Paper Group ANR 205
Understanding Priors in Bayesian Neural Networks at the Unit Level. Learning $3$D-FilterMap for Deep Convolutional Neural Networks. Heuristics for Efficient Sparse Blind Source Separation. Event Detection with Neural Networks: A Rigorous Empirical Evaluation. Deep Reinforcement Learning for Sponsored Search Real-time Bidding. Collaborative Filterin …
Understanding Priors in Bayesian Neural Networks at the Unit Level
| Title | Understanding Priors in Bayesian Neural Networks at the Unit Level |
| Authors | Mariia Vladimirova, Jakob Verbeek, Pablo Mesejo, Julyan Arbel |
| Abstract | We investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities. Bayesian neural networks with Gaussian priors are well known to induce an L2, “weight decay”, regularization. Our results characterize a more intricate regularization effect at the level of the unit activations. Our main result establishes that the induced prior distribution on the units before and after activation becomes increasingly heavy-tailed with the depth of the layer. We show that first layer units are Gaussian, second layer units are sub-exponential, and units in deeper layers are characterized by sub-Weibull distributions. Our results provide new theoretical insight on deep Bayesian neural networks, which we corroborate with simulation experiments. |
| Tasks | |
| Published | 2018-10-11 |
| URL | https://arxiv.org/abs/1810.05193v2 |
| https://arxiv.org/pdf/1810.05193v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-neural-networks-increasingly |
| Repo | |
| Framework | |
Learning $3$D-FilterMap for Deep Convolutional Neural Networks
| Title | Learning $3$D-FilterMap for Deep Convolutional Neural Networks |
| Authors | Yingzhen Yang, Jianchao Yang, Ning Xu, Wei Han |
| Abstract | We present a novel and compact architecture for deep Convolutional Neural Networks (CNNs) in this paper, termed $3$D-FilterMap Convolutional Neural Networks ($3$D-FM-CNNs). The convolution layer of $3$D-FM-CNN learns a compact representation of the filters, named $3$D-FilterMap, instead of a set of independent filters in the conventional convolution layer. The filters are extracted from the $3$D-FilterMap as overlapping $3$D submatrics with weight sharing among nearby filters, and these filters are convolved with the input to generate the output of the convolution layer for $3$D-FM-CNN. Due to the weight sharing scheme, the parameter size of the $3$D-FilterMap is much smaller than that of the filters to be learned in the conventional convolution layer when $3$D-FilterMap generates the same number of filters. Our work is fundamentally different from the network compression literature that reduces the size of a learned large network in the sense that a small network is directly learned from scratch. Experimental results demonstrate that $3$D-FM-CNN enjoys a small parameter space by learning compact $3$D-FilterMaps, while achieving performance compared to that of the baseline CNNs which learn the same number of filters as that generated by the corresponding $3$D-FilterMap. |
| Tasks | |
| Published | 2018-01-05 |
| URL | http://arxiv.org/abs/1801.01609v1 |
| http://arxiv.org/pdf/1801.01609v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-3d-filtermap-for-deep-convolutional |
| Repo | |
| Framework | |
Heuristics for Efficient Sparse Blind Source Separation
| Title | Heuristics for Efficient Sparse Blind Source Separation |
| Authors | Christophe Kervazo, Jerome Bobin, Cecile Chenot |
| Abstract | Sparse Blind Source Separation (sparse BSS) is a key method to analyze multichannel data in fields ranging from medical imaging to astrophysics. However, since it relies on seeking the solution of a non-convex penalized matrix factorization problem, its performances largely depend on the optimization strategy. In this context, Proximal Alternating Linearized Minimization (PALM) has become a standard algorithm which, despite its theoretical grounding, generally provides poor practical separation results. In this work, we propose a novel strategy that combines a heuristic approach with PALM. We show its relevance on realistic astrophysical data. |
| Tasks | |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1812.06737v1 |
| http://arxiv.org/pdf/1812.06737v1.pdf | |
| PWC | https://paperswithcode.com/paper/heuristics-for-efficient-sparse-blind-source |
| Repo | |
| Framework | |
Event Detection with Neural Networks: A Rigorous Empirical Evaluation
| Title | Event Detection with Neural Networks: A Rigorous Empirical Evaluation |
| Authors | J. Walker Orr, Prasad Tadepalli, Xiaoli Fern |
| Abstract | Detecting events and classifying them into predefined types is an important step in knowledge extraction from natural language texts. While the neural network models have generally led the state-of-the-art, the differences in performance between different architectures have not been rigorously studied. In this paper we present a novel GRU-based model that combines syntactic information along with temporal structure through an attention mechanism. We show that it is competitive with other neural network architectures through empirical evaluations under different random initializations and training-validation-test splits of ACE2005 dataset. |
| Tasks | |
| Published | 2018-08-26 |
| URL | http://arxiv.org/abs/1808.08504v1 |
| http://arxiv.org/pdf/1808.08504v1.pdf | |
| PWC | https://paperswithcode.com/paper/event-detection-with-neural-networks-a |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Sponsored Search Real-time Bidding
| Title | Deep Reinforcement Learning for Sponsored Search Real-time Bidding |
| Authors | Jun Zhao, Guang Qiu, Ziyu Guan, Wei Zhao, Xiaofei He |
| Abstract | Bidding optimization is one of the most critical problems in online advertising. Sponsored search (SS) auction, due to the randomness of user query behavior and platform nature, usually adopts keyword-level bidding strategies. In contrast, the display advertising (DA), as a relatively simpler scenario for auction, has taken advantage of real-time bidding (RTB) to boost the performance for advertisers. In this paper, we consider the RTB problem in sponsored search auction, named SS-RTB. SS-RTB has a much more complex dynamic environment, due to stochastic user query behavior and more complex bidding policies based on multiple keywords of an ad. Most previous methods for DA cannot be applied. We propose a reinforcement learning (RL) solution for handling the complex dynamic environment. Although some RL methods have been proposed for online advertising, they all fail to address the “environment changing” problem: the state transition probabilities vary between two days. Motivated by the observation that auction sequences of two days share similar transition patterns at a proper aggregation level, we formulate a robust MDP model at hour-aggregation level of the auction data and propose a control-by-model framework for SS-RTB. Rather than generating bid prices directly, we decide a bidding model for impressions of each hour and perform real-time bidding accordingly. We also extend the method to handle the multi-agent problem. We deployed the SS-RTB system in the e-commerce search auction platform of Alibaba. Empirical experiments of offline evaluation and online A/B test demonstrate the effectiveness of our method. |
| Tasks | |
| Published | 2018-03-01 |
| URL | http://arxiv.org/abs/1803.00259v1 |
| http://arxiv.org/pdf/1803.00259v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-sponsored |
| Repo | |
| Framework | |
Collaborative Filtering with Stability
| Title | Collaborative Filtering with Stability |
| Authors | Dongsheng Li, Chao Chen, Qin Lv, Junchi Yan, Li Shang, Stephen M. Chu |
| Abstract | Collaborative filtering (CF) is a popular technique in today’s recommender systems, and matrix approximation-based CF methods have achieved great success in both rating prediction and top-N recommendation tasks. However, real-world user-item rating matrices are typically sparse, incomplete and noisy, which introduce challenges to the algorithm stability of matrix approximation, i.e., small changes in the training data may significantly change the models. As a result, existing matrix approximation solutions yield low generalization performance, exhibiting high error variance on the training data, and minimizing the training error may not guarantee error reduction on the test data. This paper investigates the algorithm stability problem of matrix approximation methods and how to achieve stable collaborative filtering via stable matrix approximation. We present a new algorithm design framework, which (1) introduces new optimization objectives to guide stable matrix approximation algorithm design, and (2) solves the optimization problem to obtain stable approximation solutions with good generalization performance. Experimental results on real-world datasets demonstrate that the proposed method can achieve better accuracy compared with state-of-the-art matrix approximation methods and ensemble methods in both rating prediction and top-N recommendation tasks. |
| Tasks | Recommendation Systems |
| Published | 2018-11-06 |
| URL | http://arxiv.org/abs/1811.02198v1 |
| http://arxiv.org/pdf/1811.02198v1.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-filtering-with-stability |
| Repo | |
| Framework | |
Attention-based Few-Shot Person Re-identification Using Meta Learning
| Title | Attention-based Few-Shot Person Re-identification Using Meta Learning |
| Authors | Alireza Rahimpour, Hairong Qi |
| Abstract | In this paper, we investigate the challenging task of person re-identification from a new perspective and propose an end-to-end attention-based architecture for few-shot re-identification through meta-learning. The motivation for this task lies in the fact that humans, can usually identify another person after just seeing that given person a few times (or even once) by attending to their memory. On the other hand, the unique nature of the person re-identification problem, i.e., only few examples exist per identity and new identities always appearing during testing, calls for a few shot learning architecture with the capacity of handling new identities. Hence, we frame the problem within a meta-learning setting, where a neural network based meta-learner is trained to optimize a learner i.e., an attention-based matching function. Another challenge of the person re-identification problem is the small inter-class difference between different identities and large intra-class difference of the same identity. In order to increase the discriminative power of the model, we propose a new attention-based feature encoding scheme that takes into account the critical intra-view and cross-view relationship of images. We refer to the proposed Attention-based Re-identification Metalearning model as ARM. Extensive evaluations demonstrate the advantages of the ARM as compared to the state-of-the-art on the challenging PRID2011, CUHK01, CUHK03 and Market1501 datasets. |
| Tasks | Few-Shot Learning, Meta-Learning, Person Re-Identification |
| Published | 2018-06-24 |
| URL | http://arxiv.org/abs/1806.09613v3 |
| http://arxiv.org/pdf/1806.09613v3.pdf | |
| PWC | https://paperswithcode.com/paper/attention-based-few-shot-person-re |
| Repo | |
| Framework | |
Continuous User Authentication by Contactless Wireless Sensing
| Title | Continuous User Authentication by Contactless Wireless Sensing |
| Authors | Fei Wang, Zhenjiang Li, Jinsong Han |
| Abstract | This paper presents BodyPIN, which is a continuous user authentication system by contactless wireless sensing using commodity Wi-Fi. BodyPIN can track the current user’s legal identity throughout a computer system’s execution. In case the authentication fails, the consequent accesses will be denied to protect the system. The recent rich wireless-based user identification designs cannot be applied to BodyPIN directly, because they identify a user’s various activities, rather than the user herself. The enforced to be performed activities can thus interrupt the user’s operations on the system, highly inconvenient and not user-friendly. In this paper, we leverage the bio-electromagnetics domain human model for quantifying the impact of human body on the bypassing Wi-Fi signals and deriving the component that indicates a user’s identity. Then we extract suitable Wi-Fi signal features to fully represent such an identity component, based on which we fulfill the continuous user authentication design. We implement a BodyPIN prototype by commodity Wi-Fi NICs without any extra or dedicated wireless hardware. We show that BodyPIN achieves promising authentication performances, which is also lightweight and robust under various practical settings. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01503v1 |
| http://arxiv.org/pdf/1812.01503v1.pdf | |
| PWC | https://paperswithcode.com/paper/continuous-user-authentication-by-contactless |
| Repo | |
| Framework | |
Generate the corresponding Image from Text Description using Modified GAN-CLS Algorithm
| Title | Generate the corresponding Image from Text Description using Modified GAN-CLS Algorithm |
| Authors | Fuzhou Gong, Zigeng Xia |
| Abstract | Synthesizing images or texts automatically is a useful research area in the artificial intelligence nowadays. Generative adversarial networks (GANs), which are proposed by Goodfellow in 2014, make this task to be done more efficiently by using deep neural networks. We consider generating corresponding images from an input text description using a GAN. In this paper, we analyze the GAN-CLS algorithm, which is a kind of advanced method of GAN proposed by Scott Reed in 2016. First, we find the problem with this algorithm through inference. Then we correct the GAN-CLS algorithm according to the inference by modifying the objective function of the model. Finally, we do the experiments on the Oxford-102 dataset and the CUB dataset. As a result, our modified algorithm can generate images which are more plausible than the GAN-CLS algorithm in some cases. Also, some of the generated images match the input texts better. |
| Tasks | |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1806.11302v1 |
| http://arxiv.org/pdf/1806.11302v1.pdf | |
| PWC | https://paperswithcode.com/paper/generate-the-corresponding-image-from-text |
| Repo | |
| Framework | |
BooST: Boosting Smooth Trees for Partial Effect Estimation in Nonlinear Regressions
| Title | BooST: Boosting Smooth Trees for Partial Effect Estimation in Nonlinear Regressions |
| Authors | Yuri Fonseca, Marcelo Medeiros, Gabriel Vasconcelos, Alvaro Veiga |
| Abstract | In this paper we introduce a new machine learning (ML) model for nonlinear regression called Boosting Smooth Transition Regression Trees (BooST). The main advantage of the BooST model is that it estimates the derivatives (partial effects) of very general nonlinear models, providing more interpretation about the mapping between the covariates and the dependent variable than other tree based models, such as Random Forests. We present some examples on both simulated and real data. |
| Tasks | |
| Published | 2018-08-10 |
| URL | https://arxiv.org/abs/1808.03698v4 |
| https://arxiv.org/pdf/1808.03698v4.pdf | |
| PWC | https://paperswithcode.com/paper/boost-boosting-smooth-trees-for-partial |
| Repo | |
| Framework | |
Neural Stereoscopic Image Style Transfer
| Title | Neural Stereoscopic Image Style Transfer |
| Authors | Xinyu Gong, Haozhi Huang, Lin Ma, Fumin Shen, Wei Liu, Tong Zhang |
| Abstract | Neural style transfer is an emerging technique which is able to endow daily-life images with attractive artistic styles. Previous work has succeeded in applying convolutional neural networks (CNNs) to style transfer for monocular images or videos. However, style transfer for stereoscopic images is still a missing piece. Different from processing a monocular image, the two views of a stylized stereoscopic pair are required to be consistent to provide observers a comfortable visual experience. In this paper, we propose a novel dual path network for view-consistent style transfer on stereoscopic images. While each view of the stereoscopic pair is processed in an individual path, a novel feature aggregation strategy is proposed to effectively share information between the two paths. Besides a traditional perceptual loss being used for controlling the style transfer quality in each view, a multi-layer view loss is leveraged to enforce the network to coordinate the learning of both the paths to generate view-consistent stylized results. Extensive experiments show that, compared against previous methods, our proposed model can produce stylized stereoscopic images which achieve decent view consistency. |
| Tasks | Style Transfer |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09985v4 |
| http://arxiv.org/pdf/1802.09985v4.pdf | |
| PWC | https://paperswithcode.com/paper/neural-stereoscopic-image-style-transfer |
| Repo | |
| Framework | |
Probabilistic Causal Analysis of Social Influence
| Title | Probabilistic Causal Analysis of Social Influence |
| Authors | Francesco Bonchi, Francesco Gullo, Bud Mishra, Daniele Ramazzotti |
| Abstract | Mastering the dynamics of social influence requires separating, in a database of information propagation traces, the genuine causal processes from temporal correlation, i.e., homophily and other spurious causes. However, most studies to characterize social influence, and, in general, most data-science analyses focus on correlations, statistical independence, or conditional independence. Only recently, there has been a resurgence of interest in “causal data science”, e.g., grounded on causality theories. In this paper we adopt a principled causal approach to the analysis of social influence from information-propagation data, rooted in the theory of probabilistic causation. Our approach consists of two phases. In the first one, in order to avoid the pitfalls of misinterpreting causation when the data spans a mixture of several subtypes (“Simpson’s paradox”), we partition the set of propagation traces into groups, in such a way that each group is as less contradictory as possible in terms of the hierarchical structure of information propagation. To achieve this goal, we borrow the notion of “agony” and define the Agony-bounded Partitioning problem, which we prove being hard, and for which we develop two efficient algorithms with approximation guarantees. In the second phase, for each group from the first phase, we apply a constrained MLE approach to ultimately learn a minimal causal topology. Experiments on synthetic data show that our method is able to retrieve the genuine causal arcs w.r.t. a ground-truth generative model. Experiments on real data show that, by focusing only on the extracted causal structures instead of the whole social graph, the effectiveness of predicting influence spread is significantly improved. |
| Tasks | |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.02129v2 |
| http://arxiv.org/pdf/1808.02129v2.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-causal-analysis-of-social |
| Repo | |
| Framework | |
Deep multi-scale architectures for monocular depth estimation
| Title | Deep multi-scale architectures for monocular depth estimation |
| Authors | Michel Moukari, Sylvaine Picard, Loic Simon, Frédéric Jurie |
| Abstract | This paper aims at understanding the role of multi-scale information in the estimation of depth from monocular images. More precisely, the paper investigates four different deep CNN architectures, designed to explicitly make use of multi-scale features along the network, and compare them to a state-of-the-art single-scale approach. The paper also shows that involving multi-scale features in depth estimation not only improves the performance in terms of accuracy, but also gives qualitatively better depth maps. Experiments are done on the widely used NYU Depth dataset, on which the proposed method achieves state-of-the-art performance. |
| Tasks | Depth Estimation, Monocular Depth Estimation |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.03051v1 |
| http://arxiv.org/pdf/1806.03051v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multi-scale-architectures-for-monocular |
| Repo | |
| Framework | |
Deep Learning Classification of 3.5 GHz Band Spectrograms with Applications to Spectrum Sensing
| Title | Deep Learning Classification of 3.5 GHz Band Spectrograms with Applications to Spectrum Sensing |
| Authors | W. Max Lees, Adam Wunderlich, Peter Jeavons, Paul D. Hale, Michael R. Souryal |
| Abstract | In the United States, the Federal Communications Commission has adopted rules permitting commercial wireless networks to share spectrum with federal incumbents in the 3.5~GHz Citizens Broadband Radio Service band. These rules require commercial systems to vacate the band when sensors detect radars operated by the U.S. military; a key example being the SPN-43 air traffic control radar. Such sensors require highly-accurate detection algorithms to meet their operating requirements. In this paper, using a library of over 14,000 3.5~GHz band spectrograms collected by a recent measurement campaign, we investigate the performance of thirteen methods for SPN-43 radar detection. Namely, we compare classical methods from signal detection theory and machine learning to several deep learning architectures. We demonstrate that machine learning algorithms appreciably outperform classical signal detection methods. Specifically, we find that a three-layer convolutional neural network offers a superior tradeoff between accuracy and computational complexity. Last, we apply this three-layer network to generate descriptive statistics for the full 3.5~GHz spectrogram library. Our findings highlight potential weaknesses of classical methods and strengths of modern machine learning algorithms for radar detection in the 3.5~GHz band. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07745v3 |
| http://arxiv.org/pdf/1806.07745v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-classification-of-35-ghz-band |
| Repo | |
| Framework | |
A novel Empirical Bayes with Reversible Jump Markov Chain in User-Movie Recommendation system
| Title | A novel Empirical Bayes with Reversible Jump Markov Chain in User-Movie Recommendation system |
| Authors | Arabin Kumar Dey, Himanshu Jhamb |
| Abstract | In this article we select the unknown dimension of the feature by re- versible jump MCMC inside a simulated annealing in bayesian set up of collaborative filter. We implement the same in MovieLens small dataset. We also tune the hyper parameter by using a modified empirical bayes. It can also be used to guess an initial choice for hyper-parameters in grid search procedure even for the datasets where MCMC oscillates around the true value or takes long time to converge. |
| Tasks | |
| Published | 2018-08-15 |
| URL | http://arxiv.org/abs/1808.05480v1 |
| http://arxiv.org/pdf/1808.05480v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-empirical-bayes-with-reversible-jump |
| Repo | |
| Framework | |
