Paper Group ANR 369
Fusion Subspace Clustering: Full and Incomplete Data. Mixture Matrix Completion. Face Recognition: From Traditional to Deep Learning Methods. Node Representation Learning for Directed Graphs. Analyzing Hypersensitive AI: Instability in Corporate-Scale Machine Learning. A Unified Framework for Sparse Relaxed Regularized Regression: SR3. Parallel Att …
Fusion Subspace Clustering: Full and Incomplete Data
Title | Fusion Subspace Clustering: Full and Incomplete Data |
Authors | Daniel L. Pimentel-Alarcón, Usman Mahmood |
Abstract | Modern inference and learning often hinge on identifying low-dimensional structures that approximate large scale data. Subspace clustering achieves this through a union of linear subspaces. However, in contemporary applications data is increasingly often incomplete, rendering standard (full-data) methods inapplicable. On the other hand, existing incomplete-data methods present major drawbacks, like lifting an already high-dimensional problem, or requiring a super polynomial number of samples. Motivated by this, we introduce a new subspace clustering algorithm inspired by fusion penalties. The main idea is to permanently assign each datum to a subspace of its own, and minimize the distance between the subspaces of all data, so that subspaces of the same cluster get fused together. Our approach is entirely new to both, full and missing data, and unlike other methods, it directly allows noise, it requires no liftings, it allows low, high, and even full-rank data, it approaches optimal (information-theoretic) sampling rates, and it does not rely on other methods such as low-rank matrix completion to handle missing data. Furthermore, our extensive experiments on both real and synthetic data show that our approach performs comparably to the state-of-the-art with complete data, and dramatically better if data is missing. |
Tasks | Low-Rank Matrix Completion, Matrix Completion |
Published | 2018-08-02 |
URL | http://arxiv.org/abs/1808.00628v1 |
http://arxiv.org/pdf/1808.00628v1.pdf | |
PWC | https://paperswithcode.com/paper/fusion-subspace-clustering-full-and |
Repo | |
Framework | |
Mixture Matrix Completion
Title | Mixture Matrix Completion |
Authors | Daniel L. Pimentel-Alarcón |
Abstract | Completing a data matrix X has become an ubiquitous problem in modern data science, with applications in recommender systems, computer vision, and networks inference, to name a few. One typical assumption is that X is low-rank. A more general model assumes that each column of X corresponds to one of several low-rank matrices. This paper generalizes these models to what we call mixture matrix completion (MMC): the case where each entry of X corresponds to one of several low-rank matrices. MMC is a more accurate model for recommender systems, and brings more flexibility to other completion and clustering problems. We make four fundamental contributions about this new model. First, we show that MMC is theoretically possible (well-posed). Second, we give its precise information-theoretic identifiability conditions. Third, we derive the sample complexity of MMC. Finally, we give a practical algorithm for MMC with performance comparable to the state-of-the-art for simpler related problems, both on synthetic and real data. |
Tasks | Matrix Completion, Recommendation Systems |
Published | 2018-08-02 |
URL | http://arxiv.org/abs/1808.00616v1 |
http://arxiv.org/pdf/1808.00616v1.pdf | |
PWC | https://paperswithcode.com/paper/mixture-matrix-completion |
Repo | |
Framework | |
Face Recognition: From Traditional to Deep Learning Methods
Title | Face Recognition: From Traditional to Deep Learning Methods |
Authors | Daniel Sáez Trigueros, Li Meng, Margaret Hartnett |
Abstract | Starting in the seventies, face recognition has become one of the most researched topics in computer vision and biometrics. Traditional methods based on hand-crafted features and traditional machine learning techniques have recently been superseded by deep neural networks trained with very large datasets. In this paper we provide a comprehensive and up-to-date literature review of popular face recognition methods including both traditional (geometry-based, holistic, feature-based and hybrid methods) and deep learning methods. |
Tasks | Face Recognition |
Published | 2018-10-31 |
URL | http://arxiv.org/abs/1811.00116v1 |
http://arxiv.org/pdf/1811.00116v1.pdf | |
PWC | https://paperswithcode.com/paper/face-recognition-from-traditional-to-deep |
Repo | |
Framework | |
Node Representation Learning for Directed Graphs
Title | Node Representation Learning for Directed Graphs |
Authors | Megha Khosla, Jurek Leonhardt, Wolfgang Nejdl, Avishek Anand |
Abstract | We propose a novel approach for learning node representations in directed graphs, which maintains separate views or embedding spaces for the two distinct node roles induced by the directionality of the edges. We argue that the previous approaches either fail to encode the edge directionality or their encodings cannot be generalized across tasks. With our simple \emph{alternating random walk} strategy, we generate role specific vertex neighborhoods and train node embeddings in their corresponding source/target roles while fully exploiting the semantics of directed graphs. We also unearth the limitations of evaluations on directed graphs in previous works and propose a clear strategy for evaluating link prediction and graph reconstruction in directed graphs. We conduct extensive experiments to showcase our effectiveness on several real-world datasets on link prediction, node classification and graph reconstruction tasks. We show that the embeddings from our approach are indeed robust, generalizable and well performing across multiple kinds of tasks and graphs. We show that we consistently outperform all baselines for node classification task. In addition to providing a theoretical interpretation of our method we also show that we are considerably more robust than the other directed graph approaches. |
Tasks | Link Prediction, Multi-Label Classification, Node Classification, Representation Learning |
Published | 2018-10-22 |
URL | https://arxiv.org/abs/1810.09176v4 |
https://arxiv.org/pdf/1810.09176v4.pdf | |
PWC | https://paperswithcode.com/paper/node-representation-learning-for-directed |
Repo | |
Framework | |
Analyzing Hypersensitive AI: Instability in Corporate-Scale Machine Learning
Title | Analyzing Hypersensitive AI: Instability in Corporate-Scale Machine Learning |
Authors | Michaela Regneri, Malte Hoffmann, Jurij Kost, Niklas Pietsch, Timo Schulz, Sabine Stamm |
Abstract | Predictive geometric models deliver excellent results for many Machine Learning use cases. Despite their undoubted performance, neural predictive algorithms can show unexpected degrees of instability and variance, particularly when applied to large datasets. We present an approach to measure changes in geometric models with respect to both output consistency and topological stability. Considering the example of a recommender system using word2vec, we analyze the influence of single data points, approximation methods and parameter settings. Our findings can help to stabilize models where needed and to detect differences in informational value of data points on a large scale. |
Tasks | Recommendation Systems |
Published | 2018-07-17 |
URL | http://arxiv.org/abs/1807.07404v1 |
http://arxiv.org/pdf/1807.07404v1.pdf | |
PWC | https://paperswithcode.com/paper/analyzing-hypersensitive-ai-instability-in |
Repo | |
Framework | |
A Unified Framework for Sparse Relaxed Regularized Regression: SR3
Title | A Unified Framework for Sparse Relaxed Regularized Regression: SR3 |
Authors | Peng Zheng, Travis Askham, Steven L. Brunton, J. Nathan Kutz, Aleksandr Y. Aravkin |
Abstract | Regularized regression problems are ubiquitous in statistical modeling, signal processing, and machine learning. Sparse regression in particular has been instrumental in scientific model discovery, including compressed sensing applications, variable selection, and high-dimensional analysis. We propose a broad framework for sparse relaxed regularized regression, called SR3. The key idea is to solve a relaxation of the regularized problem, which has three advantages over the state-of-the-art: (1) solutions of the relaxed problem are superior with respect to errors, false positives, and conditioning, (2) relaxation allows extremely fast algorithms for both convex and nonconvex formulations, and (3) the methods apply to composite regularizers such as total variation (TV) and its nonconvex variants. We demonstrate the advantages of SR3 (computational efficiency, higher accuracy, faster convergence rates, greater flexibility) across a range of regularized regression problems with synthetic and real data, including applications in compressed sensing, LASSO, matrix completion, TV regularization, and group sparsity. To promote reproducible research, we also provide a companion MATLAB package that implements these examples. |
Tasks | Matrix Completion |
Published | 2018-07-14 |
URL | http://arxiv.org/abs/1807.05411v4 |
http://arxiv.org/pdf/1807.05411v4.pdf | |
PWC | https://paperswithcode.com/paper/a-unified-framework-for-sparse-relaxed |
Repo | |
Framework | |
Parallel Attention Mechanisms in Neural Machine Translation
Title | Parallel Attention Mechanisms in Neural Machine Translation |
Authors | Julian Richard Medina, Jugal Kalita |
Abstract | Recent papers in neural machine translation have proposed the strict use of attention mechanisms over previous standards such as recurrent and convolutional neural networks (RNNs and CNNs). We propose that by running traditionally stacked encoding branches from encoder-decoder attention- focused architectures in parallel, that even more sequential operations can be removed from the model and thereby decrease training time. In particular, we modify the recently published attention-based architecture called Transformer by Google, by replacing sequential attention modules with parallel ones, reducing the amount of training time and substantially improving BLEU scores at the same time. Experiments over the English to German and English to French translation tasks show that our model establishes a new state of the art. |
Tasks | Machine Translation |
Published | 2018-10-29 |
URL | http://arxiv.org/abs/1810.12427v1 |
http://arxiv.org/pdf/1810.12427v1.pdf | |
PWC | https://paperswithcode.com/paper/parallel-attention-mechanisms-in-neural |
Repo | |
Framework | |
Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning
Title | Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning |
Authors | Duc Minh Nguyen, Evaggelia Tsiligianni, Robert Calderbank, Nikos Deligiannis |
Abstract | Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Nevertheless, when training data is scarce their performance is significantly degraded due to overfitting. In this paper, we mit- igate overfitting with a data-dependent regularization technique that relies on the principles of multi-task learning. Specifically, we propose an autoencoder-based matrix completion model that performs prediction of the unknown matrix values as a main task, and manifold learning as an auxiliary task. The latter acts as an inductive bias, leading to solutions that generalize better. The proposed model outperforms the existing autoencoder-based models designed for matrix completion, achieving high reconstruction accuracy in well-known datasets. |
Tasks | Matrix Completion, Multi-Task Learning |
Published | 2018-07-04 |
URL | http://arxiv.org/abs/1807.01798v1 |
http://arxiv.org/pdf/1807.01798v1.pdf | |
PWC | https://paperswithcode.com/paper/regularizing-autoencoder-based-matrix |
Repo | |
Framework | |
Learning Local Distortion Visibility From Image Quality Data-sets
Title | Learning Local Distortion Visibility From Image Quality Data-sets |
Authors | Navaneeth Kamballur Kottayil, Giuseppe Valenzise, Frederic Dufaux, Irene Cheng |
Abstract | Accurate prediction of local distortion visibility thresholds is critical in many image and video processing applications. Existing methods require an accurate modeling of the human visual system, and are derived through pshycophysical experiments with simple, artificial stimuli. These approaches, however, are difficult to generalize to natural images with complex types of distortion. In this paper, we explore a different perspective, and we investigate whether it is possible to learn local distortion visibility from image quality scores. We propose a convolutional neural network based optimization framework to infer local detection thresholds in a distorted image. Our model is trained on multiple quality datasets, and the results are correlated with empirical visibility thresholds collected on complex stimuli in a recent study. Our results are comparable to state-of-the-art mathematical models that were trained on phsycovisual data directly. This suggests that it is possible to predict psychophysical phenomena from visibility information embedded in image quality scores. |
Tasks | |
Published | 2018-03-11 |
URL | http://arxiv.org/abs/1803.04053v1 |
http://arxiv.org/pdf/1803.04053v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-local-distortion-visibility-from |
Repo | |
Framework | |
An elementary introduction to information geometry
Title | An elementary introduction to information geometry |
Authors | Frank Nielsen |
Abstract | We describe the fundamental differential-geometric structures of information manifolds, state the fundamental theorem of information geometry, and illustrate some uses of these information manifolds in information sciences. The exposition is self-contained by concisely introducing the necessary concepts of differential geometry with proofs omitted for brevity. |
Tasks | |
Published | 2018-08-17 |
URL | http://arxiv.org/abs/1808.08271v1 |
http://arxiv.org/pdf/1808.08271v1.pdf | |
PWC | https://paperswithcode.com/paper/an-elementary-introduction-to-information |
Repo | |
Framework | |
Evolutionary RL for Container Loading
Title | Evolutionary RL for Container Loading |
Authors | S Saikia, R Verma, P Agarwal, G Shroff, L Vig, A Srinivasan |
Abstract | Loading the containers on the ship from a yard, is an impor- tant part of port operations. Finding the optimal sequence for the loading of containers, is known to be computationally hard and is an example of combinatorial optimization, which leads to the application of simple heuristics in practice. In this paper, we propose an approach which uses a mix of Evolutionary Strategies and Reinforcement Learning (RL) tech- niques to find an approximation of the optimal solution. The RL based agent uses the Policy Gradient method, an evolutionary reward strategy and a Pool of good (not-optimal) solutions to find the approximation. We find that the RL agent learns near-optimal solutions that outperforms the heuristic solutions. We also observe that the RL agent assisted with a pool generalizes better for unseen problems than an RL agent without a pool. We present our results on synthetic data as well as on subsets of real-world problems taken from container terminal. The results validate that our approach does comparatively better than the heuristics solutions available, and adapts to unseen problems better. |
Tasks | Combinatorial Optimization |
Published | 2018-05-17 |
URL | http://arxiv.org/abs/1805.06664v1 |
http://arxiv.org/pdf/1805.06664v1.pdf | |
PWC | https://paperswithcode.com/paper/evolutionary-rl-for-container-loading |
Repo | |
Framework | |
Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approach
Title | Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approach |
Authors | Chuan Qin, Hengshu Zhu, Tong Xu, Chen Zhu, Liang Jiang, Enhong Chen, Hui Xiong |
Abstract | The wide spread use of online recruitment services has led to information explosion in the job market. As a result, the recruiters have to seek the intelligent ways for Person Job Fit, which is the bridge for adapting the right job seekers to the right positions. Existing studies on Person Job Fit have a focus on measuring the matching degree between the talent qualification and the job requirements mainly based on the manual inspection of human resource experts despite of the subjective, incomplete, and inefficient nature of the human judgement. To this end, in this paper, we propose a novel end to end Ability aware Person Job Fit Neural Network model, which has a goal of reducing the dependence on manual labour and can provide better interpretation about the fitting results. The key idea is to exploit the rich information available at abundant historical job application data. Specifically, we propose a word level semantic representation for both job requirements and job seekers’ experiences based on Recurrent Neural Network. Along this line, four hierarchical ability aware attention strategies are designed to measure the different importance of job requirements for semantic representation, as well as measuring the different contribution of each job experience to a specific ability requirement. Finally, extensive experiments on a large scale real world data set clearly validate the effectiveness and interpretability of the APJFNN framework compared with several baselines. |
Tasks | |
Published | 2018-12-21 |
URL | http://arxiv.org/abs/1812.08947v1 |
http://arxiv.org/pdf/1812.08947v1.pdf | |
PWC | https://paperswithcode.com/paper/enhancing-person-job-fit-for-talent |
Repo | |
Framework | |
SentiALG: Automated Corpus Annotation for Algerian Sentiment Analysis
Title | SentiALG: Automated Corpus Annotation for Algerian Sentiment Analysis |
Authors | Imane Guellil, Ahsan Adeel, Faical Azouaou, Amir Hussain |
Abstract | Data annotation is an important but time-consuming and costly procedure. To sort a text into two classes, the very first thing we need is a good annotation guideline, establishing what is required to qualify for each class. In the literature, the difficulties associated with an appropriate data annotation has been underestimated. In this paper, we present a novel approach to automatically construct an annotated sentiment corpus for Algerian dialect (a Maghrebi Arabic dialect). The construction of this corpus is based on an Algerian sentiment lexicon that is also constructed automatically. The presented work deals with the two widely used scripts on Arabic social media: Arabic and Arabizi. The proposed approach automatically constructs a sentiment corpus containing 8000 messages (where 4000 are dedicated to Arabic and 4000 to Arabizi). The achieved F1-score is up to 72% and 78% for an Arabic and Arabizi test sets, respectively. Ongoing work is aimed at integrating transliteration process for Arabizi messages to further improve the obtained results. |
Tasks | Sentiment Analysis, Transliteration |
Published | 2018-08-15 |
URL | http://arxiv.org/abs/1808.05079v1 |
http://arxiv.org/pdf/1808.05079v1.pdf | |
PWC | https://paperswithcode.com/paper/sentialg-automated-corpus-annotation-for |
Repo | |
Framework | |
Identifying Computer-Translated Paragraphs using Coherence Features
Title | Identifying Computer-Translated Paragraphs using Coherence Features |
Authors | Hoang-Quoc Nguyen-Son, Ngoc-Dung T. Tieu, Huy H. Nguyen, Junichi Yamagishi, Isao Echizen |
Abstract | We have developed a method for extracting the coherence features from a paragraph by matching similar words in its sentences. We conducted an experiment with a parallel German corpus containing 2000 human-created and 2000 machine-translated paragraphs. The result showed that our method achieved the best performance (accuracy = 72.3%, equal error rate = 29.8%) when it is compared with previous methods on various computer-generated text including translation and paper generation (best accuracy = 67.9%, equal error rate = 32.0%). Experiments on Dutch, another rich resource language, and a low resource one (Japanese) attained similar performances. It demonstrated the efficiency of the coherence features at distinguishing computer-translated from human-created paragraphs on diverse languages. |
Tasks | Paper generation |
Published | 2018-12-28 |
URL | http://arxiv.org/abs/1812.10896v1 |
http://arxiv.org/pdf/1812.10896v1.pdf | |
PWC | https://paperswithcode.com/paper/identifying-computer-translated-paragraphs |
Repo | |
Framework | |
Progressive refinement: a method of coarse-to-fine image parsing using stacked network
Title | Progressive refinement: a method of coarse-to-fine image parsing using stacked network |
Authors | Jiagao Hu, Zhengxing Sun, Yunhan Sun, Jinlong Shi |
Abstract | To parse images into fine-grained semantic parts, the complex fine-grained elements will put it in trouble when using off-the-shelf semantic segmentation networks. In this paper, for image parsing task, we propose to parse images from coarse to fine with progressively refined semantic classes. It is achieved by stacking the segmentation layers in a segmentation network several times. The former segmentation module parses images at a coarser-grained level, and the result will be feed to the following one to provide effective contextual clues for the finer-grained parsing. To recover the details of small structures, we add skip connections from shallow layers of the network to fine-grained parsing modules. As for the network training, we merge classes in groundtruth to get coarse-to-fine label maps, and train the stacked network with these hierarchical supervision end-to-end. Our coarse-to-fine stacked framework can be injected into many advanced neural networks to improve the parsing results. Extensive evaluations on several public datasets including face parsing and human parsing well demonstrate the superiority of our method. |
Tasks | Human Parsing, Semantic Segmentation |
Published | 2018-04-23 |
URL | http://arxiv.org/abs/1804.08256v1 |
http://arxiv.org/pdf/1804.08256v1.pdf | |
PWC | https://paperswithcode.com/paper/progressive-refinement-a-method-of-coarse-to |
Repo | |
Framework | |