January 26, 2020

3444 words 17 mins read

Paper Group ANR 1374

Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems. Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults. Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents. Reinforcement Lea …

Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems


Title	Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems
Authors	Zijian Li, Ruichu Cai, Kok Soon Chai, Hong Wei Ng, Hoang Dung Vu, Marianne Winslett, Tom Z. J. Fu, Boyan Xu, Xiaoyan Yang, Zhenjie Zhang
Abstract	Data-driven models are becoming essential parts in modern mechanical systems, commonly used to capture the behavior of various equipment and varying environmental characteristics. Despite the advantages of these data-driven models on excellent adaptivity to high dynamics and aging equipment, they are usually hungry to massive labels over historical data, mostly contributed by human engineers at an extremely high cost. The label demand is now the major limiting factor to modeling accuracy, hindering the fulfillment of visions for applications. Fortunately, domain adaptation enhances the model generalization by utilizing the labelled source data as well as the unlabelled target data and then we can reuse the model on different domains. However, the mainstream domain adaptation methods cannot achieve ideal performance on time series data, because most of them focus on static samples and even the existing time series domain adaptation methods ignore the properties of time series data, such as temporal causal mechanism. In this paper, we assume that causal mechanism is invariant and present our Causal Mechanism Transfer Network(CMTN) for time series domain adaptation. By capturing and transferring the dynamic and temporal causal mechanism of multivariate time series data and alleviating the time lags and different value ranges among different machines, CMTN allows the data-driven models to exploit existing data and labels from similar systems, such that the resulting model on a new system is highly reliable even with very limited data. We report our empirical results and lessons learned from two real-world case studies, on chiller plant energy optimization and boiler fault detection, which outperforms the existing state-of-the-art method.
Tasks	Domain Adaptation, Fault Detection, Time Series
Published	2019-10-13
URL	https://arxiv.org/abs/1910.06761v1
PDF	https://arxiv.org/pdf/1910.06761v1.pdf
PWC	https://paperswithcode.com/paper/causal-mechanism-transfer-network-for-time
Repo
Framework

Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults


Title	Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults
Authors	Baihong Jin, Yingshui Tan, Yuxin Chen, Alberto Sangiovanni-Vincentelli
Abstract	The Monte Carlo dropout method has proved to be a scalable and easy-to-use approach for estimating the uncertainty of deep neural network predictions. This approach was recently applied to Fault Detection and Di-agnosis (FDD) applications to improve the classification performance on incipient faults. In this paper, we propose a novel approach of augmenting the classification model with an additional unsupervised learning task. We justify our choice of algorithm design via an information-theoretical analysis. Our experimental results on three datasets from diverse application domains show that the proposed method leads to improved fault detection and diagnosis performance, especially on out-of-distribution examples including both incipient and unknown faults.
Tasks	Fault Detection
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04202v1
PDF	https://arxiv.org/pdf/1909.04202v1.pdf
PWC	https://paperswithcode.com/paper/augmenting-monte-carlo-dropout-classification
Repo
Framework

Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents


Title	Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents
Authors	Ming Tu, Kevin Huang, Guangtao Wang, Jing Huang, Xiaodong He, Bowen Zhou
Abstract	Interpretable multi-hop reading comprehension (RC) over multiple documents is a challenging problem because it demands reasoning over multiple information sources and explaining the answer prediction by providing supporting evidences. In this paper, we propose an effective and interpretable Select, Answer and Explain (SAE) system to solve the multi-document RC problem. Our system first filters out answer-unrelated documents and thus reduce the amount of distraction information. This is achieved by a document classifier trained with a novel pairwise learning-to-rank loss. The selected answer-related documents are then input to a model to jointly predict the answer and supporting sentences. The model is optimized with a multi-task learning objective on both token level for answer prediction and sentence level for supporting sentences prediction, together with an attention-based interaction between these two tasks. Evaluated on HotpotQA, a challenging multi-hop RC data set, the proposed SAE system achieves top competitive performance in distractor setting compared to other existing systems on the leaderboard.
Tasks	Learning-To-Rank, Multi-Hop Reading Comprehension, Multi-Task Learning, Reading Comprehension
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00484v4
PDF	https://arxiv.org/pdf/1911.00484v4.pdf
PWC	https://paperswithcode.com/paper/select-answer-and-explain-interpretable-multi
Repo
Framework

Reinforcement Learning with Non-Markovian Rewards


Title	Reinforcement Learning with Non-Markovian Rewards
Authors	Mridul Agarwal, Vaneet Aggarwal
Abstract	Reinforcement Learning (RL) algorithms such as DQN owe their success to Markov Decision Processes, and the fact that maximizing the sum of rewards allows using backward induction and reduce to the Bellman optimality equation. However, many real-world problems require optimization of an objective that is non-linear in cumulative rewards for which dynamic programming cannot be applied directly. For example, in a resource allocation problem, one of the objectives is to maximize long-term fairness among the users. We notice that when the function of the sum of rewards is considered, the problem loses its Markov nature. This paper addresses and formalizes the problem of optimizing a non-linear function of the long term average of rewards. We propose model-based and model-free algorithms to learn the policy, where the model-based policy is shown to achieve a regret of $\widetilde{O}\left(\sqrt{\frac{K}{T}}\right)$ for $K$ users. Further, using the fairness in cellular base-station scheduling, and queueing system scheduling as examples, the proposed algorithm is shown to significantly outperform the conventional RL approaches.
Tasks	Decision Making
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02940v2
PDF	https://arxiv.org/pdf/1909.02940v2.pdf
PWC	https://paperswithcode.com/paper/a-reinforcement-learning-based-approach-for
Repo
Framework

Open-Set Recognition Using Intra-Class Splitting


Title	Open-Set Recognition Using Intra-Class Splitting
Authors	Patrick Schlachter, Yiwen Liao, Bin Yang
Abstract	This paper proposes a method to use deep neural networks as end-to-end open-set classifiers. It is based on intra-class data splitting. In open-set recognition, only samples from a limited number of known classes are available for training. During inference, an open-set classifier must reject samples from unknown classes while correctly classifying samples from known classes. The proposed method splits given data into typical and atypical normal subsets by using a closed-set classifier. This enables to model the abnormal classes by atypical normal samples. Accordingly, the open-set recognition problem is reformulated into a traditional classification problem. In addition, a closed-set regularization is proposed to guarantee a high closed-set classification performance. Intensive experiments on five well-known image datasets showed the effectiveness of the proposed method which outperformed the baselines and achieved a distinct improvement over the state-of-the-art methods.
Tasks	Open Set Learning
Published	2019-03-12
URL	https://arxiv.org/abs/1903.04774v3
PDF	https://arxiv.org/pdf/1903.04774v3.pdf
PWC	https://paperswithcode.com/paper/open-set-recognition-using-intra-class
Repo
Framework

EPOSIT: An Absolute Pose Estimation Method for Pinhole and Fish-Eye Cameras


Title	EPOSIT: An Absolute Pose Estimation Method for Pinhole and Fish-Eye Cameras
Authors	Zhaobing Kang, Wei Zou, Zheng Zhu, Chi Zhang, Hongxuan Ma
Abstract	This paper presents a generic 6DOF camera pose estimation method, which can be used for both the pinhole camera and the fish-eye camera. Different from existing methods, relative positions of 3D points rather than absolute coordinates in the world coordinate system are employed in our method, and it has a unique solution. The application scope of POSIT (Pose from Orthography and Scaling with Iteration) algorithm is generalized to fish-eye cameras by combining with the radially symmetric projection model. The image point relationship between the pinhole camera and the fish-eye camera is derived based on their projection model. The general pose expression which fits for different cameras can be acquired by four noncoplanar object points and their corresponding image points. Accurate estimation results are calculated iteratively. Experimental results on synthetic and real data show that the pose estimation results of our method are more stable and accurate than state-of-the-art methods. The source code is available at https://github.com/k032131/EPOSIT.
Tasks	Pose Estimation
Published	2019-09-19
URL	https://arxiv.org/abs/1909.12945v1
PDF	https://arxiv.org/pdf/1909.12945v1.pdf
PWC	https://paperswithcode.com/paper/eposit-an-absolute-pose-estimation-method-for
Repo
Framework

Hebbian Graph Embeddings


Title	Hebbian Graph Embeddings
Authors	Shalin Shah, Venkataramana Kini
Abstract	Representation learning has recently been successfully used to create vector representations of entities in language learning, recommender systems and in similarity learning. Graph embeddings exploit the locality structure of a graph and generate embeddings for nodes which could be words in a language, products of a retail website; and the nodes are connected based on a context window. In this paper, we consider graph embeddings with an error-free associative learning update rule, which models the embedding vector of node as a non-convex Gaussian mixture of the embeddings of the nodes in its immediate vicinity with some constant variance that is reduced as iterations progress. It is very easy to parallelize our algorithm without any form of shared memory, which makes it possible to use it on very large graphs with a much higher dimensionality of the embeddings. We study the efficacy of proposed method on several benchmark data sets and favorably compare with state of the art methods. Further, proposed method is applied to generate relevant recommendations for a large retailer.
Tasks	Recommendation Systems, Representation Learning
Published	2019-08-21
URL	https://arxiv.org/abs/1908.08037v4
PDF	https://arxiv.org/pdf/1908.08037v4.pdf
PWC	https://paperswithcode.com/paper/hebbian-graph-embeddings
Repo
Framework

Nonconvex Low-Rank Symmetric Tensor Completion from Noisy Data


Title	Nonconvex Low-Rank Symmetric Tensor Completion from Noisy Data
Authors	Changxiao Cai, Gen Li, H. Vincent Poor, Yuxin Chen
Abstract	We study a noisy symmetric tensor completion problem of broad practical interest, namely, the reconstruction of a low-rank symmetric tensor from highly incomplete and randomly corrupted observations of its entries. While a variety of prior work has been dedicated to this problem, prior algorithms either are computationally too expensive for large-scale applications, or come with sub-optimal statistical guarantees. Focusing on “incoherent” and well-conditioned tensors of a constant CP rank, we propose a two-stage nonconvex algorithm — (vanilla) gradient descent following a rough initialization — that achieves the best of both worlds. Specifically, the proposed nonconvex algorithm faithfully completes the tensor and retrieves all individual tensor factors within nearly linear time, while at the same time enjoying near-optimal statistical guarantees (i.e. minimal sample complexity and optimal estimation accuracy). The estimation errors are evenly spread out across all entries, thus achieving optimal $\ell_{\infty}$ statistical accuracy. The insight conveyed through our analysis of nonconvex optimization might have implications for other tensor estimation problems.
Tasks
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04436v1
PDF	https://arxiv.org/pdf/1911.04436v1.pdf
PWC	https://paperswithcode.com/paper/nonconvex-low-rank-symmetric-tensor
Repo
Framework

DSL: Discriminative Subgraph Learning via Sparse Self-Representation


Title	DSL: Discriminative Subgraph Learning via Sparse Self-Representation
Authors	Lin Zhang, Petko Bogdanov
Abstract	The goal in network state prediction (NSP) is to classify the global state (label) associated with features embedded in a graph. This graph structure encoding feature relationships is the key distinctive aspect of NSP compared to classical supervised learning. NSP arises in various applications: gene expression samples embedded in a protein-protein interaction (PPI) network, temporal snapshots of infrastructure or sensor networks, and fMRI coherence network samples from multiple subjects to name a few. Instances from these domains are typically ``wide’’ (more features than samples), and thus, feature sub-selection is required for robust and generalizable prediction. How to best employ the network structure in order to learn succinct connected subgraphs encompassing the most discriminative features becomes a central challenge in NSP. Prior work employs connected subgraph sampling or graph smoothing within optimization frameworks, resulting in either large variance of quality or weak control over the connectivity of selected subgraphs. In this work we propose an optimization framework for discriminative subgraph learning (DSL) which simultaneously enforces (i) sparsity, (ii) connectivity and (iii) high discriminative power of the resulting subgraphs of features. Our optimization algorithm is a single-step solution for the NSP and the associated feature selection problem. It is rooted in the rich literature on maximal-margin optimization, spectral graph methods and sparse subspace self-representation. DSL simultaneously ensures solution interpretability and superior predictive power (up to 16% improvement in challenging instances compared to baselines), with execution times up to an hour for large instances. \|
Tasks	Feature Selection
Published	2019-03-24
URL	http://arxiv.org/abs/1904.00791v1
PDF	http://arxiv.org/pdf/1904.00791v1.pdf
PWC	https://paperswithcode.com/paper/dsl-discriminative-subgraph-learning-via
Repo
Framework

Multi-label Classification for Fault Diagnosis of Rotating Electrical Machines


Title	Multi-label Classification for Fault Diagnosis of Rotating Electrical Machines
Authors	Adrienn Dineva, Amir Mosavi, Mate Gyimesi, Istvan Vajda
Abstract	Primary importance is devoted to Fault Detection and Diagnosis (FDI) of electrical machine and drive systems in modern industrial automation. The widespread use of Machine Learning techniques has made it possible to replace traditional motor fault detection techniques with more efficient solutions that are capable of early fault recognition by using large amounts of sensory data. However, the detection of concurrent failures is still a challenge in the presence of disturbing noises or when the multiple faults cause overlapping features. The contribution of this work is to propose a novel methodology using multi-label classification method for simultaneously diagnosing multiple faults and evaluating the fault severity under noisy conditions. Performance of various multi-label classification models are compared. Current and vibration signals are acquired under normal and fault conditions. The applicability of the proposed method is experimentally validated under diverse fault conditions such as unbalance and misalignment.
Tasks	Fault Detection, Multi-Label Classification
Published	2019-08-02
URL	https://arxiv.org/abs/1908.01078v1
PDF	https://arxiv.org/pdf/1908.01078v1.pdf
PWC	https://paperswithcode.com/paper/multi-label-classification-for-fault
Repo
Framework

HOnnotate: A method for 3D Annotation of Hand and Objects Poses


Title	HOnnotate: A method for 3D Annotation of Hand and Objects Poses
Authors	Shreyas Hampali, Mahdi Rad, Markus Oberweger, Vincent Lepetit
Abstract	We propose a method for annotating images of a hand manipulating an object with the 3D poses of both the hand and the object, together with a dataset created using this method. There is a current lack of annotated real images for this problem, as estimating the 3D poses is challenging, mostly because of the mutual occlusions between the hand and the object. To tackle this challenge, we capture sequences with one or several RGB-D cameras, and jointly optimizes the 3D hand and object poses over all the frames simultaneously. This method allows us to automatically annotate each frame with accurate estimates of the poses, despite large mutual occlusions. With this method, we created HO-3D, the first markerless dataset of color images with 3D annotations of both hand and object. This dataset is currently made of 80,000 frames, 65 sequences, 10 persons, and 10 objects, and growing. We also use it to train a deepnet to perform RGB-based single frame hand pose estimation and provide a baseline on our dataset.
Tasks	Hand Pose Estimation, Pose Estimation, Pose Prediction
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01481v4
PDF	https://arxiv.org/pdf/1907.01481v4.pdf
PWC	https://paperswithcode.com/paper/ho-3d-a-multi-user-multi-object-dataset-for
Repo
Framework

Knee menisci segmentation and relaxometry of 3D ultrashort echo time (UTE) cones MR imaging using attention U-Net with transfer learning


Title	Knee menisci segmentation and relaxometry of 3D ultrashort echo time (UTE) cones MR imaging using attention U-Net with transfer learning
Authors	Michal Byra, Mei Wu, Xiaodong Zhang, Hyungseok Jang, Ya-Jun Ma, Eric Y Chang, Sameer Shah, Jiang Du
Abstract	The purpose of this work is to develop a deep learning-based method for knee menisci segmentation in 3D ultrashort echo time (UTE) cones magnetic resonance (MR) imaging, and to automatically determine MR relaxation times, namely the T1, T1$\rho$, and T2* parameters, which can be used to assess knee osteoarthritis (OA). Whole knee joint imaging was performed using 3D UTE cones sequences to collect data from 61 human subjects. Regions of interest (ROIs) were outlined by two experienced radiologists based on subtracted T1$\rho$-weighted MR images. Transfer learning was applied to develop 2D attention U-Net convolutional neural networks for the menisci segmentation based on each radiologist’s ROIs separately. Dice scores were calculated to assess segmentation performance. Next, the T1, T1$\rho$, T2* relaxations, and ROI areas were determined for the manual and automatic segmentations, then compared.The models developed using ROIs provided by two radiologists achieved high Dice scores of 0.860 and 0.833, while the radiologists’ manual segmentations achieved a Dice score of 0.820. Linear correlation coefficients for the T1, T1$\rho$, and T2* relaxations calculated using the automatic and manual segmentations ranged between 0.90 and 0.97, and there were no associated differences between the estimated average meniscal relaxation parameters. The deep learning models achieved segmentation performance equivalent to the inter-observer variability of two radiologists. The proposed deep learning-based approach can be used to efficiently generate automatic segmentations and determine meniscal relaxations times. The method has the potential to help radiologists with the assessment of meniscal diseases, such as OA.
Tasks	Transfer Learning
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01594v1
PDF	https://arxiv.org/pdf/1908.01594v1.pdf
PWC	https://paperswithcode.com/paper/knee-menisci-segmentation-and-relaxometry-of
Repo
Framework

UniGrasp: Learning a Unified Model to Grasp with N-Fingered Robotic Hands


Title	UniGrasp: Learning a Unified Model to Grasp with N-Fingered Robotic Hands
Authors	Lin Shao, Fabio Ferreira, Mikael Jorda, Varun Nambiar, Jianlan Luo, Eugen Solowjow, Juan Aparicio Ojea, Oussama Khatib, Jeannette Bohg
Abstract	To achieve a successful grasp, gripper attributes including geometry and kinematics play a role equally important to the target object geometry. The majority of previous work has focused on developing grasp methods that generalize over novel object geometry but are specific to a certain robot hand. We propose UniGrasp, an efficient data-driven grasp synthesis method that considers both the object geometry and gripper attributes as inputs. UniGrasp is based on a novel deep neural network architecture that selects sets of contact points from the input point cloud of the object. The proposed model is trained on a large dataset to produce contact points that are in force closure and reachable by the robot hand. By using contact points as output, we can transfer between a diverse set of N-fingered robotic hands. Our model produces over 90 percent valid contact points in Top10 predictions in simulation and more than 90 percent successful grasps in the real world experiments for various known two-fingered and three-fingered grippers. Our model also achieves 93 percent and 83 percent successful grasps in the real world experiments for a novel two-fingered and five-fingered anthropomorphic robotic hand, respectively.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10900v1
PDF	https://arxiv.org/pdf/1910.10900v1.pdf
PWC	https://paperswithcode.com/paper/unigrasp-learning-a-unified-model-to-grasp
Repo
Framework

DeepLO: Geometry-Aware Deep LiDAR Odometry


Title	DeepLO: Geometry-Aware Deep LiDAR Odometry
Authors	Younggun Cho, Giseop Kim, Ayoung Kim
Abstract	Recently, learning-based ego-motion estimation approaches have drawn strong interest from studies mostly focusing on visual perception. These groundbreaking works focus on unsupervised learning for odometry estimation but mostly for visual sensors. Compared to images, a learning-based approach using Light Detection and Ranging (LiDAR) has been reported in a few studies where, most often, a supervised learning framework is proposed. In this paper, we propose a novel approach to geometry-aware deep LiDAR odometry trainable via both supervised and unsupervised frameworks. We incorporate the Iterated Closest Point (ICP) algorithm into a deep-learning framework and show the reliability of the proposed pipeline. We provide two loss functions that allow switching between supervised and unsupervised learning depending on the ground-truth validity in the training phase. An evaluation using the KITTI and Oxford RobotCar dataset demonstrates the prominent performance and efficiency of the proposed method when achieving pose accuracy.
Tasks	Motion Estimation
Published	2019-02-27
URL	http://arxiv.org/abs/1902.10562v1
PDF	http://arxiv.org/pdf/1902.10562v1.pdf
PWC	https://paperswithcode.com/paper/deeplo-geometry-aware-deep-lidar-odometry
Repo
Framework

Generating Realistic Sequences of Customer-level Transactions for Retail Datasets


Title	Generating Realistic Sequences of Customer-level Transactions for Retail Datasets
Authors	Thang Doan, Neil Veira, Saibal Ray, Brian Keng
Abstract	In order to better engage with customers, retailers rely on extensive customer and product databases which allows them to better understand customer behaviour and purchasing patterns. This has long been a challenging task as customer modelling is a multi-faceted, noisy and time-dependent problem. The most common way to tackle this problem is indirectly through task-specific supervised learning prediction problems, with relatively little literature on modelling a customer by directly simulating their future transactions. In this paper we propose a method for generating realistic sequences of baskets that a given customer is likely to purchase over a period of time. Customer embedding representations are learned using a Recurrent Neural Network (RNN) which takes into account the entire sequence of transaction data. Given the customer state at a specific point in time, a Generative Adversarial Network (GAN) is trained to generate a plausible basket of products for the following week. The newly generated basket is then fed back into the RNN to update the customer’s state. The GAN is thus used in tandem with the RNN module in a pipeline alternating between basket generation and customer state updating steps. This allows for sampling over a distribution of a customer’s future sequence of baskets, which then can be used to gain insight into how to service the customer more effectively. The methodology is empirically shown to produce baskets that appear similar to real baskets and enjoy many common properties, including frequencies of different product types, brands, and prices. Furthermore, the generated data is able to replicate most of the strongest sequential patterns that exist between product types in the real data.
Tasks
Published	2019-01-17
URL	https://arxiv.org/abs/1901.05577v2
PDF	https://arxiv.org/pdf/1901.05577v2.pdf
PWC	https://paperswithcode.com/paper/generating-realistic-sequences-of-customer
Repo
Framework