Paper Group ANR 567
Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction. Localized Linear Regression in Networked Data. Increasing city safety awareness regarding disruptive traffic stream. Accelerated Discovery of Sustainable Building Materials. Human-AI Co-Learning for Data-Driven AI. PingPong: Packet-Level Signatures for Smar …
Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction
| Title | Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction |
| Authors | Fengda Zhu, Xiaojun Chang, Runhao Zeng, Mingkui Tan |
| Abstract | Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially due to catastrophic forgetting. Specifically, the model would forget knowledge it learned in the past when trained on a new task. We consider this challenge from two perspectives: i) acquiring task-specific skills is difficult since task information and rewards are not highly related; ii) learning knowledge from previous experience is difficult in continuous control domains. In this paper, we introduce an end-to-end framework namely Continual Diversity Adversarial Network (CDAN). We first develop an unsupervised diversity exploration method to learn task-specific skills using an unsupervised objective. Then, we propose an adversarial self-correction mechanism to learn knowledge by exploiting past experience. The two learning procedures are presumably reciprocal. To evaluate the proposed method, we propose a new continuous reinforcement learning environment named Continual Ant Maze (CAM) and a new metric termed Normalized Shorten Distance (NSD). The experimental results confirm the effectiveness of diversity exploration and self-correction. It is worthwhile noting that our final result outperforms baseline by 18.35% in terms of NSD, and 0.61 according to the average reward. |
| Tasks | Autonomous Driving, Continuous Control |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09205v1 |
| https://arxiv.org/pdf/1906.09205v1.pdf | |
| PWC | https://paperswithcode.com/paper/continual-reinforcement-learning-with |
| Repo | |
| Framework | |
Localized Linear Regression in Networked Data
| Title | Localized Linear Regression in Networked Data |
| Authors | Alexander Jung, Nguyen Tran |
| Abstract | The network Lasso (nLasso) has been proposed recently as an efficient learning algorithm for massive networked data sets (big data over networks). It extends the well-known least absolute shrinkage and selection operator (Lasso) from learning sparse (generalized) linear models to network models. Efficient implementations of the nLasso have been obtained using convex optimization methods lending to scalable message passing protocols. In this paper, we analyze the statistical properties of nLasso when applied to localized linear regression problems involving networked data. Our main result is a sufficient condition on the network structure and available label information such that nLasso accurately learns a localized linear regression model from a few labeled data points. We also provide an implementation of nLasso for localized linear regression by specializing a primaldual method for solving the convex (non-smooth) nLasso problem. |
| Tasks | |
| Published | 2019-03-26 |
| URL | https://arxiv.org/abs/1903.11178v2 |
| https://arxiv.org/pdf/1903.11178v2.pdf | |
| PWC | https://paperswithcode.com/paper/localized-linear-regression-in-networked-data |
| Repo | |
| Framework | |
Increasing city safety awareness regarding disruptive traffic stream
| Title | Increasing city safety awareness regarding disruptive traffic stream |
| Authors | Olivera Kotevska |
| Abstract | Transportation systems serve the people in essence, in this study we focus in traffic information related to violation events to respond to safety requirements of the cities. Traffic violation events have an important role in city safety awareness and secure travel. In this work, we describe the use of knowledge discovery from traffic violation reports in combination with demographics approach using inductive logic programming to automatically extract knowledge about traffic violation behavior and their impact on the environment. |
| Tasks | |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1902.06670v1 |
| http://arxiv.org/pdf/1902.06670v1.pdf | |
| PWC | https://paperswithcode.com/paper/increasing-city-safety-awareness-regarding |
| Repo | |
| Framework | |
Accelerated Discovery of Sustainable Building Materials
| Title | Accelerated Discovery of Sustainable Building Materials |
| Authors | Xiou Ge, Richard T. Goodwin, Jeremy R. Gregory, Randolph E. Kirchain, Joana Maria, Lav R. Varshney |
| Abstract | Concrete is the most widely used engineered material in the world with more than 10 billion tons produced annually. Unfortunately, with that scale comes a significant burden in terms of energy, water, and release of greenhouse gases and other pollutants. As such, there is interest in creating concrete formulas that minimize this environmental burden, while satisfying engineering performance requirements. Recent advances in artificial intelligence have enabled machines to generate highly plausible artifacts, such as images of realistic looking faces. Semi-supervised generative models allow generation of artifacts with specific, desired characteristics. In this work, we use Conditional Variational Autoencoders (CVAE), a type of semi-supervised generative model, to discover concrete formulas with desired properties. Our model is trained using open data from the UCI Machine Learning Repository joined with environmental impact data computed using a web-based tool. We demonstrate CVAEs can design concrete formulas with lower emissions and natural resource usage while meeting design requirements. To ensure fair comparison between extant and generated formulas, we also train regression models to predict the environmental impacts and strength of discovered formulas. With these results, a construction engineer may create a formula that meets structural needs and best addresses local environmental concerns. |
| Tasks | |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08222v1 |
| https://arxiv.org/pdf/1905.08222v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerated-discovery-of-sustainable-building |
| Repo | |
| Framework | |
Human-AI Co-Learning for Data-Driven AI
| Title | Human-AI Co-Learning for Data-Driven AI |
| Authors | Yi-Ching Huang, Yu-Ting Cheng, Lin-Lin Chen, Jane Yung-jen Hsu |
| Abstract | Human and AI are increasingly interacting and collaborating to accomplish various complex tasks in the context of diverse application domains (e.g., healthcare, transportation, and creative design). Two dynamic, learning entities (AI and human) have distinct mental model, expertise, and ability; such fundamental difference/mismatch offers opportunities for bringing new perspectives to achieve better results. However, this mismatch can cause unexpected failure and result in serious consequences. While recent research has paid much attention to enhancing interpretability or explainability to allow machine to explain how it makes a decision for supporting humans, this research argues that there is urging the need for both human and AI should develop specific, corresponding ability to interact and collaborate with each other to form a human-AI team to accomplish superior results. This research introduces a conceptual framework called “Co-Learning,” in which people can learn with/from and grow with AI partners over time. We characterize three key concepts of co-learning: “mutual understanding,” “mutual benefits,” and “mutual growth” for facilitating human-AI collaboration on complex problem solving. We will present proof-of-concepts to investigate whether and how our approach can help human-AI team to understand and benefit each other, and ultimately improve productivity and creativity on creative problem domains. The insights will contribute to the design of Human-AI collaboration. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12544v1 |
| https://arxiv.org/pdf/1910.12544v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-ai-co-learning-for-data-driven-ai |
| Repo | |
| Framework | |
PingPong: Packet-Level Signatures for Smart Home Device Events
| Title | PingPong: Packet-Level Signatures for Smart Home Device Events |
| Authors | Rahmadi Trimananda, Janus Varmarken, Athina Markopoulou, Brian Demsky |
| Abstract | Smart home devices are vulnerable to passive inference attacks based on network traffic, even in the presence of encryption. In this paper, we present PINGPONG, a tool that can automatically extract packet-level signatures for device events (e.g., light bulb turning ON/OFF) from network traffic. We evaluated PINGPONG on popular smart home devices ranging from smart plugs and thermostats to cameras, voice-activated devices, and smart TVs. We were able to: (1) automatically extract previously unknown signatures that consist of simple sequences of packet lengths and directions; (2) use those signatures to detect the devices or specific events with an average recall of more than 97%; (3) show that the signatures are unique among hundreds of millions of packets of real world network traffic; (4) show that our methodology is also applicable to publicly available datasets; and (5) demonstrate its robustness in different settings: events triggered by local and remote smartphones, as well as by homeautomation systems. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11797v3 |
| https://arxiv.org/pdf/1907.11797v3.pdf | |
| PWC | https://paperswithcode.com/paper/pingpong-packet-level-signatures-for-smart |
| Repo | |
| Framework | |
A vector-contraction inequality for Rademacher complexities using $p$-stable variables
| Title | A vector-contraction inequality for Rademacher complexities using $p$-stable variables |
| Authors | Oscar Zatarain-Vera |
| Abstract | Andreas Maurer in the paper “A vector-contraction inequality for Rademacher complexities’’ extended the contraction inequality for Rademacher averages to Lipschitz functions with vector-valued domains; He did it replacing the Rademacher variables in the bounding expression by arbitrary idd symmetric and sub-gaussian variables. We will see how to extend this work when we replace sub-gaussian variables by $p$-stable variables for $1<p<2$. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.10136v1 |
| https://arxiv.org/pdf/1912.10136v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-vector-contraction-inequality-for-1 |
| Repo | |
| Framework | |
GeoStyle: Discovering Fashion Trends and Events
| Title | GeoStyle: Discovering Fashion Trends and Events |
| Authors | Utkarsh Mall, Kevin Matzen, Bharath Hariharan, Noah Snavely, Kavita Bala |
| Abstract | Understanding fashion styles and trends is of great potential interest to retailers and consumers alike. The photos people upload to social media are a historical and public data source of how people dress across the world and at different times. While we now have tools to automatically recognize the clothing and style attributes of what people are wearing in these photographs, we lack the ability to analyze spatial and temporal trends in these attributes or make predictions about the future. In this paper, we address this need by providing an automatic framework that analyzes large corpora of street imagery to (a) discover and forecast long-term trends of various fashion attributes as well as automatically discovered styles, and (b) identify spatio-temporally localized events that affect what people wear. We show that our framework makes long term trend forecasts that are >20% more accurate than the prior art, and identifies hundreds of socially meaningful events that impact fashion across the globe. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.11412v1 |
| https://arxiv.org/pdf/1908.11412v1.pdf | |
| PWC | https://paperswithcode.com/paper/geostyle-discovering-fashion-trends-and |
| Repo | |
| Framework | |
What is Fair? Exploring Pareto-Efficiency for Fairness Constrained Classifiers
| Title | What is Fair? Exploring Pareto-Efficiency for Fairness Constrained Classifiers |
| Authors | Ananth Balashankar, Alyssa Lees, Chris Welty, Lakshminarayanan Subramanian |
| Abstract | The potential for learned models to amplify existing societal biases has been broadly recognized. Fairness-aware classifier constraints, which apply equality metrics of performance across subgroups defined on sensitive attributes such as race and gender, seek to rectify inequity but can yield non-uniform degradation in performance for skewed datasets. In certain domains, imbalanced degradation of performance can yield another form of unintentional bias. In the spirit of constructing fairness-aware algorithms as societal imperative, we explore an alternative: Pareto-Efficient Fairness (PEF). Theoretically, we prove that PEF identifies the operating point on the Pareto curve of subgroup performances closest to the fairness hyperplane, maximizing multiple subgroup accuracy. Empirically we demonstrate that PEF outperforms by achieving Pareto levels in accuracy for all subgroups compared to strict fairness constraints in several UCI datasets. |
| Tasks | |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.14120v1 |
| https://arxiv.org/pdf/1910.14120v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-is-fair-exploring-pareto-efficiency-for |
| Repo | |
| Framework | |
Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering
| Title | Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering |
| Authors | Ilias Diakonikolas, Sushrut Karmalkar, Daniel Kane, Eric Price, Alistair Stewart |
| Abstract | We study high-dimensional sparse estimation tasks in a robust setting where a constant fraction of the dataset is adversarially corrupted. Specifically, we focus on the fundamental problems of robust sparse mean estimation and robust sparse PCA. We give the first practically viable robust estimators for these problems. In more detail, our algorithms are sample and computationally efficient and achieve near-optimal robustness guarantees. In contrast to prior provable algorithms which relied on the ellipsoid method, our algorithms use spectral techniques to iteratively remove outliers from the dataset. Our experimental evaluation on synthetic data shows that our algorithms are scalable and significantly outperform a range of previous approaches, nearly matching the best error rate without corruptions. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08085v1 |
| https://arxiv.org/pdf/1911.08085v1.pdf | |
| PWC | https://paperswithcode.com/paper/outlier-robust-high-dimensional-sparse-1 |
| Repo | |
| Framework | |
Mcity Data Collection for Automated Vehicles Study
| Title | Mcity Data Collection for Automated Vehicles Study |
| Authors | Yiqun Dong, Yuanxin Zhong, Wenbo Yu, Minghan Zhu, Pingping Lu, Yeyang Fang, Jiajun Hong, Huei Peng |
| Abstract | The main goal of this paper is to introduce the data collection effort at Mcity targeting automated vehicle development. We captured a comprehensive set of data from a set of perception sensors (Lidars, Radars, Cameras) as well as vehicle steering/brake/throttle inputs and an RTK unit. Two in-cabin cameras record the human driver’s behaviors for possible future use. The naturalistic driving on selected open roads is recorded at different time of day and weather conditions. We also perform designed choreography data collection inside the Mcity test facility focusing on vehicle to vehicle, and vehicle to vulnerable road user interactions which is quite unique among existing open-source datasets. The vehicle platform, data content, tags/labels, and selected analysis results are shown in this paper. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06258v1 |
| https://arxiv.org/pdf/1912.06258v1.pdf | |
| PWC | https://paperswithcode.com/paper/mcity-data-collection-for-automated-vehicles |
| Repo | |
| Framework | |
Legal Area Classification: A Comparative Study of Text Classifiers on Singapore Supreme Court Judgments
| Title | Legal Area Classification: A Comparative Study of Text Classifiers on Singapore Supreme Court Judgments |
| Authors | Jerrold Soh Tsin Howe, Lim How Khang, Ian Ernst Chai |
| Abstract | This paper conducts a comparative study on the performance of various machine learning (``ML’') approaches for classifying judgments into legal areas. Using a novel dataset of 6,227 Singapore Supreme Court judgments, we investigate how state-of-the-art NLP methods compare against traditional statistical models when applied to a legal corpus that comprised few but lengthy documents. All approaches tested, including topic model, word embedding, and language model-based classifiers, performed well with as little as a few hundred judgments. However, more work needs to be done to optimize state-of-the-art methods for the legal domain. | |
| Tasks | Language Modelling |
| Published | 2019-04-13 |
| URL | http://arxiv.org/abs/1904.06470v1 |
| http://arxiv.org/pdf/1904.06470v1.pdf | |
| PWC | https://paperswithcode.com/paper/legal-area-classification-a-comparative-study |
| Repo | |
| Framework | |
High Performance Visual Object Tracking with Unified Convolutional Networks
| Title | High Performance Visual Object Tracking with Unified Convolutional Networks |
| Authors | Zheng Zhu, Wei Zou, Guan Huang, Dalong Du, Chang Huang |
| Abstract | Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks. Nonetheless, the chosen CNN features are always pre-trained in different tasks and individual components in tracking systems are learned separately, thus the achieved tracking performance may be suboptimal. Besides, most of these trackers are not designed towards real-time applications because of their time-consuming feature extraction and complex optimization details. In this paper, we propose an end-to-end framework to learn the convolutional features and perform the tracking process simultaneously, namely, a unified convolutional tracker (UCT). Specifically, the UCT treats feature extractor and tracking process both as convolution operation and trains them jointly, which enables learned CNN features are tightly coupled with tracking process. During online tracking, an efficient model updating method is proposed by introducing peak-versus-noise ratio (PNR) criterion, and scale changes are handled efficiently by incorporating a scale branch into network. Experiments are performed on four challenging tracking datasets: OTB2013, OTB2015, VOT2015 and VOT2016. Our method achieves leading performance on these benchmarks while maintaining beyond real-time speed. |
| Tasks | Object Tracking, Visual Object Tracking |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1908.09445v1 |
| https://arxiv.org/pdf/1908.09445v1.pdf | |
| PWC | https://paperswithcode.com/paper/high-performance-visual-object-tracking-with |
| Repo | |
| Framework | |
Regression on imperfect class labels derived by unsupervised clustering
| Title | Regression on imperfect class labels derived by unsupervised clustering |
| Authors | Rasmus Froberg Brøndum, Thomas Yssing Michaelsen, Martin Bøgsted |
| Abstract | Outcome regressed on class labels identified by unsupervised clustering is custom in many applications. However, it is common to ignore the misclassification of class labels caused by the learning algorithm, which potentially leads to serious bias of the estimated effect parameters. Due to its generality we suggest to redress the situation by use of the simulation and extrapolation method. Performance is illustrated by simulated data from Gaussian mixture models. Finally, we apply our method to a study which regressed overall survival on class labels derived from unsupervised clustering of gene expression data from bone marrow samples of multiple myeloma patients. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05885v1 |
| https://arxiv.org/pdf/1908.05885v1.pdf | |
| PWC | https://paperswithcode.com/paper/regression-on-imperfect-class-labels-derived |
| Repo | |
| Framework | |
Neural embeddings for metaphor detection in a corpus of Greek texts
| Title | Neural embeddings for metaphor detection in a corpus of Greek texts |
| Authors | Eirini Florou, Konstantinos Perifanos, Dionysis Goutsos |
| Abstract | One of the major challenges that NLP faces is metaphor detection, especially by automatic means, a task that becomes even more difficult for languages lacking in linguistic resources and tools. Our purpose is the automatic differentiation between literal and metaphorical meaning in authentic non-annotated phrases from the Corpus of Greek Texts by means of computational methods of machine learning. For this purpose the theoretical background of distributional semantics is discussed and employed. Distributional Semantics Theory develops concepts and methods for the quantification and classification of semantic similarities displayed by linguistic elements in large amounts of linguistic data according to their distributional properties. In accordance with this model, the approach followed in the thesis takes into account the linguistic context for the computation of the distributional representation of phrases in geometrical space, as well as for their comparison with the distributional representations of other phrases, whose function in speech is already “known” with the objective to reach conclusions about their literal or metaphorical function in the specific linguistic context. This procedure aims at dealing with the lack of linguistic resources for the Greek language, as the almost impossible up to now semantic comparison between “phrases”, takes the form of an arithmetical comparison of their distributional representations in geometrical space. |
| Tasks | |
| Published | 2019-02-10 |
| URL | http://arxiv.org/abs/1902.03659v1 |
| http://arxiv.org/pdf/1902.03659v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-embeddings-for-metaphor-detection-in-a |
| Repo | |
| Framework | |
