWC	https://paperswithcode.com/paper/190413214
Repo
Framework

Spatial and Temporal Consistency-Aware Dynamic Adaptive Streaming for 360-Degree Videos


Title	Spatial and Temporal Consistency-Aware Dynamic Adaptive Streaming for 360-Degree Videos
Authors	Hui Yuan, Shiyun Zhao, Junhui Hou, Xuekai Wei, Sam Kwong
Abstract	The 360-degree video allows users to enjoy the whole scene by interactively switching viewports. However, the huge data volume of the 360-degree video limits its remote applications via network. To provide high quality of experience (QoE) for remote web users, this paper presents a tile-based adaptive streaming method for 360-degree videos. First, we propose a simple yet effective rate adaptation algorithm to determine the requested bitrate for downloading the current video segment by considering the balance between the buffer length and video quality. Then, we propose to use a Gaussian model to predict the field of view at the beginning of each requested video segment. To deal with the circumstance that the view angle is switched during the display of a video segment, we propose to download all the tiles in the 360-degree video with different priorities based on a Zipf model. Finally, in order to allocate bitrates for all the tiles, a two-stage optimization algorithm is proposed to preserve the quality of tiles in FoV and guarantee the spatial and temporal smoothness. Experimental results demonstrate the effectiveness and advantage of the proposed method compared with the state-of-the-art methods. That is, our method preserves both the quality and the smoothness of tiles in FoV, thus providing the best QoE for users.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09675v1
PDF	https://arxiv.org/pdf/1912.09675v1.pdf
PWC	https://paperswithcode.com/paper/spatial-and-temporal-consistency-aware
Repo
Framework

Eigen Artificial Neural Networks


Title	Eigen Artificial Neural Networks
Authors	Francisco Yepes Barrera
Abstract	This work has its origin in intuitive physical and statistical considerations. The problem of optimizing an artificial neural network is treated as a physical system, composed of a conservative vector force field. The derived scalar potential is a measure of the potential energy of the network, a function of the distance between predictions and targets. Starting from some analogies with wave mechanics, the description of the system is justified with an eigenvalue equation that is a variant of the Schr~odinger equation, in which the potential is defined by the mutual information between inputs and targets. The weights and parameters of the network, as well as those of the state function, are varied so as to minimize energy, using an equivalent of the variational theorem of wave mechanics. The minimum energy thus obtained implies the principle of minimum mutual information (MinMI). We also propose a definition of the potential work produced by the force field to bring a network from an arbitrary probability distribution to the potential-constrained system, which allows to establish a measure of the complexity of the system. At the end of the discussion we expose a recursive procedure that allows to refine the state function and bypass some initial assumptions, as well as a discussion of some topics in quantum mechanics applied to the formalism, such as the uncertainty principle and the temporal evolution of the system. Results demonstrate how the minimization of energy effectively leads to a decrease in the average error between network predictions and targets.
Tasks
Published	2019-05-22
URL	https://arxiv.org/abs/1907.05200v3
PDF	https://arxiv.org/pdf/1907.05200v3.pdf
PWC	https://paperswithcode.com/paper/eigen-artificial-neural-networks
Repo
Framework

Data Poisoning Attacks on Stochastic Bandits


Title	Data Poisoning Attacks on Stochastic Bandits
Authors	Fang Liu, Ness Shroff
Abstract	Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks against these learning algorithms may hijack their behavior, causing catastrophic loss in real-world applications, little is known about adversarial attacks on bandit algorithms. In this paper, we propose a framework of offline attacks on bandit algorithms and study convex optimization based attacks on several popular bandit algorithms. We show that the attacker can force the bandit algorithm to pull a target arm with high probability by a slight manipulation of the rewards in the data. Then we study a form of online attacks on bandit algorithms and propose an adaptive attack strategy against any bandit algorithm without the knowledge of the bandit algorithm. Our adaptive attack strategy can hijack the behavior of the bandit algorithm to suffer a linear regret with only a logarithmic cost to the attacker. Our results demonstrate a significant security threat to stochastic bandits.
Tasks	data poisoning, Multi-Armed Bandits, Recommendation Systems
Published	2019-05-16
URL	https://arxiv.org/abs/1905.06494v1
PDF	https://arxiv.org/pdf/1905.06494v1.pdf
PWC	https://paperswithcode.com/paper/data-poisoning-attacks-on-stochastic-bandits
Repo
Framework

Regularization Shortcomings for Continual Learning


Title	Regularization Shortcomings for Continual Learning
Authors	Timothée Lesort, Andrei Stoian, David Filliat
Abstract	In most machine learning algorithms, training data are assumed independent and identically distributed (iid). Otherwise, the algorithms’ performances are challenged. A famous phenomenon with non-iid data distribution is known as \say{catastrophic forgetting}. Algorithms dealing with it are gathered in the \textit{Continual Learning} research field. In this article, we study the \textit{regularization} based approaches to continual learning. We show that those approaches can not learn to discriminate classes from different tasks in an elemental continual benchmark: class-incremental setting. We make theoretical reasoning to prove this shortcoming and illustrate it with examples and experiments.
Tasks	Continual Learning, Multi-Task Learning
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03049v2
PDF	https://arxiv.org/pdf/1912.03049v2.pdf
PWC	https://paperswithcode.com/paper/regularization-shortcomings-for-continual
Repo
Framework

Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation


Title	Sensor Fusion for Joint 3D Object Detection and Semantic Segmentation
Authors	Gregory P. Meyer, Jake Charland, Darshan Hegde, Ankit Laddha, Carlos Vallespi-Gonzalez
Abstract	In this paper, we present an extension to LaserNet, an efficient and state-of-the-art LiDAR based 3D object detector. We propose a method for fusing image data with the LiDAR data and show that this sensor fusion method improves the detection performance of the model especially at long ranges. The addition of image data is straightforward and does not require image labels. Furthermore, we expand the capabilities of the model to perform 3D semantic segmentation in addition to 3D object detection. On a large benchmark dataset, we demonstrate our approach achieves state-of-the-art performance on both object detection and semantic segmentation while maintaining a low runtime.
Tasks	3D Object Detection, 3D Semantic Segmentation, Object Detection, Semantic Segmentation, Sensor Fusion
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11466v1
PDF	http://arxiv.org/pdf/1904.11466v1.pdf
PWC	https://paperswithcode.com/paper/sensor-fusion-for-joint-3d-object-detection
Repo
Framework

Adaptive Online Planning for Continual Lifelong Learning


Title	Adaptive Online Planning for Continual Lifelong Learning
Authors	Kevin Lu, Igor Mordatch, Pieter Abbeel
Abstract	We study learning control in an online lifelong learning scenario, where mistakes can compound catastrophically into the future and the underlying dynamics of the environment may change. Traditional model-free policy learning methods have achieved successes in difficult tasks due to their broad flexibility, and capably condense broad experiences into compact networks, but struggle in this setting, as they can activate failure modes early in their lifetimes which are difficult to recover from and face performance degradation as dynamics change. On the other hand, model-based planning methods learn and adapt quickly, but require prohibitive levels of computational resources. Under constrained computation limits, the agent must allocate its resources wisely, which requires the agent to understand both its own performance and the current state of the environment: knowing that its mastery over control in the current dynamics is poor, the agent should dedicate more time to planning. We present a new algorithm, Adaptive Online Planning (AOP), that achieves strong performance in this setting by combining model-based planning with model-free learning. By measuring the performance of the planner and the uncertainty of the model-free components, AOP is able to call upon more extensive planning only when necessary, leading to reduced computation times. We show that AOP gracefully deals with novel situations, adapting behaviors and policies effectively in the face of unpredictable changes in the world – challenges that a continual learning agent naturally faces over an extended lifetime – even when traditional reinforcement learning methods fail.
Tasks	Continual Learning
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01188v1
PDF	https://arxiv.org/pdf/1912.01188v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-online-planning-for-continual-1
Repo
Framework

Overcoming Catastrophic Forgetting by Generative Regularization


Title	Overcoming Catastrophic Forgetting by Generative Regularization
Authors	Patrick H. Chen, Wei Wei, Cho-jui Hsieh, Bo Dai
Abstract	In this paper, we propose a new method to overcome catastrophic forgetting by adding generative regularization to Bayesian inference framework. Bayesian method provides a general framework for continual learning. We could further construct a generative regularization term for all given classification models by leveraging energy-based models and Langevin-dynamic sampling to enrich the features learned in each task. By combining discriminative and generative loss together, we empirically show that the proposed method outperforms state-of-the-art methods on a variety of tasks, avoiding catastrophic forgetting in continual learning. In particular, the proposed method outperforms baseline methods over 15% on the Fashion-MNIST dataset and 10% on the CUB dataset
Tasks	Bayesian Inference, Continual Learning
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01238v2
PDF	https://arxiv.org/pdf/1912.01238v2.pdf
PWC	https://paperswithcode.com/paper/overcoming-catastrophic-forgetting-by-2
Repo
Framework

Aspect and Opinion Term Extraction for Aspect Based Sentiment Analysis of Hotel Reviews Using Transfer Learning


Title	Aspect and Opinion Term Extraction for Aspect Based Sentiment Analysis of Hotel Reviews Using Transfer Learning
Authors	Ali Akbar Septiandri, Arie Pratama Sutiono
Abstract	One of the tasks in aspect-based sentiment analysis is to extract aspect and opinion terms from review text. Our study focuses on evaluating transfer learning using BERT (Devlin et al., 2019) to classify tokens from hotel reviews in bahasa Indonesia. We show that the default BERT model failed to outperform a simple argmax method. However, changing the default BERT tokenizer to our custom one can improve the F1 scores on our labels of interest by at least 5%. For I-ASPECT and B-SENTIMENT, it can even increased the F1 scores by 11%. On entity-level evaluation, our tweak on the tokenizer can achieve F1 scores of 87% and 89% for ASPECT and SENTIMENT labels respectively. These scores are only 2% away from the best model by Fernando et al. (2019), but with much less training effort (8 vs 200 epochs).
Tasks	Aspect-Based Sentiment Analysis, Extract Aspect, Sentiment Analysis, Transfer Learning
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11879v4
PDF	https://arxiv.org/pdf/1909.11879v4.pdf
PWC	https://paperswithcode.com/paper/aspect-and-opinion-term-extraction-for-aspect
Repo
Framework

Improving Multi-Word Entity Recognition for Biomedical Texts


Title	Improving Multi-Word Entity Recognition for Biomedical Texts
Authors	Hamada A. Nayel, H. L. Shashirekha, Hiroyuki Shindo, Yuji Matsumoto
Abstract	Biomedical Named Entity Recognition (BioNER) is a crucial step for analyzing Biomedical texts, which aims at extracting biomedical named entities from a given text. Different supervised machine learning algorithms have been applied for BioNER by various researchers. The main requirement of these approaches is an annotated dataset used for learning the parameters of machine learning algorithms. Segment Representation (SR) models comprise of different tag sets used for representing the annotated data, such as IOB2, IOE2 and IOBES. In this paper, we propose an extension of IOBES model to improve the performance of BioNER. The proposed SR model, FROBES, improves the representation of multi-word entities. We used Bidirectional Long Short-Term Memory (BiLSTM) network; an instance of Recurrent Neural Networks (RNN), to design a baseline system for BioNER and evaluated the new SR model on two datasets, i2b2/VA 2010 challenge dataset and JNLPBA 2004 shared task dataset. The proposed SR model outperforms other models for multi-word entities with length greater than two. Further, the outputs of different SR models have been combined using majority voting ensemble method which outperforms the baseline models performance.
Tasks	Named Entity Recognition
Published	2019-08-15
URL	https://arxiv.org/abs/1908.05691v1
PDF	https://arxiv.org/pdf/1908.05691v1.pdf
PWC	https://paperswithcode.com/paper/improving-multi-word-entity-recognition-for
Repo
Framework

ROSA: Robust Salient Object Detection against Adversarial Attacks


Title	ROSA: Robust Salient Object Detection against Adversarial Attacks
Authors	Haofeng Li, Guanbin Li, Yizhou Yu
Abstract	Recently salient object detection has witnessed remarkable improvement owing to the deep convolutional neural networks which can harvest powerful features for images. In particular, state-of-the-art salient object detection methods enjoy high accuracy and efficiency from fully convolutional network (FCN) based frameworks which are trained from end to end and predict pixel-wise labels. However, such framework suffers from adversarial attacks which confuse neural networks via adding quasi-imperceptible noises to input images without changing the ground truth annotated by human subjects. To our knowledge, this paper is the first one that mounts successful adversarial attacks on salient object detection models and verifies that adversarial samples are effective on a wide range of existing methods. Furthermore, this paper proposes a novel end-to-end trainable framework to enhance the robustness for arbitrary FCN-based salient object detection models against adversarial attacks. The proposed framework adopts a novel idea that first introduces some new generic noise to destroy adversarial perturbations, and then learns to predict saliency maps for input images with the introduced noise. Specifically, our proposed method consists of a segment-wise shielding component, which preserves boundaries and destroys delicate adversarial noise patterns and a context-aware restoration component, which refines saliency maps through global contrast modeling. Experimental results suggest that our proposed framework improves the performance significantly for state-of-the-art models on a series of datasets.
Tasks	Object Detection, Salient Object Detection
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03434v1
PDF	https://arxiv.org/pdf/1905.03434v1.pdf
PWC	https://paperswithcode.com/paper/190503434
Repo
Framework

Mathematical decisions and non-causal elements of explainable AI


Title	Mathematical decisions and non-causal elements of explainable AI
Authors	Atoosa Kasirzadeh
Abstract	The social implications of algorithmic decision-making in sensitive contexts have generated lively debates among multiple stakeholders, such as moral and political philosophers, computer scientists, and the public. Yet, the lack of a common language and a conceptual framework for an appropriate bridging of the moral, technical, and political aspects of the debate prevents the discussion to be as effective as it can be. Social scientists and psychologists are contributing to this debate by gathering a wealth of empirical data, yet a philosophical analysis of the social implications of algorithmic decision-making remains comparatively impoverished. In attempting to address this lacuna, this paper argues that a hierarchy of different types of explanations for why and how an algorithmic decision outcome is achieved can establish the relevant connection between the moral and technical aspects of algorithmic decision-making. In particular, I offer a multi-faceted conceptual framework for the explanations and the interpretations of algorithmic decisions, and I claim that this framework can lay the groundwork for a focused discussion among multiple stakeholders about the social implications of algorithmic decision-making, as well as AI governance and ethics more generally.
Tasks	Decision Making
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13607v2
PDF	https://arxiv.org/pdf/1910.13607v2.pdf
PWC	https://paperswithcode.com/paper/mathematical-decisions-and-non-causal
Repo
Framework

Progressive LiDAR Adaptation for Road Detection


Title	Progressive LiDAR Adaptation for Road Detection
Authors	Zhe Chen, Jing Zhang, Dacheng Tao
Abstract	Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection, because LiDAR data is less susceptible to visual noises. However, the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit the benefits of LiDAR information for road detection. To overcome this issue, we introduce a novel Progressive LiDAR Adaptation-aided Road Detection (PLARD) approach to adapt LiDAR information into visual image-based road detection and improve detection performance. In PLARD, progressive LiDAR adaptation consists of two subsequent modules: 1) data space adaptation, which transforms the LiDAR data to the visual data space to align with the perspective view by applying altitude difference-based transformation; and 2) feature space adaptation, which adapts LiDAR features to visual features through a cascaded fusion structure. Comprehensive empirical studies on the well-known KITTI road detection benchmark demonstrate that PLARD takes advantage of both the visual and LiDAR information, achieving much more robust road detection even in challenging urban scenes. In particular, PLARD outperforms other state-of-the-art road detection models and is currently top of the publicly accessible benchmark leader-board.
Tasks
Published	2019-04-02
URL	http://arxiv.org/abs/1904.01206v1
PDF	http://arxiv.org/pdf/1904.01206v1.pdf
PWC	https://paperswithcode.com/paper/progressive-lidar-adaptation-for-road
Repo
Framework

Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis


Title	Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis
Authors	Mengting Hu, Shiwan Zhao, Honglei Guo, Renhong Cheng, Zhong Su
Abstract	Aspect-based sentiment analysis (ABSA) is to predict the sentiment polarity towards a particular aspect in a sentence. Recently, this task has been widely addressed by the neural attention mechanism, which computes attention weights to softly select words for generating aspect-specific sentence representations. The attention is expected to concentrate on opinion words for accurate sentiment prediction. However, attention is prone to be distracted by noisy or misleading words, or opinion words from other aspects. In this paper, we propose an alternative hard-selection approach, which determines the start and end positions of the opinion snippet, and selects the words between these two positions for sentiment prediction. Specifically, we learn deep associations between the sentence and aspect, and the long-term dependencies within the sentence by leveraging the pre-trained BERT model. We further detect the opinion snippet by self-critical reinforcement learning. Especially, experimental results demonstrate the effectiveness of our method and prove that our hard-selection approach outperforms soft-selection approaches when handling multi-aspect sentences.
Tasks	Aspect-Based Sentiment Analysis, Sentiment Analysis
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11297v1
PDF	https://arxiv.org/pdf/1909.11297v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-detect-opinion-snippet-for-aspect
Repo
Framework

CruzAffect at AffCon 2019 Shared Task: A feature-rich approach to characterize happiness


Title	CruzAffect at AffCon 2019 Shared Task: A feature-rich approach to characterize happiness
Authors	Jiaqi Wu, Ryan Compton, Geetanjali Rakshit, Marilyn Walker, Pranav Anand, Steve Whittaker
Abstract	We present our system, CruzAffect, for the CL-Aff Shared Task 2019. CruzAffect consists of several types of robust and efficient models for affective classification tasks. We utilize both traditional classifiers, such as XGBoosted Forest, as well as a deep learning Convolutional Neural Networks (CNN) classifier. We explore rich feature sets such as syntactic features, emotional features, and profile features, and utilize several sentiment lexicons, to discover essential indicators of social involvement and control that a subject might exercise in their happy moments, as described in textual snippets from the HappyDB database. The data comes with a labeled set (10K), and a larger unlabeled set (70K). We therefore use supervised methods on the 10K dataset, and a bootstrapped semi-supervised approach for the 70K. We evaluate these models for binary classification of agency and social labels (Task 1), as well as multi-class prediction for concepts labels (Task 2). We obtain promising results on the held-out data, suggesting that the proposed feature sets effectively represent the data for affective classification tasks. We also build concepts models that discover general themes recurring in happy moments. Our results indicate that generic characteristics are shared between the classes of agency, social and concepts, suggesting it should be possible to build general models for affective classification tasks.
Tasks
Published	2019-02-16
URL	http://arxiv.org/abs/1902.06024v1
PDF	http://arxiv.org/pdf/1902.06024v1.pdf
PWC	https://paperswithcode.com/paper/cruzaffect-at-affcon-2019-shared-task-a
Repo
Framework