January 29, 2020

3209 words 16 mins read

Paper Group ANR 537

Approximate Inference in Structured Instances with Noisy Categorical Observations. Fault Detection Using Nonlinear Low-Dimensional Representation of Sensor Data. Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning. City-scale Road Extraction from Satellite Imagery. Unsupervised Deep Feature Transfer for Low R …

Approximate Inference in Structured Instances with Noisy Categorical Observations


Title	Approximate Inference in Structured Instances with Noisy Categorical Observations
Authors	Alireza Heidari, Ihab F. Ilyas, Theodoros Rekatsinas
Abstract	We study the problem of recovering the latent ground truth labeling of a structured instance with categorical random variables in the presence of noisy observations. We present a new approximate algorithm for graphs with categorical variables that achieves low Hamming error in the presence of noisy vertex and edge observations. Our main result shows a logarithmic dependency of the Hamming error to the number of categories of the random variables. Our approach draws connections to correlation clustering with a fixed number of clusters. Our results generalize the works of Globerson et al. (2015) and Foster et al. (2018), who study the hardness of structured prediction under binary labels, to the case of categorical labels.
Tasks	Structured Prediction
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00141v2
PDF	https://arxiv.org/pdf/1907.00141v2.pdf
PWC	https://paperswithcode.com/paper/approximate-inference-in-structured-instances
Repo
Framework

Fault Detection Using Nonlinear Low-Dimensional Representation of Sensor Data


Title	Fault Detection Using Nonlinear Low-Dimensional Representation of Sensor Data
Authors	Kai Shen, Anya Mcguirk, Yuwei Liao, Arin Chaudhuri, Deovrat Kakde
Abstract	Sensor data analysis plays a key role in health assessment of critical equipment. Such data are multivariate and exhibit nonlinear relationships. This paper describes how one can exploit nonlinear dimension reduction techniques, such as the t-distributed stochastic neighbor embedding (t-SNE) and kernel principal component analysis (KPCA) for fault detection. We show that using anomaly detection with low dimensional representations provides better interpretability and is conducive to edge processing in IoT applications.
Tasks	Anomaly Detection, Dimensionality Reduction, Fault Detection
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01150v1
PDF	https://arxiv.org/pdf/1910.01150v1.pdf
PWC	https://paperswithcode.com/paper/fault-detection-using-nonlinear-low
Repo
Framework

Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning


Title	Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning
Authors	Guanyu Gao, Jie Li, Yonggang Wen
Abstract	Heating, Ventilation, and Air Conditioning (HVAC) is extremely energy-consuming, accounting for 40% of total building energy consumption. Therefore, it is crucial to design some energy-efficient building thermal control policies which can reduce the energy consumption of HVAC while maintaining the comfort of the occupants. However, implementing such a policy is challenging, because it involves various influencing factors in a building environment, which are usually hard to model and may be different from case to case. To address this challenge, we propose a deep reinforcement learning based framework for energy optimization and thermal comfort control in smart buildings. We formulate the building thermal control as a cost-minimization problem which jointly considers the energy consumption of HVAC and the thermal comfort of the occupants. To solve the problem, we first adopt a deep neural network based approach for predicting the occupants’ thermal comfort, and then adopt Deep Deterministic Policy Gradients (DDPG) for learning the thermal control policy. To evaluate the performance, we implement a building thermal control simulation system and evaluate the performance under various settings. The experiment results show that our method can improve the thermal comfort prediction accuracy, and reduce the energy consumption of HVAC while improving the occupants’ thermal comfort.
Tasks
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04693v1
PDF	http://arxiv.org/pdf/1901.04693v1.pdf
PWC	https://paperswithcode.com/paper/energy-efficient-thermal-comfort-control-in
Repo
Framework

City-scale Road Extraction from Satellite Imagery


Title	City-scale Road Extraction from Satellite Imagery
Authors	Adam Van Etten
Abstract	Automated road network extraction from remote sensing imagery remains a significant challenge despite its importance in a broad array of applications. To this end, we leverage recent open source advances and the high quality SpaceNet dataset to explore road network extraction at scale, an approach we call City-scale Road Extraction from Satellite Imagery (CRESI). Specifically, we create an algorithm to extract road networks directly from imagery over city-scale regions, which can subsequently be used for routing purposes. We quantify the performance of our algorithm with the APLS and TOPO graph-theoretic metrics over a diverse 608 square kilometer test area covering four cities. We find an aggregate score of APLS = 0.73, and a TOPO score of 0.58 (a significant improvement over existing methods). Inference speed is 160 square kilometers per hour on modest hardware. Finally, we demonstrate that one can use the extracted road network for any number of applications, such as optimized routing.
Tasks
Published	2019-04-22
URL	https://arxiv.org/abs/1904.09901v2
PDF	https://arxiv.org/pdf/1904.09901v2.pdf
PWC	https://paperswithcode.com/paper/city-scale-road-extraction-from-satellite
Repo
Framework

Unsupervised Deep Feature Transfer for Low Resolution Image Classification


Title	Unsupervised Deep Feature Transfer for Low Resolution Image Classification
Authors	Yuanwei Wu, Ziming Zhang, Guanghui Wang
Abstract	In this paper, we propose a simple while effective unsupervised deep feature transfer algorithm for low resolution image classification. No fine-tuning on convenet filters is required in our method. We use pre-trained convenet to extract features for both high- and low-resolution images, and then feed them into a two-layer feature transfer network for knowledge transfer. A SVM classifier is learned directly using these transferred low resolution features. Our network can be embedded into the state-of-the-art deep neural networks as a plug-in feature enhancement module. It preserves data structures in feature space for high resolution images, and transfers the distinguishing features from a well-structured source domain (high resolution features space) to a not well-organized target domain (low resolution features space). Extensive experiments on VOC2007 test set show that the proposed method achieves significant improvements over the baseline of using feature extraction.
Tasks	Image Classification, Transfer Learning
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10012v2
PDF	https://arxiv.org/pdf/1908.10012v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-deep-feature-transfer-for-low
Repo
Framework

Robust Learning from Noisy Side-information by Semidefinite Programming


Title	Robust Learning from Noisy Side-information by Semidefinite Programming
Authors	En-Liang Hu, Quanming Yao
Abstract	Robustness recently becomes one of the major concerns among machine learning community, since learning algorithms are usually vulnerable to outliers or corruptions. Motivated by such a trend and needs, we pursue robustness in semi-definite programming (SDP) in this paper. Specifically, this is done by replacing the commonly used squared loss with the more robust $\ell_1$-loss in the low-rank SDP. However, the resulting objective becomes neither convex nor smooth. As no existing algorithms can be applied, we design an efficient algorithm, based on majorization-minimization, to optimize the objective. The proposed algorithm not only has cheap iterations and low space complexity but also theoretically converges to some critical points. Finally, empirical study shows that the new objective armed with proposed algorithm outperforms state-of-the-art in terms of both speed and accuracy.
Tasks
Published	2019-05-12
URL	https://arxiv.org/abs/1905.04629v1
PDF	https://arxiv.org/pdf/1905.04629v1.pdf
PWC	https://paperswithcode.com/paper/robust-learning-from-noisy-side-information
Repo
Framework

Semi-supervised acoustic model training for five-lingual code-switched ASR


Title	Semi-supervised acoustic model training for five-lingual code-switched ASR
Authors	Astik Biswas, Emre Yılmaz, Febe de Wet, Ewald van der Westhuizen, Thomas Niesler
Abstract	This paper presents recent progress in the acoustic modelling of under-resourced code-switched (CS) speech in multiple South African languages. We consider two approaches. The first constructs separate bilingual acoustic models corresponding to language pairs (English-isiZulu, English-isiXhosa, English-Setswana and English-Sesotho). The second constructs a single unified five-lingual acoustic model representing all the languages (English, isiZulu, isiXhosa, Setswana and Sesotho). For these two approaches we consider the effectiveness of semi-supervised training to increase the size of the very sparse acoustic training sets. Using approximately 11 hours of untranscribed speech, we show that both approaches benefit from semi-supervised training. The bilingual TDNN-F acoustic models also benefit from the addition of CNN layers (CNN-TDNN-F), while the five-lingual system does not show any significant improvement. Furthermore, because English is common to all language pairs in our data, it dominates when training a unified language model, leading to improved English ASR performance at the expense of the other languages. Nevertheless, the five-lingual model offers flexibility because it can process more than two languages simultaneously, and is therefore an attractive option as an automatic transcription system in a semi-supervised training pipeline.
Tasks	Acoustic Modelling, Language Modelling
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08647v2
PDF	https://arxiv.org/pdf/1906.08647v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-acoustic-model-training-for-1
Repo
Framework

Task-Discriminative Domain Alignment for Unsupervised Domain Adaptation


Title	Task-Discriminative Domain Alignment for Unsupervised Domain Adaptation
Authors	Behnam Gholami, Pritish Sahu, Minyoung Kim, Vladimir Pavlovic
Abstract	Domain Adaptation (DA), the process of effectively adapting task models learned on one domain, the source, to other related but distinct domains, the targets, with no or minimal retraining, is typically accomplished using the process of source-to-target manifold alignment. However, this process often leads to unsatisfactory adaptation performance, in part because it ignores the task-specific structure of the data. In this paper, we improve the performance of DA by introducing a discriminative discrepancy measure which takes advantage of auxiliary information available in the source and the target domains to better align the source and target distributions. Specifically, we leverage the cohesive clustering structure within individual data manifolds, associated with different tasks, to improve the alignment. This structure is explicit in the source, where the task labels are available, but is implicit in the target, making the problem challenging. We address the challenge by devising a deep DA framework, which combines a new task-driven domain alignment discriminator with domain regularizers that encourage the shared features as task-specific and domain invariant, and prompt the task model to be data structure preserving, guiding its decision boundaries through the low density data regions. We validate our framework on standard benchmarks, including Digits (MNIST, USPS, SVHN, MNIST-M), PACS, and VisDA. Our results show that our proposed model consistently outperforms the state-of-the-art in unsupervised domain adaptation.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12366v1
PDF	https://arxiv.org/pdf/1909.12366v1.pdf
PWC	https://paperswithcode.com/paper/task-discriminative-domain-alignment-for
Repo
Framework

Memory-Augmented Neural Networks for Machine Translation


Title	Memory-Augmented Neural Networks for Machine Translation
Authors	Mark Collier, Joeran Beel
Abstract	Memory-augmented neural networks (MANNs) have been shown to outperform other recurrent neural network architectures on a series of artificial sequence learning tasks, yet they have had limited application to real-world tasks. We evaluate direct application of Neural Turing Machines (NTM) and Differentiable Neural Computers (DNC) to machine translation. We further propose and evaluate two models which extend the attentional encoder-decoder with capabilities inspired by memory augmented neural networks. We evaluate our proposed models on IWSLT Vietnamese to English and ACL Romanian to English datasets. Our proposed models and the memory augmented neural networks perform similarly to the attentional encoder-decoder on the Vietnamese to English translation task while have a 0.3-1.9 lower BLEU score for the Romanian to English task. Interestingly, our analysis shows that despite being equipped with additional flexibility and being randomly initialized memory augmented neural networks learn an algorithm for machine translation almost identical to the attentional encoder-decoder.
Tasks	Machine Translation
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08314v1
PDF	https://arxiv.org/pdf/1909.08314v1.pdf
PWC	https://paperswithcode.com/paper/memory-augmented-neural-networks-for-machine
Repo
Framework

Functional Principal Component Analysis for Extrapolating Multi-stream Longitudinal Data


Title	Functional Principal Component Analysis for Extrapolating Multi-stream Longitudinal Data
Authors	Seokhyun Chung, Raed Kontar
Abstract	The advance of modern sensor technologies enables collection of multi-stream longitudinal data where multiple signals from different units are collected in real-time. In this article, we present a non-parametric approach to predict the evolution of multi-stream longitudinal data for an in-service unit through borrowing strength from other historical units. Our approach first decomposes each stream into a linear combination of eigenfunctions and their corresponding functional principal component (FPC) scores. A Gaussian process prior for the FPC scores is then established based on a functional semi-metric that measures similarities between streams of historical units and the in-service unit. Finally, an empirical Bayesian updating strategy is derived to update the established prior using real-time stream data obtained from the in-service unit. Experiments on synthetic and real world data show that the proposed framework outperforms state-of-the-art approaches and can effectively account for heterogeneity as well as achieve high predictive accuracy.
Tasks
Published	2019-03-09
URL	http://arxiv.org/abs/1903.03871v1
PDF	http://arxiv.org/pdf/1903.03871v1.pdf
PWC	https://paperswithcode.com/paper/functional-principal-component-analysis-for
Repo
Framework

Spectral Graph Matching and Regularized Quadratic Relaxations I: The Gaussian Model


Title	Spectral Graph Matching and Regularized Quadratic Relaxations I: The Gaussian Model
Authors	Zhou Fan, Cheng Mao, Yihong Wu, Jiaming Xu
Abstract	Graph matching aims at finding the vertex correspondence between two unlabeled graphs that maximizes the total edge weight correlation. This amounts to solving a computationally intractable quadratic assignment problem. In this paper we propose a new spectral method, GRAph Matching by Pairwise eigen-Alignments (GRAMPA). Departing from prior spectral approaches that only compare top eigenvectors, or eigenvectors of the same order, GRAMPA first constructs a similarity matrix as a weighted sum of outer products between all pairs of eigenvectors of the two graphs, with weights given by a Cauchy kernel applied to the separation of the corresponding eigenvalues, then outputs a matching by a simple rounding procedure. The similarity matrix can also be interpreted as the solution to a regularized quadratic programming relaxation of the quadratic assignment problem. For the Gaussian Wigner model in which two complete graphs on $n$ vertices have Gaussian edge weights with correlation coefficient $1-\sigma^2$, we show that GRAMPA exactly recovers the correct vertex correspondence with high probability when $\sigma = O(\frac{1}{\log n})$. This matches the state of the art of polynomial-time algorithms, and significantly improves over existing spectral methods which require $\sigma$ to be polynomially small in $n$. The superiority of GRAMPA is also demonstrated on a variety of synthetic and real datasets, in terms of both statistical accuracy and computational efficiency. Universality results, including similar guarantees for dense and sparse Erd\H{o}s-R'{e}nyi graphs, are deferred to the companion paper.
Tasks	Graph Matching
Published	2019-07-20
URL	https://arxiv.org/abs/1907.08880v1
PDF	https://arxiv.org/pdf/1907.08880v1.pdf
PWC	https://paperswithcode.com/paper/spectral-graph-matching-and-regularized-1
Repo
Framework

Quantum-Inspired Computing: Can it be a Microscopic Computing Model of the Brain?


Title	Quantum-Inspired Computing: Can it be a Microscopic Computing Model of the Brain?
Authors	Yasunao Katayama
Abstract	Quantum computing and the workings of the brain have many aspects in common and have been attracting increasing attention in academia and industry. The computation in both is parallel and non-discrete. Though the underlying physical dynamics (e.g., equation of motion) may be deterministic, the observed or interpreted outcomes are often probabilistic. Consequently, various investigations have been undertaken to understand and reproduce the brain on the basis of quantum physics and computing. However, there have been arguments on whether the brain can and have to take advantage of quantum phenomena that need to survive in the macroscopic space-time region at room temperature. This paper presents a unique microscopic computational model for the brain based on an ansatz that the brain computes in a manner similar to quantum computing, but with classical waves. Log-scale encoding of information in the context of computing with waves is shown to play a critical role in bridging the computing models with classical and quantum waves. Our quantum-inspired computing model opens up a possibility of unifying the computing framework of artificial intelligence and quantum computing beyond quantum machine learning approaches.
Tasks	Quantum Machine Learning
Published	2019-04-11
URL	https://arxiv.org/abs/1904.10508v2
PDF	https://arxiv.org/pdf/1904.10508v2.pdf
PWC	https://paperswithcode.com/paper/190410508
Repo
Framework

The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine


Title	The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
Authors	Brian Coyle, Daniel Mills, Vincent Danos, Elham Kashefi
Abstract	The search for an application of near-term quantum devices is widespread. Quantum Machine Learning is touted as a potential utilisation of such devices, particularly those which are out of the reach of the simulation capabilities of classical computers. In this work, we propose a generative Quantum Machine Learning Model, called the Ising Born Machine (IBM), which we show cannot, in the worst case, and up to suitable notions of error, be simulated efficiently by a classical device. We also show this holds for all the circuit families encountered during training. In particular, we explore quantum circuit learning using non-universal circuits derived from Ising Model Hamiltonians, which are implementable on near term quantum devices. We propose two novel training methods for the IBM by utilising the Stein Discrepancy and the Sinkhorn Divergence cost functions. We show numerically, both using a simulator within Rigetti’s Forest platform and on the Aspen-1 16Q chip, that the cost functions we suggest outperform the more commonly used Maximum Mean Discrepancy (MMD) for differentiable training. We also propose an improvement to the MMD by proposing a novel utilisation of quantum kernels which we demonstrate provides improvements over its classical counterpart. We discuss the potential of these methods to learn `hard' quantum distributions, a feat which would demonstrate the advantage of quantum over classical computers, and provide the first formal definitions for what we call` Quantum Learning Supremacy’. Finally, we propose a novel view on the area of quantum circuit compilation by using the IBM to `mimic’ target quantum circuits using classical output data only. \|
Tasks	Quantum Machine Learning
Published	2019-04-03
URL	https://arxiv.org/abs/1904.02214v2
PDF	https://arxiv.org/pdf/1904.02214v2.pdf
PWC	https://paperswithcode.com/paper/the-born-supremacy-quantum-advantage-and
Repo
Framework

Unsupervised Bilingual Lexicon Induction from Mono-lingual Multimodal Data


Title	Unsupervised Bilingual Lexicon Induction from Mono-lingual Multimodal Data
Authors	Shizhe Chen, Qin Jin, Alexander Hauptmann
Abstract	Bilingual lexicon induction, translating words from the source language to the target language, is a long-standing natural language processing task. Recent endeavors prove that it is promising to employ images as pivot to learn the lexicon induction without reliance on parallel corpora. However, these vision-based approaches simply associate words with entire images, which are constrained to translate concrete words and require object-centered images. We humans can understand words better when they are within a sentence with context. Therefore, in this paper, we propose to utilize images and their associated captions to address the limitations of previous approaches. We propose a multi-lingual caption model trained with different mono-lingual multimodal data to map words in different languages into joint spaces. Two types of word representation are induced from the multi-lingual caption model: linguistic features and localized visual features. The linguistic feature is learned from the sentence contexts with visual semantic constraints, which is beneficial to learn translation for words that are less visual-relevant. The localized visual feature is attended to the region in the image that correlates to the word, so that it alleviates the image restriction for salient visual representation. The two types of features are complementary for word translation. Experimental results on multiple language pairs demonstrate the effectiveness of our proposed method, which substantially outperforms previous vision-based approaches without using any parallel sentences or supervision of seed word pairs.
Tasks
Published	2019-06-02
URL	https://arxiv.org/abs/1906.00378v1
PDF	https://arxiv.org/pdf/1906.00378v1.pdf
PWC	https://paperswithcode.com/paper/190600378
Repo
Framework

Simultaneous multi-view instance detection with learned geometric soft-constraints


Title	Simultaneous multi-view instance detection with learned geometric soft-constraints
Authors	Ahmed Samy Nassar, Sebastien Lefevre, Jan D. Wegner
Abstract	We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection. What makes multi-view object instance detection difficult are strong changes in viewpoint, lighting conditions, high similarity of neighbouring objects, and strong variability in scale. By turning object detection and instance re-identification in different views into a joint learning task, we are able to incorporate both image appearance and geometric soft constraints into a single, multi-view detection process that is learnable end-to-end. We validate our method on a new, large data set of street-level panoramas of urban objects and show superior performance compared to various baselines. Our contribution is threefold: a large-scale, publicly available data set for multi-view instance detection and re-identification; an annotation tool custom-tailored for multi-view instance detection; and a novel, holistic multi-view instance detection and re-identification method that jointly models geometry and appearance across views.
Tasks	Object Detection
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10892v1
PDF	https://arxiv.org/pdf/1907.10892v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-multi-view-instance-detection
Repo
Framework