Paper Group ANR 173
Deep Residual Hashing. Image Denoising via Multi-scale Nonlinear Diffusion Models. Graying the black box: Understanding DQNs. Tracking Switched Dynamic Network Topologies from Information Cascades. Improving Tweet Representations using Temporal and User Context. Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Sear …
Deep Residual Hashing
| Title | Deep Residual Hashing |
| Authors | Sailesh Conjeti, Abhijit Guha Roy, Amin Katouzian, Nassir Navab |
| Abstract | Hashing aims at generating highly compact similarity preserving code words which are well suited for large-scale image retrieval tasks. Most existing hashing methods first encode the images as a vector of hand-crafted features followed by a separate binarization step to generate hash codes. This two-stage process may produce sub-optimal encoding. In this paper, for the first time, we propose a deep architecture for supervised hashing through residual learning, termed Deep Residual Hashing (DRH), for an end-to-end simultaneous representation learning and hash coding. The DRH model constitutes four key elements: (1) a sub-network with multiple stacked residual blocks; (2) hashing layer for binarization; (3) supervised retrieval loss function based on neighbourhood component analysis for similarity preserving embedding; and (4) hashing related losses and regularisation to control the quantization error and improve the quality of hash coding. We present results of extensive experiments on a large public chest x-ray image database with co-morbidities and discuss the outcome showing substantial improvements over the latest state-of-the art methods. |
| Tasks | Image Retrieval, Quantization, Representation Learning |
| Published | 2016-12-16 |
| URL | http://arxiv.org/abs/1612.05400v1 |
| http://arxiv.org/pdf/1612.05400v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-residual-hashing |
| Repo | |
| Framework | |
Image Denoising via Multi-scale Nonlinear Diffusion Models
| Title | Image Denoising via Multi-scale Nonlinear Diffusion Models |
| Authors | Wensen Feng, Peng Qiao, Xuanyang Xi, Yunjin Chen |
| Abstract | Image denoising is a fundamental operation in image processing and holds considerable practical importance for various real-world applications. Arguably several thousands of papers are dedicated to image denoising. In the past decade, sate-of-the-art denoising algorithm have been clearly dominated by non-local patch-based methods, which explicitly exploit patch self-similarity within image. However, in recent two years, discriminatively trained local approaches have started to outperform previous non-local models and have been attracting increasing attentions due to the additional advantage of computational efficiency. Successful approaches include cascade of shrinkage fields (CSF) and trainable nonlinear reaction diffusion (TNRD). These two methods are built on filter response of linear filters of small size using feed forward architectures. Due to the locality inherent in local approaches, the CSF and TNRD model become less effective when noise level is high and consequently introduces some noise artifacts. In order to overcome this problem, in this paper we introduce a multi-scale strategy. To be specific, we build on our newly-developed TNRD model, adopting the multi-scale pyramid image representation to devise a multi-scale nonlinear diffusion process. As expected, all the parameters in the proposed multi-scale diffusion model, including the filters and the influence functions across scales, are learned from training data through a loss based approach. Numerical results on Gaussian and Poisson denoising substantiate that the exploited multi-scale strategy can successfully boost the performance of the original TNRD model with single scale. As a consequence, the resulting multi-scale diffusion models can significantly suppress the typical incorrect features for those noisy images with heavy noise. |
| Tasks | Denoising, Image Denoising |
| Published | 2016-09-21 |
| URL | http://arxiv.org/abs/1609.06585v1 |
| http://arxiv.org/pdf/1609.06585v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-denoising-via-multi-scale-nonlinear |
| Repo | |
| Framework | |
Graying the black box: Understanding DQNs
| Title | Graying the black box: Understanding DQNs |
| Authors | Tom Zahavy, Nir Ben Zrihem, Shie Mannor |
| Abstract | In recent years there is a growing interest in using deep representations for reinforcement learning. In this paper, we present a methodology and tools to analyze Deep Q-networks (DQNs) in a non-blind matter. Moreover, we propose a new model, the Semi Aggregated Markov Decision Process (SAMDP), and an algorithm that learns it automatically. The SAMDP model allows us to identify spatio-temporal abstractions directly from features and may be used as a sub-goal detector in future work. Using our tools we reveal that the features learned by DQNs aggregate the state space in a hierarchical fashion, explaining its success. Moreover, we are able to understand and describe the policies learned by DQNs for three different Atari2600 games and suggest ways to interpret, debug and optimize deep neural networks in reinforcement learning. |
| Tasks | |
| Published | 2016-02-08 |
| URL | http://arxiv.org/abs/1602.02658v4 |
| http://arxiv.org/pdf/1602.02658v4.pdf | |
| PWC | https://paperswithcode.com/paper/graying-the-black-box-understanding-dqns |
| Repo | |
| Framework | |
Tracking Switched Dynamic Network Topologies from Information Cascades
| Title | Tracking Switched Dynamic Network Topologies from Information Cascades |
| Authors | Brian Baingana, Georgios B. Giannakis |
| Abstract | Contagions such as the spread of popular news stories, or infectious diseases, propagate in cascades over dynamic networks with unobservable topologies. However, “social signals” such as product purchase time, or blog entry timestamps are measurable, and implicitly depend on the underlying topology, making it possible to track it over time. Interestingly, network topologies often “jump” between discrete states that may account for sudden changes in the observed signals. The present paper advocates a switched dynamic structural equation model to capture the topology-dependent cascade evolution, as well as the discrete states driving the underlying topologies. Conditions under which the proposed switched model is identifiable are established. Leveraging the edge sparsity inherent to social networks, a recursive $\ell_1$-norm regularized least-squares estimator is put forth to jointly track the states and network topologies. An efficient first-order proximal-gradient algorithm is developed to solve the resulting optimization problem. Numerical experiments on both synthetic data and real cascades measured over the span of one year are conducted, and test results corroborate the efficacy of the advocated approach. |
| Tasks | |
| Published | 2016-06-28 |
| URL | http://arxiv.org/abs/1606.08882v1 |
| http://arxiv.org/pdf/1606.08882v1.pdf | |
| PWC | https://paperswithcode.com/paper/tracking-switched-dynamic-network-topologies |
| Repo | |
| Framework | |
Improving Tweet Representations using Temporal and User Context
| Title | Improving Tweet Representations using Temporal and User Context |
| Authors | Ganesh J, Manish Gupta, Vasudeva Varma |
| Abstract | In this work we propose a novel representation learning model which computes semantic representations for tweets accurately. Our model systematically exploits the chronologically adjacent tweets (‘context’) from users’ Twitter timelines for this task. Further, we make our model user-aware so that it can do well in modeling the target tweet by exploiting the rich knowledge about the user such as the way the user writes the post and also summarizing the topics on which the user writes. We empirically demonstrate that the proposed models outperform the state-of-the-art models in predicting the user profile attributes like spouse, education and job by 19.66%, 2.27% and 2.22% respectively. |
| Tasks | Representation Learning |
| Published | 2016-12-19 |
| URL | http://arxiv.org/abs/1612.06062v1 |
| http://arxiv.org/pdf/1612.06062v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-tweet-representations-using |
| Repo | |
| Framework | |
Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Search and Analytics
| Title | Event Search and Analytics: Detecting Events in Semantically Annotated Corpora for Search and Analytics |
| Authors | Dhruv Gupta |
| Abstract | In this article, I present the questions that I seek to answer in my PhD research. I posit to analyze natural language text with the help of semantic annotations and mine important events for navigating large text corpora. Semantic annotations such as named entities, geographic locations, and temporal expressions can help us mine events from the given corpora. These events thus provide us with useful means to discover the locked knowledge in them. I pose three problems that can help unlock this knowledge vault in semantically annotated text corpora: i. identifying important events; ii. semantic search; and iii. event analytics. |
| Tasks | |
| Published | 2016-03-01 |
| URL | http://arxiv.org/abs/1603.00260v1 |
| http://arxiv.org/pdf/1603.00260v1.pdf | |
| PWC | https://paperswithcode.com/paper/event-search-and-analytics-detecting-events |
| Repo | |
| Framework | |
Bicycle-Sharing System Analysis and Trip Prediction
| Title | Bicycle-Sharing System Analysis and Trip Prediction |
| Authors | Jiawei Zhang, Xiao Pan, Moyin Li, Philip S. Yu |
| Abstract | Bicycle-sharing systems, which can provide shared bike usage services for the public, have been launched in many big cities. In bicycle-sharing systems, people can borrow and return bikes at any stations in the service region very conveniently. Therefore, bicycle-sharing systems are normally used as a short-distance trip supplement for private vehicles as well as regular public transportation. Meanwhile, for stations located at different places in the service region, the bike usages can be quite skewed and imbalanced. Some stations have too many incoming bikes and get jammed without enough docks for upcoming bikes, while some other stations get empty quickly and lack enough bikes for people to check out. Therefore, inferring the potential destinations and arriving time of each individual trip beforehand can effectively help the service providers schedule manual bike re-dispatch in advance. In this paper, we will study the individual trip prediction problem for bicycle-sharing systems. To address the problem, we study a real-world bicycle-sharing system and analyze individuals’ bike usage behaviors first. Based on the analysis results, a new trip destination prediction and trip duration inference model will be introduced. Experiments conducted on a real-world bicycle-sharing system demonstrate the effectiveness of the proposed model. |
| Tasks | |
| Published | 2016-04-03 |
| URL | http://arxiv.org/abs/1604.00664v1 |
| http://arxiv.org/pdf/1604.00664v1.pdf | |
| PWC | https://paperswithcode.com/paper/bicycle-sharing-system-analysis-and-trip |
| Repo | |
| Framework | |
Learning Points and Routes to Recommend Trajectories
| Title | Learning Points and Routes to Recommend Trajectories |
| Authors | Dawei Chen, Cheng Soon Ong, Lexing Xie |
| Abstract | The problem of recommending tours to travellers is an important and broadly studied area. Suggested solutions include various approaches of points-of-interest (POI) recommendation and route planning. We consider the task of recommending a sequence of POIs, that simultaneously uses information about POIs and routes. Our approach unifies the treatment of various sources of information by representing them as features in machine learning algorithms, enabling us to learn from past behaviour. Information about POIs are used to learn a POI ranking model that accounts for the start and end points of tours. Data about previous trajectories are used for learning transition patterns between POIs that enable us to recommend probable routes. In addition, a probabilistic model is proposed to combine the results of POI ranking and the POI to POI transitions. We propose a new F$_1$ score on pairs of POIs that capture the order of visits. Empirical results show that our approach improves on recent methods, and demonstrate that combining points and routes enables better trajectory recommendations. |
| Tasks | |
| Published | 2016-08-25 |
| URL | http://arxiv.org/abs/1608.07051v1 |
| http://arxiv.org/pdf/1608.07051v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-points-and-routes-to-recommend |
| Repo | |
| Framework | |
Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network
| Title | Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network |
| Authors | Fangxuan Sun, Jun Lin, Zhongfeng Wang |
| Abstract | Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory requirement. In this paper, an equal distance nonuniform quantization (ENQ) scheme and a K-means clustering nonuniform quantization (KNQ) scheme are proposed to reduce the required memory storage when low complexity hardware or software implementations are considered. For the VGG-16 and the AlexNet, the proposed nonuniform quantization schemes reduce the number of required memory storage by approximately 50% while achieving almost the same or even better classification accuracy compared to the state-of-the-art quantization method. Compared to the ENQ scheme, the proposed KNQ scheme provides a better tradeoff when higher accuracy is required. |
| Tasks | Object Detection, Quantization, Speech Recognition |
| Published | 2016-07-10 |
| URL | http://arxiv.org/abs/1607.02720v2 |
| http://arxiv.org/pdf/1607.02720v2.pdf | |
| PWC | https://paperswithcode.com/paper/intra-layer-nonuniform-quantization-for-deep |
| Repo | |
| Framework | |
PAC Reinforcement Learning with Rich Observations
| Title | PAC Reinforcement Learning with Rich Observations |
| Authors | Akshay Krishnamurthy, Alekh Agarwal, John Langford |
| Abstract | We propose and study a new model for reinforcement learning with rich observations, generalizing contextual bandits to sequential decision making. These models require an agent to take actions based on observations (features) with the goal of achieving long-term performance competitive with a large set of policies. To avoid barriers to sample-efficient learning associated with large observation spaces and general POMDPs, we focus on problems that can be summarized by a small number of hidden states and have long-term rewards that are predictable by a reactive function class. In this setting, we design and analyze a new reinforcement learning algorithm, Least Squares Value Elimination by Exploration. We prove that the algorithm learns near optimal behavior after a number of episodes that is polynomial in all relevant parameters, logarithmic in the number of policies, and independent of the size of the observation space. Our result provides theoretical justification for reinforcement learning with function approximation. |
| Tasks | Decision Making, Multi-Armed Bandits |
| Published | 2016-02-08 |
| URL | http://arxiv.org/abs/1602.02722v4 |
| http://arxiv.org/pdf/1602.02722v4.pdf | |
| PWC | https://paperswithcode.com/paper/pac-reinforcement-learning-with-rich |
| Repo | |
| Framework | |
Generate Image Descriptions based on Deep RNN and Memory Cells for Images Features
| Title | Generate Image Descriptions based on Deep RNN and Memory Cells for Images Features |
| Authors | Shijian Tang, Song Han |
| Abstract | Generating natural language descriptions for images is a challenging task. The traditional way is to use the convolutional neural network (CNN) to extract image features, followed by recurrent neural network (RNN) to generate sentences. In this paper, we present a new model that added memory cells to gate the feeding of image features to the deep neural network. The intuition is enabling our model to memorize how much information from images should be fed at each stage of the RNN. Experiments on Flickr8K and Flickr30K datasets showed that our model outperforms other state-of-the-art models with higher BLEU scores. |
| Tasks | |
| Published | 2016-02-05 |
| URL | http://arxiv.org/abs/1602.01895v1 |
| http://arxiv.org/pdf/1602.01895v1.pdf | |
| PWC | https://paperswithcode.com/paper/generate-image-descriptions-based-on-deep-rnn |
| Repo | |
| Framework | |
Feature Selection as a Multiagent Coordination Problem
| Title | Feature Selection as a Multiagent Coordination Problem |
| Authors | Kleanthis Malialis, Jun Wang, Gary Brooks, George Frangou |
| Abstract | Datasets with hundreds to tens of thousands features is the new norm. Feature selection constitutes a central problem in machine learning, where the aim is to derive a representative set of features from which to construct a classification (or prediction) model for a specific task. Our experimental study involves microarray gene expression datasets, these are high-dimensional and noisy datasets that contain genetic data typically used for distinguishing between benign or malicious tissues or classifying different types of cancer. In this paper, we formulate feature selection as a multiagent coordination problem and propose a novel feature selection method using multiagent reinforcement learning. The central idea of the proposed approach is to “assign” a reinforcement learning agent to each feature where each agent learns to control a single feature, we refer to this approach as MARL. Applying this to microarray datasets creates an enormous multiagent coordination problem between thousands of learning agents. To address the scalability challenge we apply a form of reward shaping called CLEAN rewards. We compare in total nine feature selection methods, including state-of-the-art methods, and show that the proposed method using CLEAN rewards can significantly scale-up, thus outperforming the rest of learning-based methods. We further show that a hybrid variant of MARL achieves the best overall performance. |
| Tasks | Feature Selection |
| Published | 2016-03-16 |
| URL | http://arxiv.org/abs/1603.05152v1 |
| http://arxiv.org/pdf/1603.05152v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-selection-as-a-multiagent |
| Repo | |
| Framework | |
Particle Swarm Optimized Power Consumption of Trilateration
| Title | Particle Swarm Optimized Power Consumption of Trilateration |
| Authors | Hussein S. Al-Olimat, Robert C. Green II, Mansoor Alam, Vijay Devabhaktuni, Wei Cheng |
| Abstract | Trilateration-based localization (TBL) has become a corner stone of modern technology. This study formulates the concern on how wireless sensor networks can take advantage of the computational intelligent techniques using both single- and multi-objective particle swarm optimization (PSO) with an overall aim of concurrently minimizing the required time for localization, minimizing energy consumed during localization, and maximizing the number of nodes fully localized through the adjustment of wireless sensor transmission ranges while using TBL process. A parameter-study of the applied PSO variants is performed, leading to results that show algorithmic improvements of up to 32% in the evaluated objectives. |
| Tasks | |
| Published | 2016-02-08 |
| URL | http://arxiv.org/abs/1602.02473v1 |
| http://arxiv.org/pdf/1602.02473v1.pdf | |
| PWC | https://paperswithcode.com/paper/particle-swarm-optimized-power-consumption-of |
| Repo | |
| Framework | |
Online optimization and regret guarantees for non-additive long-term constraints
| Title | Online optimization and regret guarantees for non-additive long-term constraints |
| Authors | Rodolphe Jenatton, Jim Huang, Dominik Csiba, Cedric Archambeau |
| Abstract | We consider online optimization in the 1-lookahead setting, where the objective does not decompose additively over the rounds of the online game. The resulting formulation enables us to deal with non-stationary and/or long-term constraints , which arise, for example, in online display advertising problems. We propose an on-line primal-dual algorithm for which we obtain dynamic cumulative regret guarantees. They depend on the convexity and the smoothness of the non-additive penalty, as well as terms capturing the smoothness with which the residuals of the non-stationary and long-term constraints vary over the rounds. We conduct experiments on synthetic data to illustrate the benefits of the non-additive penalty and show vanishing regret convergence on live traffic data collected by a display advertising platform in production. |
| Tasks | |
| Published | 2016-02-17 |
| URL | http://arxiv.org/abs/1602.05394v2 |
| http://arxiv.org/pdf/1602.05394v2.pdf | |
| PWC | https://paperswithcode.com/paper/online-optimization-and-regret-guarantees-for |
| Repo | |
| Framework | |
A two-stage learning method for protein-protein interaction prediction
| Title | A two-stage learning method for protein-protein interaction prediction |
| Authors | Amir Ahooye Atashin, Parsa Bagherzadeh, Kamaledin Ghiasi-Shirazi |
| Abstract | In this paper, a new method for PPI (proteinprotein interaction) prediction is proposed. In PPI prediction, a reliable and sufficient number of training samples is not available, but a large number of unlabeled samples is in hand. In the proposed method, the denoising auto encoders are employed for learning robust features. The obtained robust features are used in order to train a classifier with a better performance. The experimental results demonstrate the capabilities of the proposed method. Protein-protein interaction; Denoising auto encoder;Robust features; Unlabelled data; |
| Tasks | Denoising |
| Published | 2016-06-14 |
| URL | http://arxiv.org/abs/1606.04561v2 |
| http://arxiv.org/pdf/1606.04561v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-two-stage-learning-method-for-protein |
| Repo | |
| Framework | |
