October 19, 2019

3124 words 15 mins read

Paper Group ANR 381

Convolutional Geometric Matrix Completion. Parameter Transfer Unit for Deep Neural Networks. Random perturbation and matrix sparsification and completion. Static and Dynamic Robust PCA and Matrix Completion: A Review. Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form. Sliding Bidirectional Recurrent Neural …

Convolutional Geometric Matrix Completion


Title	Convolutional Geometric Matrix Completion
Authors	Kai-Lang Yao, Wu-Jun Li, Jianbo Yang, Xinyan Lu
Abstract	Geometric matrix completion (GMC) has been proposed for recommendation by integrating the relationship (link) graphs among users/items into matrix completion (MC). Traditional GMC methods typically adopt graph regularization to impose smoothness priors for MC. Recently, geometric deep learning on graphs (GDLG) is proposed to solve the GMC problem, showing better performance than existing GMC methods including traditional graph regularization based methods. To the best of our knowledge, there exists only one GDLG method for GMC, which is called RMGCNN. RMGCNN combines graph convolutional network (GCN) and recurrent neural network (RNN) together for GMC. In the original work of RMGCNN, RMGCNN demonstrates better performance than pure GCN-based method. In this paper, we propose a new GMC method, called convolutional geometric matrix completion (CGMC), for recommendation with graphs among users/items. CGMC is a pure GCN-based method with a newly designed graph convolutional network. Experimental results on real datasets show that CGMC can outperform other state-of-the-art methods including RMGCNN in terms of both accuracy and speed.
Tasks	Matrix Completion
Published	2018-03-02
URL	https://arxiv.org/abs/1803.00754v2
PDF	https://arxiv.org/pdf/1803.00754v2.pdf
PWC	https://paperswithcode.com/paper/convolutional-geometric-matrix-completion
Repo
Framework

Parameter Transfer Unit for Deep Neural Networks


Title	Parameter Transfer Unit for Deep Neural Networks
Authors	Yinghua Zhang, Yu Zhang, Qiang Yang
Abstract	Parameters in deep neural networks which are trained on large-scale databases can generalize across multiple domains, which is referred as “transferability”. Unfortunately, the transferability is usually defined as discrete states and it differs with domains and network architectures. Existing works usually heuristically apply parameter-sharing or fine-tuning, and there is no principled approach to learn a parameter transfer strategy. To address the gap, a parameter transfer unit (PTU) is proposed in this paper. The PTU learns a fine-grained nonlinear combination of activations from both the source and the target domain networks, and subsumes hand-crafted discrete transfer states. In the PTU, the transferability is controlled by two gates which are artificial neurons and can be learned from data. The PTU is a general and flexible module which can be used in both CNNs and RNNs. Experiments are conducted with various network architectures and multiple transfer domain pairs. Results demonstrate the effectiveness of the PTU as it outperforms heuristic parameter-sharing and fine-tuning in most settings.
Tasks
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08613v1
PDF	http://arxiv.org/pdf/1804.08613v1.pdf
PWC	https://paperswithcode.com/paper/parameter-transfer-unit-for-deep-neural
Repo
Framework

Random perturbation and matrix sparsification and completion


Title	Random perturbation and matrix sparsification and completion
Authors	Sean O’Rourke, Van Vu, Ke Wang
Abstract	We discuss general perturbation inequalities when the perturbation is random. As applications, we obtain several new results concerning two important problems: matrix sparsification and matrix completion.
Tasks	Matrix Completion
Published	2018-03-02
URL	http://arxiv.org/abs/1803.00679v1
PDF	http://arxiv.org/pdf/1803.00679v1.pdf
PWC	https://paperswithcode.com/paper/random-perturbation-and-matrix-sparsification
Repo
Framework

Static and Dynamic Robust PCA and Matrix Completion: A Review


Title	Static and Dynamic Robust PCA and Matrix Completion: A Review
Authors	Namrata Vaswani, Praneeth Narayanamurthy
Abstract	Principal Components Analysis (PCA) is one of the most widely used dimension reduction techniques. Robust PCA (RPCA) refers to the problem of PCA when the data may be corrupted by outliers. Recent work by Cand{`e}s, Wright, Li, and Ma defined RPCA as a problem of decomposing a given data matrix into the sum of a low-rank matrix (true data) and a sparse matrix (outliers). The column space of the low-rank matrix then gives the PCA solution. This simple definition has lead to a large amount of interesting new work on provably correct, fast, and practical solutions to RPCA. More recently, the dynamic (time-varying) version of the RPCA problem has been studied and a series of provably correct, fast, and memory efficient tracking solutions have been proposed. Dynamic RPCA (or robust subspace tracking) is the problem of tracking data lying in a (slowly) changing subspace while being robust to sparse outliers. This article provides an exhaustive review of the last decade of literature on RPCA and its dynamic counterpart (robust subspace tracking), along with describing their theoretical guarantees, discussing the pros and cons of various approaches, and providing empirical comparisons of performance and speed. A brief overview of the (low-rank) matrix completion literature is also provided (the focus is on works not discussed in other recent reviews). This refers to the problem of completing a low-rank matrix when only a subset of its entries are observed. It can be interpreted as a simpler special case of RPCA in which the indices of the outlier corrupted entries are known.
Tasks	Dimensionality Reduction, Low-Rank Matrix Completion, Matrix Completion
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00651v2
PDF	http://arxiv.org/pdf/1803.00651v2.pdf
PWC	https://paperswithcode.com/paper/static-and-dynamic-robust-pca-and-matrix
Repo
Framework

Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form


Title	Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form
Authors	Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli
Abstract	Semidefinite programs (SDP) are important in learning and combinatorial optimization with numerous applications. In pursuit of low-rank solutions and low complexity algorithms, we consider the Burer–Monteiro factorization approach for solving SDPs. We show that all approximate local optima are global optima for the penalty formulation of appropriately rank-constrained SDPs as long as the number of constraints scales sub-quadratically with the desired rank of the optimal solution. Our result is based on a simple penalty function formulation of the rank-constrained SDP along with a smoothed analysis to avoid worst-case cost matrices. We particularize our results to two applications, namely, Max-Cut and matrix completion.
Tasks	Combinatorial Optimization, Matrix Completion
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00186v1
PDF	http://arxiv.org/pdf/1803.00186v1.pdf
PWC	https://paperswithcode.com/paper/smoothed-analysis-for-low-rank-solutions-to
Repo
Framework

Sliding Bidirectional Recurrent Neural Networks for Sequence Detection in Communication Systems


Title	Sliding Bidirectional Recurrent Neural Networks for Sequence Detection in Communication Systems
Authors	Nariman Farsad, Andrea Goldsmith
Abstract	The design and analysis of communication systems typically rely on the development of mathematical models that describe the underlying communication channel. However, in some systems, such as molecular communication systems where chemical signals are used for transfer of information, the underlying channel models are unknown. In these scenarios, a completely new approach to design and analysis is required. In this work, we focus on one important aspect of communication systems, the detection algorithms, and demonstrate that by using tools from deep learning, it is possible to train detectors that perform well without any knowledge of the underlying channel models. We propose a technique we call sliding bidirectional recurrent neural network (SBRNN) for real-time sequence detection. We evaluate this algorithm using experimental data that is collected by a chemical communication platform, where the channel model is unknown and difficult to model analytically. We show that deep learning algorithms perform significantly better than a detector proposed in previous works, and the SBRNN outperforms other techniques considered in this work.
Tasks
Published	2018-02-19
URL	http://arxiv.org/abs/1802.08154v1
PDF	http://arxiv.org/pdf/1802.08154v1.pdf
PWC	https://paperswithcode.com/paper/sliding-bidirectional-recurrent-neural
Repo
Framework

Learning Latent Features with Pairwise Penalties in Low-Rank Matrix Completion


Title	Learning Latent Features with Pairwise Penalties in Low-Rank Matrix Completion
Authors	Kaiyi Ji, Jian Tan, Jinfeng Xu, Yuejie Chi
Abstract	Low-rank matrix completion has achieved great success in many real-world data applications. A matrix factorization model that learns latent features is usually employed and, to improve prediction performance, the similarities between latent variables can be exploited by pairwise learning using the graph regularized matrix factorization (GRMF) method. However, existing GRMF approaches often use the squared loss to measure the pairwise differences, which may be overly influenced by dissimilar pairs and lead to inferior prediction. To fully empower pairwise learning for matrix completion, we propose a general optimization framework that allows a rich class of (non-)convex pairwise penalty functions. A new and efficient algorithm is developed to solve the proposed optimization problem, with a theoretical convergence guarantee under mild assumptions. In an important situation where the latent variables form a small number of subgroups, its statistical guarantee is also fully considered. In particular, we theoretically characterize the performance of the complexity-regularized maximum likelihood estimator, as a special case of our framework, which is shown to have smaller errors when compared to the standard matrix completion framework without pairwise penalties. We conduct extensive experiments on both synthetic and real datasets to demonstrate the superior performance of this general framework.
Tasks	Low-Rank Matrix Completion, Matrix Completion
Published	2018-02-16
URL	https://arxiv.org/abs/1802.05821v2
PDF	https://arxiv.org/pdf/1802.05821v2.pdf
PWC	https://paperswithcode.com/paper/learning-latent-features-with-pairwise
Repo
Framework

Active Feature Acquisition with Supervised Matrix Completion


Title	Active Feature Acquisition with Supervised Matrix Completion
Authors	Sheng-Jun Huang, Miao Xu, Ming-Kun Xie, Masashi Sugiyama, Gang Niu, Songcan Chen
Abstract	Feature missing is a serious problem in many applications, which may lead to low quality of training data and further significantly degrade the learning performance. While feature acquisition usually involves special devices or complex process, it is expensive to acquire all feature values for the whole dataset. On the other hand, features may be correlated with each other, and some values may be recovered from the others. It is thus important to decide which features are most informative for recovering the other features as well as improving the learning performance. In this paper, we try to train an effective classification model with least acquisition cost by jointly performing active feature querying and supervised matrix completion. When completing the feature matrix, a novel target function is proposed to simultaneously minimize the reconstruction error on observed entries and the supervised loss on training data. When querying the feature value, the most uncertain entry is actively selected based on the variance of previous iterations. In addition, a bi-objective optimization method is presented for cost-aware active selection when features bear different acquisition costs. The effectiveness of the proposed approach is well validated by both theoretical analysis and experimental study.
Tasks	Matrix Completion
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05380v2
PDF	http://arxiv.org/pdf/1802.05380v2.pdf
PWC	https://paperswithcode.com/paper/active-feature-acquisition-with-supervised
Repo
Framework

Real Time Surveillance for Low Resolution and Limited-Data Scenarios: An Image Set Classification Approach


Title	Real Time Surveillance for Low Resolution and Limited-Data Scenarios: An Image Set Classification Approach
Authors	Uzair Nadeem, Syed Afaq Ali Shah, Mohammed Bennamoun, Roberto Togneri, Ferdous Sohel
Abstract	This paper proposes a novel image set classification technique based on the concept of linear regression. Unlike most other approaches, the proposed technique does not involve any training or feature extraction. The gallery image sets are represented as subspaces in a high dimensional space. Class specific gallery subspaces are used to estimate regression models for each image of the test image set. Images of the test set are then projected on the gallery subspaces. Residuals, calculated using the Euclidean distance between the original and the projected test images, are used as the distance metric. Three different strategies are devised to decide on the final class of the test image set. We performed extensive evaluations of the proposed technique under the challenges of low resolution, noise and less gallery data for the tasks of surveillance, video-based face recognition and object recognition. Experiments show that the proposed technique achieves a better classification accuracy and a faster execution time compared to existing techniques especially under the challenging conditions of low resolution and small gallery and test data.
Tasks	Face Recognition, Object Recognition
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09470v2
PDF	http://arxiv.org/pdf/1803.09470v2.pdf
PWC	https://paperswithcode.com/paper/real-time-surveillance-for-low-resolution-and
Repo
Framework

Revisiting Iterative Relevance Feedback for Document and Passage Retrieval


Title	Revisiting Iterative Relevance Feedback for Document and Passage Retrieval
Authors	Keping Bi, Qingyao Ai, W. Bruce Croft
Abstract	As more and more search traffic comes from mobile phones, intelligent assistants, and smart-home devices, new challenges (e.g., limited presentation space) and opportunities come up in information retrieval. Previously, an effective technique, relevance feedback (RF), has rarely been used in real search scenarios due to the overhead of collecting users’ relevance judgments. However, since users tend to interact more with the search results shown on the new interfaces, it becomes feasible to obtain users’ assessments on a few results during each interaction. This makes iterative relevance feedback (IRF) techniques look promising today. IRF has not been studied systematically in the new search scenarios and its effectiveness is mostly unknown. In this paper, we re-visit IRF and extend it with RF models proposed in recent years. We conduct extensive experiments to analyze and compare IRF with the standard top-k RF framework on document and passage retrieval. Experimental results show that IRF is at least as effective as the standard top-k RF framework for documents and much more effective for passages. This indicates that IRF for passage retrieval has huge potential.
Tasks	Information Retrieval
Published	2018-12-13
URL	https://arxiv.org/abs/1812.05731v3
PDF	https://arxiv.org/pdf/1812.05731v3.pdf
PWC	https://paperswithcode.com/paper/revisiting-iterative-relevance-feedback-for
Repo
Framework

Practical Constrained Optimization of Auction Mechanisms in E-Commerce Sponsored Search Advertising


Title	Practical Constrained Optimization of Auction Mechanisms in E-Commerce Sponsored Search Advertising
Authors	Gang Bai, Zhihui Xie, Liang Wang
Abstract	Sponsored search in E-commerce platforms such as Amazon, Taobao and Tmall provides sellers an effective way to reach potential buyers with most relevant purpose. In this paper, we study the auction mechanism optimization problem in sponsored search on Alibaba’s mobile E-commerce platform. Besides generating revenue, we are supposed to maintain an efficient marketplace with plenty of quality users, guarantee a reasonable return on investment (ROI) for advertisers, and meanwhile, facilitate a pleasant shopping experience for the users. These requirements essentially pose a constrained optimization problem. Directly optimizing over auction parameters yields a discontinuous, non-convex problem that denies effective solutions. One of our major contribution is a practical convex optimization formulation of the original problem. We devise a novel re-parametrization of auction mechanism with discrete sets of representative instances. To construct the optimization problem, we build an auction simulation system which estimates the resulted business indicators of the selected parameters by replaying the auctions recorded from real online requests. We summarized the experiments on real search traffics to analyze the effects of fidelity of auction simulation, the efficacy under various constraint targets and the influence of regularization. The experiment results show that with proper entropy regularization, we are able to maximize revenue while constraining other business indicators within given ranges.
Tasks
Published	2018-07-31
URL	http://arxiv.org/abs/1807.11790v1
PDF	http://arxiv.org/pdf/1807.11790v1.pdf
PWC	https://paperswithcode.com/paper/practical-constrained-optimization-of-auction
Repo
Framework

Deep Learning Architect: Classification for Architectural Design through the Eye of Artificial Intelligence


Title	Deep Learning Architect: Classification for Architectural Design through the Eye of Artificial Intelligence
Authors	Yuji Yoshimura, Bill Cai, Zhoutong Wang, Carlo Ratti
Abstract	This paper applies state-of-the-art techniques in deep learning and computer vision to measure visual similarities between architectural designs by different architects. Using a dataset consisting of web scraped images and an original collection of images of architectural works, we first train a deep convolutional neural network (DCNN) model capable of achieving 73% accuracy in classifying works belonging to 34 different architects. Through examining the weights in the trained DCNN model, we are able to quantitatively measure the visual similarities between architects that are implicitly learned by our model. Using this measure, we cluster architects that are identified to be similar and compare our findings to conventional classification made by architectural historians and theorists. Our clustering of architectural designs remarkably corroborates conventional views in architectural history, and the learned architectural features also coheres with the traditional understanding of architectural designs.
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.01714v1
PDF	http://arxiv.org/pdf/1812.01714v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-architect-classification-for
Repo
Framework

Augmented Mitotic Cell Count using Field Of Interest Proposal


Title	Augmented Mitotic Cell Count using Field Of Interest Proposal
Authors	Marc Aubreville, Christof A. Bertram, Robert Klopfleisch, Andreas Maier
Abstract	Histopathological prognostication of neoplasia including most tumor grading systems are based upon a number of criteria. Probably the most important is the number of mitotic figures which are most commonly determined as the mitotic count (MC), i.e. number of mitotic figures within 10 consecutive high power fields. Often the area with the highest mitotic activity is to be selected for the MC. However, since mitotic activity is not known in advance, an arbitrary choice of this region is considered one important cause for high variability in the prognostication and grading. In this work, we present an algorithmic approach that first calculates a mitotic cell map based upon a deep convolutional network. This map is in a second step used to construct a mitotic activity estimate. Lastly, we select the image segment representing the size of ten high power fields with the overall highest mitotic activity as a region proposal for an expert MC determination. We evaluate the approach using a dataset of 32 completely annotated whole slide images, where 22 were used for training of the network and 10 for test. We find a correlation of r=0.936 in mitotic count estimate.
Tasks
Published	2018-10-01
URL	http://arxiv.org/abs/1810.00850v1
PDF	http://arxiv.org/pdf/1810.00850v1.pdf
PWC	https://paperswithcode.com/paper/augmented-mitotic-cell-count-using-field-of
Repo
Framework

S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation


Title	S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation
Authors	Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit
Abstract	We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views. More exactly, image locations corresponding to the same physical 3D point should all have the same label. We show that introducing such constraints during learning is very effective, even when no manual label is available for a 3D point, and can be done simply by employing techniques from ‘general’ semi-supervised learning to the context of semantic segmentation. To demonstrate this idea, we use RGB-D image sequences of rigid scenes, for a 4-class segmentation problem derived from the ScanNet dataset. Starting from RGB-D sequences with a few annotated frames, we show that we can incorporate RGB-D sequences without any manual annotations to improve the performance, which makes our approach very convenient. Furthermore, we demonstrate our approach for semantic segmentation of objects on the LabelFusion dataset, where we show that one manually labeled image in a scene is sufficient for high performance on the whole scene.
Tasks	Semantic Segmentation, Semi-Supervised Semantic Segmentation
Published	2018-12-27
URL	http://arxiv.org/abs/1812.10717v2
PDF	http://arxiv.org/pdf/1812.10717v2.pdf
PWC	https://paperswithcode.com/paper/s4-net-geometry-consistent-semi-supervised
Repo
Framework

The Rapidly Changing Landscape of Conversational Agents


Title	The Rapidly Changing Landscape of Conversational Agents
Authors	Vinayak Mathur, Arpit Singh
Abstract	Conversational agents have become ubiquitous, ranging from goal-oriented systems for helping with reservations to chit-chat models found in modern virtual assistants. In this survey paper, we explore this fascinating field. We look at some of the pioneering work that defined the field and gradually move to the current state-of-the-art models. We look at statistical, neural, generative adversarial network based and reinforcement learning based approaches and how they evolved. Along the way we discuss various challenges that the field faces, lack of context in utterances, not having a good quantitative metric to compare models, lack of trust in agents because they do not have a consistent persona etc. We structure this paper in a way that answers these pertinent questions and discusses competing approaches to solve them.
Tasks
Published	2018-03-22
URL	http://arxiv.org/abs/1803.08419v2
PDF	http://arxiv.org/pdf/1803.08419v2.pdf
PWC	https://paperswithcode.com/paper/the-rapidly-changing-landscape-of
Repo
Framework