Paper Group ANR 937
IoT2Vec: Identification of Similar IoT Devices via Activity Footprints. A Kernel Embedding-based Approach for Nonstationary Causal Model Inference. One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL. Par4Sim – Adaptive Paraphrasing for Text Simplification. Knowledge and Blameworthiness. A Bayesian Model for Bivariate Causal I …
IoT2Vec: Identification of Similar IoT Devices via Activity Footprints
| Title | IoT2Vec: Identification of Similar IoT Devices via Activity Footprints |
| Authors | Kushal Singla, Joy Bose |
| Abstract | We consider a smart home or smart office environment with a number of IoT devices connected and passing data between one another. The footprints of the data transferred can provide valuable information about the devices, which can be used to (a) identify the IoT devices and (b) in case of failure, to identify the correct replacements for these devices. In this paper, we generate the embeddings for IoT devices in a smart home using Word2Vec, and explore the possibility of having a similar concept for IoT devices, aka IoT2Vec. These embeddings can be used in a number of ways, such as to find similar devices in an IoT device store, or as a signature of each type of IoT device. We show results of a feasibility study on the CASAS dataset of IoT device activity logs, using our method to identify the patterns in embeddings of various types of IoT devices in a household. |
| Tasks | |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.07907v1 |
| http://arxiv.org/pdf/1805.07907v1.pdf | |
| PWC | https://paperswithcode.com/paper/iot2vec-identification-of-similar-iot-devices |
| Repo | |
| Framework | |
A Kernel Embedding-based Approach for Nonstationary Causal Model Inference
| Title | A Kernel Embedding-based Approach for Nonstationary Causal Model Inference |
| Authors | Shoubo Hu, Zhitang Chen, Laiwan Chan |
| Abstract | Although nonstationary data are more common in the real world, most existing causal discovery methods do not take nonstationarity into consideration. In this letter, we propose a kernel embedding-based approach, ENCI, for nonstationary causal model inference where data are collected from multiple domains with varying distributions. In ENCI, we transform the complicated relation of a cause-effect pair into a linear model of variables of which observations correspond to the kernel embeddings of the cause-and-effect distributions in different domains. In this way, we are able to estimate the causal direction by exploiting the causal asymmetry of the transformed linear model. Furthermore, we extend ENCI to causal graph discovery for multiple variables by transforming the relations among them into a linear nongaussian acyclic model. We show that by exploiting the nonstationarity of distributions, both cause-effect pairs and two kinds of causal graphs are identifiable under mild conditions. Experiments on synthetic and real-world data are conducted to justify the efficacy of ENCI over major existing methods. |
| Tasks | Causal Discovery |
| Published | 2018-09-23 |
| URL | http://arxiv.org/abs/1809.08560v1 |
| http://arxiv.org/pdf/1809.08560v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-kernel-embedding-based-approach-for |
| Repo | |
| Framework | |
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
| Title | One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL |
| Authors | Tom Le Paine, Sergio Gómez Colmenarejo, Ziyu Wang, Scott Reed, Yusuf Aytar, Tobias Pfaff, Matt W. Hoffman, Gabriel Barth-Maron, Serkan Cabi, David Budden, Nando de Freitas |
| Abstract | Humans are experts at high-fidelity imitation – closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap learning of new tasks. Achieving these abilities in autonomous agents is an open problem. In this paper, we introduce an off-policy RL algorithm (MetaMimic) to narrow this gap. MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators. MetaMimic relies on the principle of storing all experiences in a memory and replaying these to learn massive deep neural network policies by off-policy RL. This paper introduces, to the best of our knowledge, the largest existing neural networks for deep RL and shows that larger networks with normalization are needed to achieve one-shot high-fidelity imitation on a challenging manipulation task. The results also show that both types of policy can be learned from vision, in spite of the task rewards being sparse, and without access to demonstrator actions. |
| Tasks | |
| Published | 2018-10-11 |
| URL | http://arxiv.org/abs/1810.05017v1 |
| http://arxiv.org/pdf/1810.05017v1.pdf | |
| PWC | https://paperswithcode.com/paper/one-shot-high-fidelity-imitation-training |
| Repo | |
| Framework | |
Par4Sim – Adaptive Paraphrasing for Text Simplification
| Title | Par4Sim – Adaptive Paraphrasing for Text Simplification |
| Authors | Seid Muhie Yimam, Chris Biemann |
| Abstract | Learning from a real-world data stream and continuously updating the model without explicit supervision is a new challenge for NLP applications with machine learning components. In this work, we have developed an adaptive learning system for text simplification, which improves the underlying learning-to-rank model from usage data, i.e. how users have employed the system for the task of simplification. Our experimental result shows that, over a period of time, the performance of the embedded paraphrase ranking model increases steadily improving from a score of 62.88% up to 75.70% based on the NDCG@10 evaluation metrics. To our knowledge, this is the first study where an NLP component is adaptively improved through usage. |
| Tasks | Learning-To-Rank, Text Simplification |
| Published | 2018-06-21 |
| URL | http://arxiv.org/abs/1806.08309v1 |
| http://arxiv.org/pdf/1806.08309v1.pdf | |
| PWC | https://paperswithcode.com/paper/par4sim-adaptive-paraphrasing-for-text |
| Repo | |
| Framework | |
Knowledge and Blameworthiness
| Title | Knowledge and Blameworthiness |
| Authors | Pavel Naumov, Jia Tao |
| Abstract | Blameworthiness of an agent or a coalition of agents is often defined in terms of the principle of alternative possibilities: for the coalition to be responsible for an outcome, the outcome must take place and the coalition should have had a strategy to prevent it. In this article we argue that in the settings with imperfect information, not only should the coalition have had a strategy, but it also should have known that it had a strategy, and it should have known what the strategy was. The main technical result of the article is a sound and complete bimodal logic that describes the interplay between knowledge and blameworthiness in strategic games with imperfect information. |
| Tasks | |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.02446v3 |
| http://arxiv.org/pdf/1811.02446v3.pdf | |
| PWC | https://paperswithcode.com/paper/blameworthiness-in-games-with-imperfect |
| Repo | |
| Framework | |
A Bayesian Model for Bivariate Causal Inference
| Title | A Bayesian Model for Bivariate Causal Inference |
| Authors | Maximilian Kurthen, Torsten A. Enßlin |
| Abstract | We address the problem of two-variable causal inference without intervention. This task is to infer an existing causal relation between two random variables, i.e. $X \rightarrow Y$ or $Y \rightarrow X$ , from purely observational data. As the option to modify a potential cause is not given in many situations only structural properties of the data can be used to solve this ill-posed problem. We briefly review a number of state-of-the-art methods for this, including very recent ones. A novel inference method is introduced, Bayesian Causal Inference (BCI), which assumes a generative Bayesian hierarchical model to pursue the strategy of Bayesian model selection. In the adopted model the distribution of the cause variable is given by a Poisson lognormal distribution, which allows to explicitly regard the discrete nature of datasets, correlations in the parameter spaces, as well as the variance of probability densities on logarithmic scales. We assume Fourier diagonal Field covariance operators. The model itself is restricted to use cases where a direct causal relation $X \rightarrow Y$ has to be decided against a relation $Y \rightarrow X$ , therefore we compare it other methods for this exact problem setting. The generative model assumed provides synthetic causal data for benchmarking our model in comparison to existing State-of-the-art models, namely LiNGAM , ANM-HSIC , ANM-MML , IGCI and CGNN . We explore how well the above methods perform in case of high noise settings, strongly discretized data and very sparse data. BCI performs generally reliable with synthetic data as well as with the real world TCEP benchmark set, with an accuracy comparable to state-of-the-art algorithms. We discuss directions for the future development of BCI . |
| Tasks | Causal Inference, Model Selection |
| Published | 2018-12-24 |
| URL | https://arxiv.org/abs/1812.09895v2 |
| https://arxiv.org/pdf/1812.09895v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-causal-inference |
| Repo | |
| Framework | |
Building a Reproducible Machine Learning Pipeline
| Title | Building a Reproducible Machine Learning Pipeline |
| Authors | Peter Sugimura, Florian Hartl |
| Abstract | Reproducibility of modeling is a problem that exists for any machine learning practitioner, whether in industry or academia. The consequences of an irreproducible model can include significant financial costs, lost time, and even loss of personal reputation (if results prove unable to be replicated). This paper will first discuss the problems we have encountered while building a variety of machine learning models, and subsequently describe the framework we built to tackle the problem of model reproducibility. The framework is comprised of four main components (data, feature, scoring, and evaluation layers), which are themselves comprised of well defined transformations. This enables us to not only exactly replicate a model, but also to reuse the transformations across different models. As a result, the platform has dramatically increased the speed of both offline and online experimentation while also ensuring model reproducibility. |
| Tasks | |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.04570v1 |
| http://arxiv.org/pdf/1810.04570v1.pdf | |
| PWC | https://paperswithcode.com/paper/building-a-reproducible-machine-learning |
| Repo | |
| Framework | |
Pulsed Schlieren Imaging of Ultrasonic Haptics and Levitation using Phased Arrays
| Title | Pulsed Schlieren Imaging of Ultrasonic Haptics and Levitation using Phased Arrays |
| Authors | Michele Iodice, William Frier, James Wilcox, Ben Long, Orestis Georgiou |
| Abstract | Ultrasonic acoustic fields have recently been used to generate haptic effects on the human skin as well as to levitate small sub-wavelength size particles. Schlieren imaging and background-oriented schlieren techniques can be used for acoustic wave pattern and beam shape visualization. These techniques exploit variations in the refractive index of a propagation medium by applying refractive optics or cross-correlation algorithms of photographs of illuminated background patterns. Here both background-oriented and traditional schlieren systems are used to visualize the regions of the acoustic power involved in creating dynamic haptic sensations and dynamic levitation traps. We demonstrate for the first time the application of back-ground-oriented schlieren for imaging ultrasonic fields in air. We detail our imaging apparatus and present improved algorithms used to visualize these phenomena that we have produced using multiple phased arrays. Moreover, to improve imaging, we leverage an electronically controlled, high-output LED which is pulsed in synchrony with the ultrasonic carrier frequency. |
| Tasks | |
| Published | 2018-09-29 |
| URL | http://arxiv.org/abs/1810.00258v1 |
| http://arxiv.org/pdf/1810.00258v1.pdf | |
| PWC | https://paperswithcode.com/paper/pulsed-schlieren-imaging-of-ultrasonic |
| Repo | |
| Framework | |
A Spatial Mapping Algorithm with Applications in Deep Learning-Based Structure Classification
| Title | A Spatial Mapping Algorithm with Applications in Deep Learning-Based Structure Classification |
| Authors | Thomas Corcoran, Rafael Zamora-Resendiz, Xinlian Liu, Silvia Crivelli |
| Abstract | Convolutional Neural Network (CNN)-based machine learning systems have made breakthroughs in feature extraction and image recognition tasks in two dimensions (2D). Although there is significant ongoing work to apply CNN technology to domains involving complex 3D data, the success of such efforts has been constrained, in part, by limitations in data representation techniques. Most current approaches rely upon low-resolution 3D models, strategic limitation of scope in the 3D space, or the application of lossy projection techniques to allow for the use of 2D CNNs. To address this issue, we present a mapping algorithm that converts 3D structures to 2D and 1D data grids by mapping a traversal of a 3D space-filling curve to the traversal of corresponding 2D and 1D curves. We explore the performance of 2D and 1D CNNs trained on data encoded with our method versus comparable volumetric CNNs operating upon raw 3D data from a popular benchmarking dataset. Our experiments demonstrate that both 2D and 1D representations of 3D data generated via our method preserve a significant proportion of the 3D data’s features in forms learnable by CNNs. Furthermore, we demonstrate that our method of encoding 3D data into lower-dimensional representations allows for decreased CNN training time cost, increased original 3D model rendering resolutions, and supports increased numbers of data channels when compared to purely volumetric approaches. This demonstration is accomplished in the context of a structural biology classification task wherein we train 3D, 2D, and 1D CNNs on examples of two homologous branches within the Ras protein family. The essential contribution of this paper is the introduction of a dimensionality-reduction method that may ease the application of powerful deep learning tools to domains characterized by complex structural data. |
| Tasks | Dimensionality Reduction |
| Published | 2018-02-07 |
| URL | http://arxiv.org/abs/1802.02532v2 |
| http://arxiv.org/pdf/1802.02532v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-spatial-mapping-algorithm-with-applications |
| Repo | |
| Framework | |
Weakly-supervised Dictionary Learning
| Title | Weakly-supervised Dictionary Learning |
| Authors | Zeyu You, Raviv Raich, Xiaoli Z. Fern, Jinsub Kim |
| Abstract | We present a probabilistic modeling and inference framework for discriminative analysis dictionary learning under a weak supervision setting. Dictionary learning approaches have been widely used for tasks such as low-level signal denoising and restoration as well as high-level classification tasks, which can be applied to audio and image analysis. Synthesis dictionary learning aims at jointly learning a dictionary and corresponding sparse coefficients to provide accurate data representation. This approach is useful for denoising and signal restoration, but may lead to sub-optimal classification performance. By contrast, analysis dictionary learning provides a transform that maps data to a sparse discriminative representation suitable for classification. We consider the problem of analysis dictionary learning for time-series data under a weak supervision setting in which signals are assigned with a global label instead of an instantaneous label signal. We propose a discriminative probabilistic model that incorporates both label information and sparsity constraints on the underlying latent instantaneous label signal using cardinality control. We present the expectation maximization (EM) procedure for maximum likelihood estimation (MLE) of the proposed model. To facilitate a computationally efficient E-step, we propose both a chain and a novel tree graph reformulation of the graphical model. The performance of the proposed model is demonstrated on both synthetic and real-world data. |
| Tasks | Denoising, Dictionary Learning, Time Series |
| Published | 2018-02-05 |
| URL | http://arxiv.org/abs/1802.01709v1 |
| http://arxiv.org/pdf/1802.01709v1.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-dictionary-learning |
| Repo | |
| Framework | |
Deep learning-based virtual histology staining using auto-fluorescence of label-free tissue
| Title | Deep learning-based virtual histology staining using auto-fluorescence of label-free tissue |
| Authors | Yair Rivenson, Hongda Wang, Zhensong Wei, Yibo Zhang, Harun Gunaydin, Aydogan Ozcan |
| Abstract | Histological analysis of tissue samples is one of the most widely used methods for disease diagnosis. After taking a sample from a patient, it goes through a lengthy and laborious preparation, which stains the tissue to visualize different histological features under a microscope. Here, we demonstrate a label-free approach to create a virtually-stained microscopic image using a single wide-field auto-fluorescence image of an unlabeled tissue sample, bypassing the standard histochemical staining process, saving time and cost. This method is based on deep learning, and uses a convolutional neural network trained using a generative adversarial network model to transform an auto-fluorescence image of an unlabeled tissue section into an image that is equivalent to the bright-field image of the stained-version of the same sample. We validated this method by successfully creating virtually-stained microscopic images of human tissue samples, including sections of salivary gland, thyroid, kidney, liver and lung tissue, also covering three different stains. This label-free virtual-staining method eliminates cumbersome and costly histochemical staining procedures, and would significantly simplify tissue preparation in pathology and histology fields. |
| Tasks | |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11293v1 |
| http://arxiv.org/pdf/1803.11293v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-virtual-histology |
| Repo | |
| Framework | |
Balanced Linear Contextual Bandits
| Title | Balanced Linear Contextual Bandits |
| Authors | Maria Dimakopoulou, Zhengyuan Zhou, Susan Athey, Guido Imbens |
| Abstract | Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult estimation problems along the path of learning. We develop algorithms for contextual bandits with linear payoffs that integrate balancing methods from the causal inference literature in their estimation to make it less prone to problems of estimation bias. We provide the first regret bound analyses for linear contextual bandits with balancing and show that our algorithms match the state of the art theoretical guarantees. We demonstrate the strong practical advantage of balanced contextual bandits on a large number of supervised learning datasets and on a synthetic example that simulates model misspecification and prejudice in the initial training data. |
| Tasks | Causal Inference, Multi-Armed Bandits |
| Published | 2018-12-15 |
| URL | http://arxiv.org/abs/1812.06227v1 |
| http://arxiv.org/pdf/1812.06227v1.pdf | |
| PWC | https://paperswithcode.com/paper/balanced-linear-contextual-bandits |
| Repo | |
| Framework | |
What is the Effect of Importance Weighting in Deep Learning?
| Title | What is the Effect of Importance Weighting in Deep Learning? |
| Authors | Jonathon Byrd, Zachary C. Lipton |
| Abstract | Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is well-characterized for low-capacity misspecified models, little is known about how it impacts over-parameterized, deep neural networks. This work is inspired by recent theoretical results showing that on (linearly) separable data, deep linear networks optimized by SGD learn weight-agnostic solutions, prompting us to ask, for realistic deep networks, for which many practical datasets are separable, what is the effect of importance weighting? We present the surprising finding that while importance weighting impacts models early in training, its effect diminishes over successive epochs. Moreover, while L2 regularization and batch normalization (but not dropout), restore some of the impact of importance weighting, they express the effect via (seemingly) the wrong abstraction: why should practitioners tweak the L2 regularization, and by how much, to produce the correct weighting effect? Our experiments confirm these findings across a range of architectures and datasets. |
| Tasks | Causal Inference, Domain Adaptation, L2 Regularization |
| Published | 2018-12-08 |
| URL | https://arxiv.org/abs/1812.03372v3 |
| https://arxiv.org/pdf/1812.03372v3.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-risk-minimization-deep-learning |
| Repo | |
| Framework | |
Part-level Car Parsing and Reconstruction from Single Street View
| Title | Part-level Car Parsing and Reconstruction from Single Street View |
| Authors | Qichuan Geng, Hong Zhang, Xinyu Huang, Sen Wang, Feixiang Lu, Xinjing Cheng, Zhong Zhou, Ruigang Yang |
| Abstract | Part information has been shown to be resistant to occlusions and viewpoint changes, which is beneficial for various vision-related tasks. However, we found very limited work in car pose estimation and reconstruction from street views leveraging the part information. There are two major contributions in this paper. Firstly, we make the first attempt to build a framework to simultaneously estimate shape, translation, orientation, and semantic parts of cars in 3D space from a single street view. As it is labor-intensive to annotate semantic parts on real street views, we propose a specific approach to implicitly transfer part features from synthesized images to real street views. For pose and shape estimation, we propose a novel network structure that utilizes both part features and 3D losses. Secondly, we are the first to construct a high-quality dataset that contains 348 different car models with physical dimensions and part-level annotations based on global and local deformations. Given these models, we further generate 60K synthesized images with randomization of orientation, illumination, occlusion, and texture. Our results demonstrate that our part segmentation performance is significantly improved after applying our implicit transfer approach. Our network for pose and shape estimation achieves the state-of-the-art performance on the ApolloCar3D dataset and outperforms 3D-RCNN and DeepMANTA by 12.57 and 8.91 percentage points in terms of mean A3DP-Abs. |
| Tasks | Domain Adaptation, Pose Estimation, Vehicle Re-Identification |
| Published | 2018-11-27 |
| URL | https://arxiv.org/abs/1811.10837v2 |
| https://arxiv.org/pdf/1811.10837v2.pdf | |
| PWC | https://paperswithcode.com/paper/part-level-car-parsing-and-reconstruction |
| Repo | |
| Framework | |
SegStereo: Exploiting Semantic Information for Disparity Estimation
| Title | SegStereo: Exploiting Semantic Information for Disparity Estimation |
| Authors | Guorun Yang, Hengshuang Zhao, Jianping Shi, Zhidong Deng, Jiaya Jia |
| Abstract | Disparity estimation for binocular stereo images finds a wide range of applications. Traditional algorithms may fail on featureless regions, which could be handled by high-level clues such as semantic segments. In this paper, we suggest that appropriate incorporation of semantic cues can greatly rectify prediction in commonly-used disparity estimation frameworks. Our method conducts semantic feature embedding and regularizes semantic cues as the loss term to improve learning disparity. Our unified model SegStereo employs semantic features from segmentation and introduces semantic softmax loss, which helps improve the prediction accuracy of disparity maps. The semantic cues work well in both unsupervised and supervised manners. SegStereo achieves state-of-the-art results on KITTI Stereo benchmark and produces decent prediction on both CityScapes and FlyingThings3D datasets. |
| Tasks | Disparity Estimation |
| Published | 2018-07-31 |
| URL | http://arxiv.org/abs/1807.11699v1 |
| http://arxiv.org/pdf/1807.11699v1.pdf | |
| PWC | https://paperswithcode.com/paper/segstereo-exploiting-semantic-information-for |
| Repo | |
| Framework | |
