Paper Group ANR 517
Measuring #GamerGate: A Tale of Hate, Sexism, and Bullying. Limits of End-to-End Learning. Aggregated Wasserstein Metric and State Registration for Hidden Markov Models. Direct estimation of density functionals using a polynomial basis. Learnings Options End-to-End for Continuous Action Tasks. Auxiliary Variables for Multi-Dirichlet Priors. On Stei …
Measuring #GamerGate: A Tale of Hate, Sexism, and Bullying
| Title | Measuring #GamerGate: A Tale of Hate, Sexism, and Bullying |
| Authors | Despoina Chatzakou, Nicolas Kourtellis, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Athena Vakali |
| Abstract | Over the past few years, online aggression and abusive behaviors have occurred in many different forms and on a variety of platforms. In extreme cases, these incidents have evolved into hate, discrimination, and bullying, and even materialized into real-world threats and attacks against individuals or groups. In this paper, we study the Gamergate controversy. Started in August 2014 in the online gaming world, it quickly spread across various social networking platforms, ultimately leading to many incidents of cyberbullying and cyberaggression. We focus on Twitter, presenting a measurement study of a dataset of 340k unique users and 1.6M tweets to study the properties of these users, the content they post, and how they differ from random Twitter users. We find that users involved in this “Twitter war” tend to have more friends and followers, are generally more engaged and post tweets with negative sentiment, less joy, and more hate than random users. We also perform preliminary measurements on how the Twitter suspension mechanism deals with such abusive behaviors. While we focus on Gamergate, our methodology to collect and analyze tweets related to aggressive and bullying activities is of independent interest. |
| Tasks | |
| Published | 2017-02-24 |
| URL | http://arxiv.org/abs/1702.07784v1 |
| http://arxiv.org/pdf/1702.07784v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-gamergate-a-tale-of-hate-sexism-and |
| Repo | |
| Framework | |
Limits of End-to-End Learning
| Title | Limits of End-to-End Learning |
| Authors | Tobias Glasmachers |
| Abstract | End-to-end learning refers to training a possibly complex learning system by applying gradient-based learning to the system as a whole. End-to-end learning system is specifically designed so that all modules are differentiable. In effect, not only a central learning machine, but also all “peripheral” modules like representation learning and memory formation are covered by a holistic learning process. The power of end-to-end learning has been demonstrated on many tasks, like playing a whole array of Atari video games with a single architecture. While pushing for solutions to more challenging tasks, network architectures keep growing more and more complex. In this paper we ask the question whether and to what extent end-to-end learning is a future-proof technique in the sense of scaling to complex and diverse data processing architectures. We point out potential inefficiencies, and we argue in particular that end-to-end learning does not make optimal use of the modular design of present neural networks. Our surprisingly simple experiments demonstrate these inefficiencies, up to the complete breakdown of learning. |
| Tasks | Representation Learning |
| Published | 2017-04-26 |
| URL | http://arxiv.org/abs/1704.08305v1 |
| http://arxiv.org/pdf/1704.08305v1.pdf | |
| PWC | https://paperswithcode.com/paper/limits-of-end-to-end-learning |
| Repo | |
| Framework | |
Aggregated Wasserstein Metric and State Registration for Hidden Markov Models
| Title | Aggregated Wasserstein Metric and State Registration for Hidden Markov Models |
| Authors | Yukun Chen, Jianbo Ye, Jia Li |
| Abstract | We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time position follows a Gaussian mixture distribution, a fact exploited to softly match, aka register, the states in two HMMs. We refer to such HMMs as Gaussian mixture model-HMM (GMM-HMM). The registration of states is inspired by the intrinsic relationship of optimal transport and the Wasserstein metric between distributions. Specifically, the components of the marginal GMMs are matched by solving an optimal transport problem where the cost between components is the Wasserstein metric for Gaussian distributions. The solution of the optimization problem is a fast approximation to the Wasserstein metric between two GMMs. The new Aggregated Wasserstein distance is a semi-metric and can be computed without generating Monte Carlo samples. It is invariant to relabeling or permutation of states. The distance is defined meaningfully even for two HMMs that are estimated from data of different dimensionality, a situation that can arise due to missing variables. This distance quantifies the dissimilarity of GMM-HMMs by measuring both the difference between the two marginal GMMs and that between the two transition matrices. Our new distance is tested on tasks of retrieval, classification, and t-SNE visualization of time series. Experiments on both synthetic and real data have demonstrated its advantages in terms of accuracy as well as efficiency in comparison with existing distances based on the Kullback-Leibler divergence. |
| Tasks | Time Series |
| Published | 2017-11-12 |
| URL | http://arxiv.org/abs/1711.05792v2 |
| http://arxiv.org/pdf/1711.05792v2.pdf | |
| PWC | https://paperswithcode.com/paper/aggregated-wasserstein-metric-and-state |
| Repo | |
| Framework | |
Direct estimation of density functionals using a polynomial basis
| Title | Direct estimation of density functionals using a polynomial basis |
| Authors | Alan Wisler, Visar Berisha, Andreas Spanias, Alfred O. Hero |
| Abstract | A number of fundamental quantities in statistical signal processing and information theory can be expressed as integral functions of two probability density functions. Such quantities are called density functionals as they map density functions onto the real line. For example, information divergence functions measure the dissimilarity between two probability density functions and are useful in a number of applications. Typically, estimating these quantities requires complete knowledge of the underlying distribution followed by multi-dimensional integration. Existing methods make parametric assumptions about the data distribution or use non-parametric density estimation followed by high-dimensional integration. In this paper, we propose a new alternative. We introduce the concept of “data-driven basis functions” - functions of distributions whose value we can estimate given only samples from the underlying distributions without requiring distribution fitting or direct integration. We derive a new data-driven complete basis that is similar to the deterministic Bernstein polynomial basis and develop two methods for performing basis expansions of functionals of two distributions. We also show that the new basis set allows us to approximate functions of distributions as closely as desired. Finally, we evaluate the methodology by developing data driven estimators for the Kullback-Leibler divergences and the Hellinger distance and by constructing empirical estimates of tight bounds on the Bayes error rate. |
| Tasks | Density Estimation |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06516v2 |
| http://arxiv.org/pdf/1702.06516v2.pdf | |
| PWC | https://paperswithcode.com/paper/direct-estimation-of-density-functionals |
| Repo | |
| Framework | |
Learnings Options End-to-End for Continuous Action Tasks
| Title | Learnings Options End-to-End for Continuous Action Tasks |
| Authors | Martin Klissarov, Pierre-Luc Bacon, Jean Harb, Doina Precup |
| Abstract | We present new results on learning temporally extended actions for continuoustasks, using the options framework (Suttonet al.[1999b], Precup [2000]). In orderto achieve this goal we work with the option-critic architecture (Baconet al.[2017])using a deliberation cost and train it with proximal policy optimization (Schulmanet al.[2017]) instead of vanilla policy gradient. Results on Mujoco domains arepromising, but lead to interesting questions aboutwhena given option should beused, an issue directly connected to the use of initiation sets. |
| Tasks | |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1712.00004v1 |
| http://arxiv.org/pdf/1712.00004v1.pdf | |
| PWC | https://paperswithcode.com/paper/learnings-options-end-to-end-for-continuous |
| Repo | |
| Framework | |
Auxiliary Variables for Multi-Dirichlet Priors
| Title | Auxiliary Variables for Multi-Dirichlet Priors |
| Authors | Christoph Carl Kling |
| Abstract | Bayesian models that mix multiple Dirichlet prior parameters, called Multi-Dirichlet priors (MD) in this paper, are gaining popularity. Inferring mixing weights and parameters of mixed prior distributions seems tricky, as sums over Dirichlet parameters complicate the joint distribution of model parameters. This paper shows a novel auxiliary variable scheme which helps to simplify the inference for models involving hierarchical MDs and MDPs. Using this scheme, it is easy to derive fully collapsed inference schemes which allow for an efficient inference. |
| Tasks | |
| Published | 2017-08-17 |
| URL | http://arxiv.org/abs/1708.05257v1 |
| http://arxiv.org/pdf/1708.05257v1.pdf | |
| PWC | https://paperswithcode.com/paper/auxiliary-variables-for-multi-dirichlet |
| Repo | |
| Framework | |
On Stein’s Identity and Near-Optimal Estimation in High-dimensional Index Models
| Title | On Stein’s Identity and Near-Optimal Estimation in High-dimensional Index Models |
| Authors | Zhuoran Yang, Krishnakumar Balasubramanian, Han Liu |
| Abstract | We consider estimating the parametric components of semi-parametric multiple index models in a high-dimensional and non-Gaussian setting. Such models form a rich class of non-linear models with applications to signal processing, machine learning and statistics. Our estimators leverage the score function based first and second-order Stein’s identities and do not require the covariates to satisfy Gaussian or elliptical symmetry assumptions common in the literature. Moreover, to handle score functions and responses that are heavy-tailed, our estimators are constructed via carefully thresholding their empirical counterparts. We show that our estimator achieves near-optimal statistical rate of convergence in several settings. We supplement our theoretical results via simulation experiments that confirm the theory. |
| Tasks | |
| Published | 2017-09-26 |
| URL | http://arxiv.org/abs/1709.08795v2 |
| http://arxiv.org/pdf/1709.08795v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-steins-identity-and-near-optimal |
| Repo | |
| Framework | |
Discriminative Metric Learning with Deep Forest
| Title | Discriminative Metric Learning with Deep Forest |
| Authors | Lev V. Utkin, Mikhail A. Ryabinin |
| Abstract | A Discriminative Deep Forest (DisDF) as a metric learning algorithm is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. The case of the fully supervised learning is studied when the class labels of individual training examples are known. The main idea underlying the algorithm is to assign weights to decision trees in random forest in order to reduce distances between objects from the same class and to increase them between objects from different classes. The weights are training parameters. A specific objective function which combines Euclidean and Manhattan distances and simplifies the optimization problem for training the DisDF is proposed. The numerical experiments illustrate the proposed distance metric algorithm. |
| Tasks | Metric Learning |
| Published | 2017-05-25 |
| URL | http://arxiv.org/abs/1705.09620v1 |
| http://arxiv.org/pdf/1705.09620v1.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-metric-learning-with-deep |
| Repo | |
| Framework | |
OSU Multimodal Machine Translation System Report
| Title | OSU Multimodal Machine Translation System Report |
| Authors | Mingbo Ma, Dapeng Li, Kai Zhao, Liang Huang |
| Abstract | This paper describes Oregon State University’s submissions to the shared WMT’17 task “multimodal translation task I”. In this task, all the sentence pairs are image captions in different languages. The key difference between this task and conventional machine translation is that we have corresponding images as additional information for each sentence pair. In this paper, we introduce a simple but effective system which takes an image shared between different languages, feeding it into the both encoding and decoding side. We report our system’s performance for English-French and English-German with Flickr30K (in-domain) and MSCOCO (out-of-domain) datasets. Our system achieves the best performance in TER for English-German for MSCOCO dataset. |
| Tasks | Image Captioning, Machine Translation, Multimodal Machine Translation |
| Published | 2017-10-07 |
| URL | http://arxiv.org/abs/1710.02718v2 |
| http://arxiv.org/pdf/1710.02718v2.pdf | |
| PWC | https://paperswithcode.com/paper/osu-multimodal-machine-translation-system |
| Repo | |
| Framework | |
Deep D-bar: Real time Electrical Impedance Tomography Imaging with Deep Neural Networks
| Title | Deep D-bar: Real time Electrical Impedance Tomography Imaging with Deep Neural Networks |
| Authors | Sarah Jane Hamilton, Andreas Hauptmann |
| Abstract | The mathematical problem for Electrical Impedance Tomography (EIT) is a highly nonlinear ill-posed inverse problem requiring carefully designed reconstruction procedures to ensure reliable image generation. D-bar methods are based on a rigorous mathematical analysis and provide robust direct reconstructions by using a low-pass filtering of the associated nonlinear Fourier data. Similarly to low-pass filtering of linear Fourier data, only using low frequencies in the image recovery process results in blurred images lacking sharp features such as clear organ boundaries. Convolutional Neural Networks provide a powerful framework for post-processing such convolved direct reconstructions. In this study, we demonstrate that these CNN techniques lead to sharp and reliable reconstructions even for the highly nonlinear inverse problem of EIT. The network is trained on data sets of simulated examples and then applied to experimental data without the need to perform an additional transfer training. Results for absolute EIT images are presented using experimental EIT data from the ACT4 and KIT4 EIT systems. |
| Tasks | Image Generation |
| Published | 2017-11-08 |
| URL | http://arxiv.org/abs/1711.03180v2 |
| http://arxiv.org/pdf/1711.03180v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-d-bar-real-time-electrical-impedance |
| Repo | |
| Framework | |
Investigating Inner Properties of Multimodal Representation and Semantic Compositionality with Brain-based Componential Semantics
| Title | Investigating Inner Properties of Multimodal Representation and Semantic Compositionality with Brain-based Componential Semantics |
| Authors | Shaonan Wang, Jiajun Zhang, Nan Lin, Chengqing Zong |
| Abstract | Multimodal models have been proven to outperform text-based approaches on learning semantic representations. However, it still remains unclear what properties are encoded in multimodal representations, in what aspects do they outperform the single-modality representations, and what happened in the process of semantic compositionality in different input modalities. Considering that multimodal models are originally motivated by human concept representations, we assume that correlating multimodal representations with brain-based semantics would interpret their inner properties to answer the above questions. To that end, we propose simple interpretation methods based on brain-based componential semantics. First we investigate the inner properties of multimodal representations by correlating them with corresponding brain-based property vectors. Then we map the distributed vector space to the interpretable brain-based componential space to explore the inner properties of semantic compositionality. Ultimately, the present paper sheds light on the fundamental questions of natural language understanding, such as how to represent the meaning of words and how to combine word meanings into larger units. |
| Tasks | Learning Semantic Representations |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05516v2 |
| http://arxiv.org/pdf/1711.05516v2.pdf | |
| PWC | https://paperswithcode.com/paper/investigating-inner-properties-of-multimodal |
| Repo | |
| Framework | |
Dynamic Compositional Neural Networks over Tree Structure
| Title | Dynamic Compositional Neural Networks over Tree Structure |
| Authors | Pengfei Liu, Xipeng Qiu, Xuanjing Huang |
| Abstract | Tree-structured neural networks have proven to be effective in learning semantic representations by exploiting syntactic information. In spite of their success, most existing models suffer from the underfitting problem: they recursively use the same shared compositional function throughout the whole compositional process and lack expressive power due to inability to capture the richness of compositionality. In this paper, we address this issue by introducing the dynamic compositional neural networks over tree structure (DC-TreeNN), in which the compositional function is dynamically generated by a meta network. The role of meta-network is to capture the metaknowledge across the different compositional rules and formulate them. Experimental results on two typical tasks show the effectiveness of the proposed models. |
| Tasks | Learning Semantic Representations |
| Published | 2017-05-11 |
| URL | http://arxiv.org/abs/1705.04153v1 |
| http://arxiv.org/pdf/1705.04153v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-compositional-neural-networks-over |
| Repo | |
| Framework | |
Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty
| Title | Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty |
| Authors | Apratim Bhattacharyya, Mario Fritz, Bernt Schiele |
| Abstract | Progress towards advanced systems for assisted and autonomous driving is leveraging recent advances in recognition and segmentation methods. Yet, we are still facing challenges in bringing reliable driving to inner cities, as those are composed of highly dynamic scenes observed from a moving platform at considerable speeds. Anticipation becomes a key element in order to react timely and prevent accidents. In this paper we argue that it is necessary to predict at least 1 second and we thus propose a new model that jointly predicts ego motion and people trajectories over such large time horizons. We pay particular attention to modeling the uncertainty of our estimates arising from the non-deterministic nature of natural traffic scenes. Our experimental results show that it is indeed possible to predict people trajectories at the desired time horizons and that our uncertainty estimates are informative of the prediction error. We also show that both sequence modeling of trajectories as well as our novel method of long term odometry prediction are essential for best performance. |
| Tasks | Autonomous Driving |
| Published | 2017-11-24 |
| URL | http://arxiv.org/abs/1711.09026v2 |
| http://arxiv.org/pdf/1711.09026v2.pdf | |
| PWC | https://paperswithcode.com/paper/long-term-on-board-prediction-of-people-in |
| Repo | |
| Framework | |
Anisotropic twicing for single particle reconstruction using autocorrelation analysis
| Title | Anisotropic twicing for single particle reconstruction using autocorrelation analysis |
| Authors | Tejal Bhamre, Teng Zhang, Amit Singer |
| Abstract | The missing phase problem in X-ray crystallography is commonly solved using the technique of molecular replacement, which borrows phases from a previously solved homologous structure, and appends them to the measured Fourier magnitudes of the diffraction patterns of the unknown structure. More recently, molecular replacement has been proposed for solving the missing orthogonal matrices problem arising in Kam’s autocorrelation analysis for single particle reconstruction using X-ray free electron lasers and cryo-EM. In classical molecular replacement, it is common to estimate the magnitudes of the unknown structure as twice the measured magnitudes minus the magnitudes of the homologous structure, a procedure known as `twicing’. Mathematically, this is equivalent to finding an unbiased estimator for a complex-valued scalar. We generalize this scheme for the case of estimating real or complex valued matrices arising in single particle autocorrelation analysis. We name this approach “Anisotropic Twicing” because unlike the scalar case, the unbiased estimator is not obtained by a simple magnitude isotropic correction. We compare the performance of the least squares, twicing and anisotropic twicing estimators on synthetic and experimental datasets. We demonstrate 3D homology modeling in cryo-EM directly from experimental data without iterative refinement or class averaging, for the first time. | |
| Tasks | |
| Published | 2017-04-26 |
| URL | http://arxiv.org/abs/1704.07969v1 |
| http://arxiv.org/pdf/1704.07969v1.pdf | |
| PWC | https://paperswithcode.com/paper/anisotropic-twicing-for-single-particle |
| Repo | |
| Framework | |
Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images
| Title | Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images |
| Authors | Ebrahim Karami, Siva Prasad, Mohamed Shehata |
| Abstract | Fast and robust image matching is a very important task with various applications in computer vision and robotics. In this paper, we compare the performance of three different image matching techniques, i.e., SIFT, SURF, and ORB, against different kinds of transformations and deformations such as scaling, rotation, noise, fish eye distortion, and shearing. For this purpose, we manually apply different types of transformations on original images and compute the matching evaluation parameters such as the number of key points in images, the matching rate, and the execution time required for each algorithm and we will show that which algorithm is the best more robust against each kind of distortion. Index Terms-Image matching, scale invariant feature transform (SIFT), speed up robust feature (SURF), robust independent elementary features (BRIEF), oriented FAST, rotated BRIEF (ORB). |
| Tasks | |
| Published | 2017-10-07 |
| URL | http://arxiv.org/abs/1710.02726v1 |
| http://arxiv.org/pdf/1710.02726v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-matching-using-sift-surf-brief-and-orb |
| Repo | |
| Framework | |
