Paper Group ANR 466
Discovering the Graph Structure in the Clustering Results. Item Silk Road: Recommending Items from Information Domains to Social Users. A Computer Vision System to Localize and Classify Wastes on the Streets. Time-Sensitive Bandit Learning and Satisficing Thompson Sampling. Safe Exploration for Identifying Linear Systems via Robust Optimization. 3D …
Discovering the Graph Structure in the Clustering Results
| Title | Discovering the Graph Structure in the Clustering Results |
| Authors | Evgeny Bauman, Konstantin Bauman |
| Abstract | In a standard cluster analysis, such as k-means, in addition to clusters locations and distances between them, it’s important to know if they are connected or well separated from each other. The main focus of this paper is discovering the relations between the resulting clusters. We propose a new method which is based on pairwise overlapping k-means clustering, that in addition to means of clusters provides the graph structure of their relations. The proposed method has a set of parameters that can be tuned in order to control the sensitivity of the model and the desired relative size of the pairwise overlapping interval between means of two adjacent clusters, i.e., level of overlapping. We present the exact formula for calculating that parameter. The empirical study presented in the paper demonstrates that our approach works well not only on toy data but also compliments standard clustering results with a reasonable graph structure on real datasets, such as financial indices and restaurants. |
| Tasks | |
| Published | 2017-05-18 |
| URL | http://arxiv.org/abs/1705.06753v1 |
| http://arxiv.org/pdf/1705.06753v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-the-graph-structure-in-the |
| Repo | |
| Framework | |
Item Silk Road: Recommending Items from Information Domains to Social Users
| Title | Item Silk Road: Recommending Items from Information Domains to Social Users |
| Authors | Xiang Wang, Xiangnan He, Liqiang Nie, Tat-Seng Chua |
| Abstract | Online platforms can be divided into information-oriented and social-oriented domains. The former refers to forums or E-commerce sites that emphasize user-item interactions, like Trip.com and Amazon; whereas the latter refers to social networking services (SNSs) that have rich user-user connections, such as Facebook and Twitter. Despite their heterogeneity, these two domains can be bridged by a few overlapping users, dubbed as bridge users. In this work, we address the problem of cross-domain social recommendation, i.e., recommending relevant items of information domains to potential users of social networks. To our knowledge, this is a new problem that has rarely been studied before. Existing cross-domain recommender systems are unsuitable for this task since they have either focused on homogeneous information domains or assumed that users are fully overlapped. Towards this end, we present a novel Neural Social Collaborative Ranking (NSCR) approach, which seamlessly sews up the user-item interactions in information domains and user-user connections in SNSs. In the information domain part, the attributes of users and items are leveraged to strengthen the embedding learning of users and items. In the SNS part, the embeddings of bridge users are propagated to learn the embeddings of other non-bridge users. Extensive experiments on two real-world datasets demonstrate the effectiveness and rationality of our NSCR method. |
| Tasks | Collaborative Ranking, Recommendation Systems |
| Published | 2017-06-10 |
| URL | http://arxiv.org/abs/1706.03205v1 |
| http://arxiv.org/pdf/1706.03205v1.pdf | |
| PWC | https://paperswithcode.com/paper/item-silk-road-recommending-items-from |
| Repo | |
| Framework | |
A Computer Vision System to Localize and Classify Wastes on the Streets
| Title | A Computer Vision System to Localize and Classify Wastes on the Streets |
| Authors | Mohammad Saeed Rad, Andreas von Kaenel, Andre Droux, Francois Tieche, Nabil Ouerhani, Hazim Kemal Ekenel, Jean-Philippe Thiran |
| Abstract | Littering quantification is an important step for improving cleanliness of cities. When human interpretation is too cumbersome or in some cases impossible, an objective index of cleanliness could reduce the littering by awareness actions. In this paper, we present a fully automated computer vision application for littering quantification based on images taken from the streets and sidewalks. We have employed a deep learning based framework to localize and classify different types of wastes. Since there was no waste dataset available, we built our acquisition system mounted on a vehicle. Collected images containing different types of wastes. These images are then annotated for training and benchmarking the developed system. Our results on real case scenarios show accurate detection of littering on variant backgrounds. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11374v1 |
| http://arxiv.org/pdf/1710.11374v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-computer-vision-system-to-localize-and |
| Repo | |
| Framework | |
Time-Sensitive Bandit Learning and Satisficing Thompson Sampling
| Title | Time-Sensitive Bandit Learning and Satisficing Thompson Sampling |
| Authors | Daniel Russo, David Tse, Benjamin Van Roy |
| Abstract | The literature on bandit learning and regret analysis has focused on contexts where the goal is to converge on an optimal action in a manner that limits exploration costs. One shortcoming imposed by this orientation is that it does not treat time preference in a coherent manner. Time preference plays an important role when the optimal action is costly to learn relative to near-optimal actions. This limitation has not only restricted the relevance of theoretical results but has also influenced the design of algorithms. Indeed, popular approaches such as Thompson sampling and UCB can fare poorly in such situations. In this paper, we consider discounted rather than cumulative regret, where a discount factor encodes time preference. We propose satisficing Thompson sampling – a variation of Thompson sampling – and establish a strong discounted regret bound for this new algorithm. |
| Tasks | |
| Published | 2017-04-28 |
| URL | http://arxiv.org/abs/1704.09028v1 |
| http://arxiv.org/pdf/1704.09028v1.pdf | |
| PWC | https://paperswithcode.com/paper/time-sensitive-bandit-learning-and |
| Repo | |
| Framework | |
Safe Exploration for Identifying Linear Systems via Robust Optimization
| Title | Safe Exploration for Identifying Linear Systems via Robust Optimization |
| Authors | Tyler Lu, Martin Zinkevich, Craig Boutilier, Binz Roy, Dale Schuurmans |
| Abstract | Safely exploring an unknown dynamical system is critical to the deployment of reinforcement learning (RL) in physical systems where failures may have catastrophic consequences. In scenarios where one knows little about the dynamics, diverse transition data covering relevant regions of state-action space is needed to apply either model-based or model-free RL. Motivated by the cooling of Google’s data centers, we study how one can safely identify the parameters of a system model with a desired accuracy and confidence level. In particular, we focus on learning an unknown linear system with Gaussian noise assuming only that, initially, a nominal safe action is known. Define safety as satisfying specific linear constraints on the state space (e.g., requirements on process variable) that must hold over the span of an entire trajectory, and given a Probably Approximately Correct (PAC) style bound on the estimation error of model parameters, we show how to compute safe regions of action space by gradually growing a ball around the nominal safe action. One can apply any exploration strategy where actions are chosen from such safe regions. Experiments on a stylized model of data center cooling dynamics show how computing proper safe regions can increase the sample efficiency of safe exploration. |
| Tasks | Safe Exploration |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1711.11165v1 |
| http://arxiv.org/pdf/1711.11165v1.pdf | |
| PWC | https://paperswithcode.com/paper/safe-exploration-for-identifying-linear |
| Repo | |
| Framework | |
3D Sketching using Multi-View Deep Volumetric Prediction
| Title | 3D Sketching using Multi-View Deep Volumetric Prediction |
| Authors | Johanna Delanoy, Mathieu Aubry, Phillip Isola, Alexei A. Efros, Adrien Bousseau |
| Abstract | Sketch-based modeling strives to bring the ease and immediacy of drawing to the 3D world. However, while drawings are easy for humans to create, they are very challenging for computers to interpret due to their sparsity and ambiguity. We propose a data-driven approach that tackles this challenge by learning to reconstruct 3D shapes from one or more drawings. At the core of our approach is a deep convolutional neural network (CNN) that predicts occupancy of a voxel grid from a line drawing. This CNN provides us with an initial 3D reconstruction as soon as the user completes a single drawing of the desired shape. We complement this single-view network with an updater CNN that refines an existing prediction given a new drawing of the shape created from a novel viewpoint. A key advantage of our approach is that we can apply the updater iteratively to fuse information from an arbitrary number of viewpoints, without requiring explicit stroke correspondences between the drawings. We train both CNNs by rendering synthetic contour drawings from hand-modeled shape collections as well as from procedurally-generated abstract shapes. Finally, we integrate our CNNs in a minimal modeling interface that allows users to seamlessly draw an object, rotate it to see its 3D reconstruction, and refine it by re-drawing from another vantage point using the 3D reconstruction as guidance. The main strengths of our approach are its robustness to freehand bitmap drawings, its ability to adapt to different object categories, and the continuum it offers between single-view and multi-view sketch-based modeling. |
| Tasks | 3D Reconstruction |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08390v4 |
| http://arxiv.org/pdf/1707.08390v4.pdf | |
| PWC | https://paperswithcode.com/paper/3d-sketching-using-multi-view-deep-volumetric |
| Repo | |
| Framework | |
Perception Driven Texture Generation
| Title | Perception Driven Texture Generation |
| Authors | Yanhai Gan, Huifang Chi, Ying Gao, Jun Liu, Guoqiang Zhong, Junyu Dong |
| Abstract | This paper investigates a novel task of generating texture images from perceptual descriptions. Previous work on texture generation focused on either synthesis from examples or generation from procedural models. Generating textures from perceptual attributes have not been well studied yet. Meanwhile, perceptual attributes, such as directionality, regularity and roughness are important factors for human observers to describe a texture. In this paper, we propose a joint deep network model that combines adversarial training and perceptual feature regression for texture generation, while only random noise and user-defined perceptual attributes are required as input. In this model, a preliminary trained convolutional neural network is essentially integrated with the adversarial framework, which can drive the generated textures to possess given perceptual attributes. An important aspect of the proposed model is that, if we change one of the input perceptual features, the corresponding appearance of the generated textures will also be changed. We design several experiments to validate the effectiveness of the proposed method. The results show that the proposed method can produce high quality texture images with desired perceptual properties. |
| Tasks | Texture Synthesis |
| Published | 2017-03-24 |
| URL | http://arxiv.org/abs/1703.09784v1 |
| http://arxiv.org/pdf/1703.09784v1.pdf | |
| PWC | https://paperswithcode.com/paper/perception-driven-texture-generation |
| Repo | |
| Framework | |
GALILEO: A Generalized Low-Entropy Mixture Model
| Title | GALILEO: A Generalized Low-Entropy Mixture Model |
| Authors | Cetin Savkli, Jeffrey Lin, Philip Graff, Matthew Kinsey |
| Abstract | We present a new method of generating mixture models for data with categorical attributes. The keys to this approach are an entropy-based density metric in categorical space and annealing of high-entropy/low-density components from an initial state with many components. Pruning of low-density components using the entropy-based density allows GALILEO to consistently find high-quality clusters and the same optimal number of clusters. GALILEO has shown promising results on a range of test datasets commonly used for categorical clustering benchmarks. We demonstrate that the scaling of GALILEO is linear in the number of records in the dataset, making this method suitable for very large categorical datasets. |
| Tasks | |
| Published | 2017-08-24 |
| URL | http://arxiv.org/abs/1708.07242v1 |
| http://arxiv.org/pdf/1708.07242v1.pdf | |
| PWC | https://paperswithcode.com/paper/galileo-a-generalized-low-entropy-mixture |
| Repo | |
| Framework | |
A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
| Title | A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots |
| Authors | Yu Wu, Wei Wu, Chen Xing, Can Xu, Zhoujun Li, Ming Zhou |
| Abstract | We study the problem of response selection for multi-turn conversation in retrieval-based chatbots. The task requires matching a response candidate with a conversation context, whose challenges include how to recognize important parts of the context, and how to model the relationships among utterances in the context. Existing matching methods may lose important information in contexts as we can interpret them with a unified framework in which contexts are transformed to fixed-length vectors without any interaction with responses before matching. The analysis motivates us to propose a new matching framework that can sufficiently carry the important information in contexts to matching and model the relationships among utterances at the same time. The new framework, which we call a sequential matching framework (SMF), lets each utterance in a context interacts with a response candidate at the first step and transforms the pair to a matching vector. The matching vectors are then accumulated following the order of the utterances in the context with a recurrent neural network (RNN) which models the relationships among the utterances. The context-response matching is finally calculated with the hidden states of the RNN. Under SMF, we propose a sequential convolutional network and sequential attention network and conduct experiments on two public data sets to test their performance. Experimental results show that both models can significantly outperform the state-of-the-art matching methods. We also show that the models are interpretable with visualizations that provide us insights on how they capture and leverage the important information in contexts for matching. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11344v1 |
| http://arxiv.org/pdf/1710.11344v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-sequential-matching-framework-for-multi |
| Repo | |
| Framework | |
Finding optimal finite biological sequences over finite alphabets: the OptiFin toolbox
| Title | Finding optimal finite biological sequences over finite alphabets: the OptiFin toolbox |
| Authors | Régis Garnier, Christophe Guyeux, Stéphane Chrétien |
| Abstract | In this paper, we present a toolbox for a specific optimization problem that frequently arises in bioinformatics or genomics. In this specific optimisation problem, the state space is a set of words of specified length over a finite alphabet. To each word is associated a score. The overall objective is to find the words which have the lowest possible score. This type of general optimization problem is encountered in e.g 3D conformation optimisation for protein structure prediction, or largest core genes subset discovery based on best supported phylogenetic tree for a set of species. In order to solve this problem, we propose a toolbox that can be easily launched using MPI and embeds 3 well-known metaheuristics. The toolbox is fully parametrized and well documented. It has been specifically designed to be easy modified and possibly improved by the user depending on the application, and does not require to be a computer scientist. We show that the toolbox performs very well on two difficult practical problems. |
| Tasks | |
| Published | 2017-06-25 |
| URL | http://arxiv.org/abs/1706.08089v1 |
| http://arxiv.org/pdf/1706.08089v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-optimal-finite-biological-sequences |
| Repo | |
| Framework | |
True Asymptotic Natural Gradient Optimization
| Title | True Asymptotic Natural Gradient Optimization |
| Authors | Yann Ollivier |
| Abstract | We introduce a simple algorithm, True Asymptotic Natural Gradient Optimization (TANGO), that converges to a true natural gradient descent in the limit of small learning rates, without explicit Fisher matrix estimation. For quadratic models the algorithm is also an instance of averaged stochastic gradient, where the parameter is a moving average of a “fast”, constant-rate gradient descent. TANGO appears as a particular de-linearization of averaged SGD, and is sometimes quite different on non-quadratic models. This further connects averaged SGD and natural gradient, both of which are arguably optimal asymptotically. In large dimension, small learning rates will be required to approximate the natural gradient well. Still, this shows it is possible to get arbitrarily close to exact natural gradient descent with a lightweight algorithm. |
| Tasks | |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.08449v1 |
| http://arxiv.org/pdf/1712.08449v1.pdf | |
| PWC | https://paperswithcode.com/paper/true-asymptotic-natural-gradient-optimization |
| Repo | |
| Framework | |
Raw Waveform-based Speech Enhancement by Fully Convolutional Networks
| Title | Raw Waveform-based Speech Enhancement by Fully Convolutional Networks |
| Authors | Szu-Wei Fu, Yu Tsao, Xugang Lu, Hisashi Kawai |
| Abstract | This study proposes a fully convolutional network (FCN) model for raw waveform-based speech enhancement. The proposed system performs speech enhancement in an end-to-end (i.e., waveform-in and waveform-out) manner, which dif-fers from most existing denoising methods that process the magnitude spectrum (e.g., log power spectrum (LPS)) only. Because the fully connected layers, which are involved in deep neural networks (DNN) and convolutional neural networks (CNN), may not accurately characterize the local information of speech signals, particularly with high frequency components, we employed fully convolutional layers to model the waveform. More specifically, FCN consists of only convolutional layers and thus the local temporal structures of speech signals can be efficiently and effectively preserved with relatively few weights. Experimental results show that DNN- and CNN-based models have limited capability to restore high frequency components of waveforms, thus leading to decreased intelligibility of enhanced speech. By contrast, the proposed FCN model can not only effectively recover the waveforms but also outperform the LPS-based DNN baseline in terms of short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ). In addition, the number of model parameters in FCN is approximately only 0.2% compared with that in both DNN and CNN. |
| Tasks | Denoising, Speech Enhancement |
| Published | 2017-03-07 |
| URL | http://arxiv.org/abs/1703.02205v3 |
| http://arxiv.org/pdf/1703.02205v3.pdf | |
| PWC | https://paperswithcode.com/paper/raw-waveform-based-speech-enhancement-by |
| Repo | |
| Framework | |
Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition
| Title | Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition |
| Authors | Yufei Wang, Zhe Lin, Xiaohui Shen, Scott Cohen, Garrison W. Cottrell |
| Abstract | Recently, there has been a lot of interest in automatically generating descriptions for an image. Most existing language-model based approaches for this task learn to generate an image description word by word in its original word order. However, for humans, it is more natural to locate the objects and their relationships first, and then elaborate on each object, describing notable attributes. We present a coarse-to-fine method that decomposes the original image description into a skeleton sentence and its attributes, and generates the skeleton sentence and attribute phrases separately. By this decomposition, our method can generate more accurate and novel descriptions than the previous state-of-the-art. Experimental results on the MS-COCO and a larger scale Stock3M datasets show that our algorithm yields consistent improvements across different evaluation metrics, especially on the SPICE metric, which has much higher correlation with human ratings than the conventional metrics. Furthermore, our algorithm can generate descriptions with varied length, benefiting from the separate control of the skeleton and attributes. This enables image description generation that better accommodates user preferences. |
| Tasks | Image Captioning, Language Modelling |
| Published | 2017-04-23 |
| URL | http://arxiv.org/abs/1704.06972v1 |
| http://arxiv.org/pdf/1704.06972v1.pdf | |
| PWC | https://paperswithcode.com/paper/skeleton-key-image-captioning-by-skeleton |
| Repo | |
| Framework | |
Regularising Non-linear Models Using Feature Side-information
| Title | Regularising Non-linear Models Using Feature Side-information |
| Authors | Amina Mollaysa, Pablo Strasser, Alexandros Kalousis |
| Abstract | Very often features come with their own vectorial descriptions which provide detailed information about their properties. We refer to these vectorial descriptions as feature side-information. In the standard learning scenario, input is represented as a vector of features and the feature side-information is most often ignored or used only for feature selection prior to model fitting. We believe that feature side-information which carries information about features intrinsic property will help improve model prediction if used in a proper way during learning process. In this paper, we propose a framework that allows for the incorporation of the feature side-information during the learning of very general model families to improve the prediction performance. We control the structures of the learned models so that they reflect features similarities as these are defined on the basis of the side-information. We perform experiments on a number of benchmark datasets which show significant predictive performance gains, over a number of baselines, as a result of the exploitation of the side-information. |
| Tasks | Feature Selection |
| Published | 2017-03-07 |
| URL | http://arxiv.org/abs/1703.02570v1 |
| http://arxiv.org/pdf/1703.02570v1.pdf | |
| PWC | https://paperswithcode.com/paper/regularising-non-linear-models-using-feature |
| Repo | |
| Framework | |
A Versatile, Sound Tool for Simplifying Definitions
| Title | A Versatile, Sound Tool for Simplifying Definitions |
| Authors | Alessandro Coglio, Matt Kaufmann, Eric W. Smith |
| Abstract | We present a tool, simplify-defun, that transforms the definition of a given function into a simplified definition of a new function, providing a proof checked by ACL2 that the old and new functions are equivalent. When appropriate it also generates termination and guard proofs for the new function. We explain how the tool is engineered so that these proofs will succeed. Examples illustrate its utility, in particular for program transformation in synthesis and verification. |
| Tasks | |
| Published | 2017-05-03 |
| URL | http://arxiv.org/abs/1705.01228v1 |
| http://arxiv.org/pdf/1705.01228v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-versatile-sound-tool-for-simplifying |
| Repo | |
| Framework | |
