Paper Group ANR 766
A Critical Analysis of Biased Parsers in Unsupervised Parsing. Smooth Adversarial Examples. Non-negative representation based discriminative dictionary learning for face recognition. Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices. From Observability to Significance in Distributed Information Syst …
A Critical Analysis of Biased Parsers in Unsupervised Parsing
| Title | A Critical Analysis of Biased Parsers in Unsupervised Parsing |
| Authors | Chris Dyer, Gábor Melis, Phil Blunsom |
| Abstract | A series of recent papers has used a parsing algorithm due to Shen et al. (2018) to recover phrase-structure trees based on proxies for “syntactic depth.” These proxy depths are obtained from the representations learned by recurrent language models augmented with mechanisms that encourage the (unsupervised) discovery of hierarchical structure latent in natural language sentences. Using the same parser, we show that proxies derived from a conventional LSTM language model produce trees comparably well to the specialized architectures used in previous work. However, we also provide a detailed analysis of the parsing algorithm, showing (1) that it is incomplete—that is, it can recover only a fraction of possible trees—and (2) that it has a marked bias for right-branching structures which results in inflated performance in right-branching languages like English. Our analysis shows that evaluating with biased parsing algorithms can inflate the apparent structural competence of language models. |
| Tasks | Language Modelling |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09428v1 |
| https://arxiv.org/pdf/1909.09428v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-critical-analysis-of-biased-parsers-in |
| Repo | |
| Framework | |
Smooth Adversarial Examples
| Title | Smooth Adversarial Examples |
| Authors | Hanwei Zhang, Yannis Avrithis, Teddy Furon, Laurent Amsaleg |
| Abstract | This paper investigates the visual quality of the adversarial examples. Recent papers propose to smooth the perturbations to get rid of high frequency artefacts. In this work, smoothing has a different meaning as it perceptually shapes the perturbation according to the visual content of the image to be attacked. The perturbation becomes locally smooth on the flat areas of the input image, but it may be noisy on its textured areas and sharp across its edges. This operation relies on Laplacian smoothing, well-known in graph signal processing, which we integrate in the attack pipeline. We benchmark several attacks with and without smoothing under a white-box scenario and evaluate their transferability. Despite the additional constraint of smoothness, our attack has the same probability of success at lower distortion. |
| Tasks | |
| Published | 2019-03-28 |
| URL | http://arxiv.org/abs/1903.11862v1 |
| http://arxiv.org/pdf/1903.11862v1.pdf | |
| PWC | https://paperswithcode.com/paper/smooth-adversarial-examples |
| Repo | |
| Framework | |
Non-negative representation based discriminative dictionary learning for face recognition
| Title | Non-negative representation based discriminative dictionary learning for face recognition |
| Authors | Zhe Chen, Xiao-Jun Wu, Josef Kittler |
| Abstract | In this paper, we propose a non-negative representation based discriminative dictionary learning algorithm (NRDL) for multicategory face classification. In contrast to traditional dictionary learning methods, NRDL investigates the use of non-negative representation (NR), which contributes to learning discriminative dictionary atoms. In order to make the learned dictionary more suitable for classification, NRDL seamlessly incorporates nonnegative representation constraint, discriminative dictionary learning and linear classifier training into a unified model. Specifically, NRDL introduces a positive constraint on representation matrix to find distinct atoms from heterogeneous training samples, which results in sparse and discriminative representation. Moreover, a discriminative dictionary encouraging function is proposed to enhance the uniqueness of class-specific sub-dictionaries. Meanwhile, an inter-class incoherence constraint and a compact graph based regularization term are constructed to respectively improve the discriminability of learned classifier. Experimental results on several benchmark face data sets verify the advantages of our NRDL algorithm over the state-of-the-art dictionary learning methods. |
| Tasks | Dictionary Learning, Face Recognition |
| Published | 2019-03-19 |
| URL | https://arxiv.org/abs/1903.07836v2 |
| https://arxiv.org/pdf/1903.07836v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-negative-representation-based |
| Repo | |
| Framework | |
Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices
| Title | Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices |
| Authors | Yaoyi Li, Jianfu Zhang, Weijie Zhao, Hongtao Lu |
| Abstract | Recently, significant progress has been achieved in deep image matting. Most of the classical image matting methods are time-consuming and require an ideal trimap which is difficult to attain in practice. A high efficient image matting method based on a weakly annotated mask is in demand for mobile applications. In this paper, we propose a novel method based on Deep Learning and Guided Filter, called Inductive Guided Filter, which can tackle the real-time general image matting task on mobile devices. We design a lightweight hourglass network to parameterize the original Guided Filter method that takes an image and a weakly annotated mask as input. Further, the use of Gabor loss is proposed for training networks for complicated textures in image matting. Moreover, we create an image matting dataset MAT-2793 with a variety of foreground objects. Experimental results demonstrate that our proposed method massively reduces running time with robust accuracy. |
| Tasks | Image Matting |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06747v1 |
| https://arxiv.org/pdf/1905.06747v1.pdf | |
| PWC | https://paperswithcode.com/paper/inductive-guided-filter-real-time-deep-image |
| Repo | |
| Framework | |
From Observability to Significance in Distributed Information Systems
| Title | From Observability to Significance in Distributed Information Systems |
| Authors | Mark Burgess |
| Abstract | To understand and explain process behaviour we need to be able to see it, and decide its significance, i.e. be able to tell a story about its behaviours. This paper describes a few of the modelling challenges that underlie monitoring and observation of processes in IT, by human or by software. The topic of the observability of systems has been elevated recently in connection with computer monitoring and tracing of processes for debugging and forensics. It raises the issue of well-known principles of measurement, in bounded contexts, but these issues have been left implicit in the Computer Science literature. This paper aims to remedy this omission, by laying out a simple promise theoretic model, summarizing a long standing trail of work on the observation of distributed systems, based on elementary distinguishability of observations, and classical causality, with history. Three distinct views of a system are sought, across a number of scales, that described how information is transmitted (and lost) as it moves around the system, aggregated into journals and logs. |
| Tasks | |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05636v2 |
| https://arxiv.org/pdf/1907.05636v2.pdf | |
| PWC | https://paperswithcode.com/paper/from-observability-to-significance-in |
| Repo | |
| Framework | |
Association rule mining and itemset-correlation based variants
| Title | Association rule mining and itemset-correlation based variants |
| Authors | Niels Mündler |
| Abstract | Association rules express implication formed relations among attributes in databases of itemsets. The apriori algorithm is presented, the basis for most association rule mining algorithms. It works by pruning away rules that need not be evaluated based on the user specified minimum support confidence. Additionally, variations of the algorithm are presented that enable it to handle quantitative attributes and to extract rules about generalizations of items, but preserve the downward closure property that enables pruning. Intertransformation of the extensions is proposed for special cases. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09535v1 |
| https://arxiv.org/pdf/1907.09535v1.pdf | |
| PWC | https://paperswithcode.com/paper/association-rule-mining-and-itemset |
| Repo | |
| Framework | |
Spatio-Temporal RBF Neural Networks
| Title | Spatio-Temporal RBF Neural Networks |
| Authors | Shujaat Khan, Jawwad Ahmad, Alishba Sadiq, Imran Naseem, Muhammad Moinuddin |
| Abstract | Herein, we propose a spatio-temporal extension of RBFNN for nonlinear system identification problem. The proposed algorithm employs the concept of time-space orthogonality and separately models the dynamics and nonlinear complexities of the system. The proposed RBF architecture is explored for the estimation of a highly nonlinear system and results are compared with the standard architecture for both the conventional and fractional gradient decent-based learning rules. The spatio-temporal RBF is shown to perform better than the standard and fractional RBFNNs by achieving fast convergence and significantly reduced estimation error. |
| Tasks | |
| Published | 2019-08-04 |
| URL | https://arxiv.org/abs/1908.01321v1 |
| https://arxiv.org/pdf/1908.01321v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatio-temporal-rbf-neural-networks |
| Repo | |
| Framework | |
EM Converges for a Mixture of Many Linear Regressions
| Title | EM Converges for a Mixture of Many Linear Regressions |
| Authors | Jeongyeol Kwon, Constantine Caramanis |
| Abstract | We study the convergence of the Expectation-Maximization (EM) algorithm for mixtures of linear regressions with an arbitrary number $k$ of components. We show that as long as signal-to-noise ratio (SNR) is $\tilde{\Omega}(k)$, well-initialized EM converges to the true regression parameters. Previous results for $k \geq 3$ have only established local convergence for the noiseless setting, i.e., where SNR is infinitely large. Our results enlarge the scope to the environment with noises, and notably, we establish a statistical error rate that is independent of the norm (or pairwise distance) of the regression parameters. In particular, our results imply exact recovery as $\sigma \rightarrow 0$, in contrast to most previous local convergence results for EM, where the statistical error scaled with the norm of parameters. Standard moment-method approaches may be applied to guarantee we are in the region where our local convergence guarantees apply. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12106v2 |
| https://arxiv.org/pdf/1905.12106v2.pdf | |
| PWC | https://paperswithcode.com/paper/em-converges-for-a-mixture-of-many-linear |
| Repo | |
| Framework | |
Using Latent Variable Models to Observe Academic Pathways
| Title | Using Latent Variable Models to Observe Academic Pathways |
| Authors | Nate Gruver, Ali Malik, Brahm Capoor, Chris Piech, Mitchell L. Stevens, Andreas Paepcke |
| Abstract | Understanding large-scale patterns in student course enrollment is a problem of great interest to university administrators and educational researchers. Yet important decisions are often made without a good quantitative framework of the process underlying student choices. We propose a probabilistic approach to modelling course enrollment decisions, drawing inspiration from multilabel classification and mixture models. We use ten years of anonymized student transcripts from a large university to construct a Gaussian latent variable model that learns the joint distribution over course enrollments. The models allow for a diverse set of inference queries and robustness to data sparsity. We demonstrate the efficacy of this approach in comparison to others, including deep learning architectures, and demonstrate its ability to infer the underlying student interests that guide enrollment decisions. |
| Tasks | Latent Variable Models |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13383v1 |
| https://arxiv.org/pdf/1905.13383v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-latent-variable-models-to-observe |
| Repo | |
| Framework | |
A general graph-based framework for top-N recommendation using content, temporal and trust information
| Title | A general graph-based framework for top-N recommendation using content, temporal and trust information |
| Authors | Armel Jacques Nzekon Nzeko’o, Maurice Tchuente, Matthieu Latapy |
| Abstract | Recommending appropriate items to users is crucial in many e-commerce platforms that contain implicit data as users’ browsing, purchasing and streaming history. One common approach consists in selecting the N most relevant items to each user, for a given N, which is called top-N recommendation. To do so, recommender systems rely on various kinds of information, like item and user features, past interest of users for items, browsing history and trust between users. However, they often use only one or two such pieces of information, which limits their performance. In this paper, we design and implement GraFC2T2, a general graph-based framework to easily combine and compare various kinds of side information for top-N recommendation. It encodes content-based features, temporal and trust information into a complex graph, and uses personalized PageRank on this graph to perform recommendation. We conduct experiments on Epinions and Ciao datasets, and compare obtained performances using F1-score, Hit ratio and MAP evaluation metrics, to systems based on matrix factorization and deep learning. This shows that our framework is convenient for such explorations, and that combining different kinds of information indeed improves recommendation in general. |
| Tasks | Recommendation Systems |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02681v1 |
| https://arxiv.org/pdf/1905.02681v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-graph-based-framework-for-top-n |
| Repo | |
| Framework | |
Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction
| Title | Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction |
| Authors | Xiangbo Shu, Liyan Zhang, Guo-Jun Qi, Wei Liu, Jinhui Tang |
| Abstract | Human motion prediction aims to generate future motions based on the observed human motions. Witnessing the success of Recurrent Neural Networks (RNN) in modeling the sequential data, recent works utilize RNN to model human-skeleton motion on the observed motion sequence and predict future human motions. However, these methods did not consider the existence of the spatial coherence among joints and the temporal evolution among skeletons, which reflects the crucial characteristics of human motion in spatiotemporal space. To this end, we propose a novel Skeleton-joint Co-attention Recurrent Neural Networks (SC-RNN) to capture the spatial coherence among joints, and the temporal evolution among skeletons simultaneously on a skeleton-joint co-attention feature map in spatiotemporal space. First, a skeleton-joint feature map is constructed as the representation of the observed motion sequence. Second, we design a new Skeleton-joint Co-Attention (SCA) mechanism to dynamically learn a skeleton-joint co-attention feature map of this skeleton-joint feature map, which can refine the useful observed motion information to predict one future motion. Third, a variant of GRU embedded with SCA collaboratively models the human-skeleton motion and human-joint motion in spatiotemporal space by regarding the skeleton-joint co-attention feature map as the motion context. Experimental results on human motion prediction demonstrate the proposed method outperforms the related methods. |
| Tasks | motion prediction |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13245v2 |
| https://arxiv.org/pdf/1909.13245v2.pdf | |
| PWC | https://paperswithcode.com/paper/spatiotemporal-co-attention-recurrent-neural |
| Repo | |
| Framework | |
Unpaired Image Translation via Adaptive Convolution-based Normalization
| Title | Unpaired Image Translation via Adaptive Convolution-based Normalization |
| Authors | Wonwoong Cho, Kangyeol Kim, Eungyeup Kim, Hyunwoo J. Kim, Jaegul Choo |
| Abstract | Disentangling content and style information of an image has played an important role in recent success in image translation. In this setting, how to inject given style into an input image containing its own content is an important issue, but existing methods followed relatively simple approaches, leaving room for improvement especially when incorporating significant style changes. In response, we propose an advanced normalization technique based on adaptive convolution (AdaCoN), in order to properly impose style information into the content of an input image. In detail, after locally standardizing the content representation in a channel-wise manner, AdaCoN performs adaptive convolution where the convolution filter weights are dynamically estimated using the encoded style representation. The flexibility of AdaCoN can handle complicated image translation tasks involving significant style changes. Our qualitative and quantitative experiments demonstrate the superiority of our proposed method against various existing approaches that inject the style into the content. |
| Tasks | |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1911.13271v1 |
| https://arxiv.org/pdf/1911.13271v1.pdf | |
| PWC | https://paperswithcode.com/paper/unpaired-image-translation-via-adaptive |
| Repo | |
| Framework | |
A Spiking Neural Network with Local Learning Rules Derived From Nonnegative Similarity Matching
| Title | A Spiking Neural Network with Local Learning Rules Derived From Nonnegative Similarity Matching |
| Authors | Cengiz Pehlevan |
| Abstract | The design and analysis of spiking neural network algorithms will be accelerated by the advent of new theoretical approaches. In an attempt at such approach, we provide a principled derivation of a spiking algorithm for unsupervised learning, starting from the nonnegative similarity matching cost function. The resulting network consists of integrate-and-fire units and exhibits local learning rules, making it biologically plausible and also suitable for neuromorphic hardware. We show in simulations that the algorithm can perform sparse feature extraction and manifold learning, two tasks which can be formulated as nonnegative similarity matching problems. |
| Tasks | |
| Published | 2019-02-04 |
| URL | http://arxiv.org/abs/1902.01429v2 |
| http://arxiv.org/pdf/1902.01429v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-spiking-neural-network-with-local-learning |
| Repo | |
| Framework | |
Iterative Neural Networks with Bounded Weights
| Title | Iterative Neural Networks with Bounded Weights |
| Authors | Tomasz Piotrowski, Krzysztof Rykaczewski |
| Abstract | A recent analysis of a model of iterative neural network in Hilbert spaces established fundamental properties of such networks, such as existence of the fixed points sets, convergence analysis, and Lipschitz continuity. Building on these results, we show that under a single mild condition on the weights of the network, one is guaranteed to obtain a neural network converging to its unique fixed point. We provide a bound on the norm of this fixed point in terms of norms of weights and biases of the network. We also show why this model of a feed-forward neural network is not able to accomodate Hopfield networks under our assumption. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05982v2 |
| https://arxiv.org/pdf/1908.05982v2.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-neural-networks-with-bounded |
| Repo | |
| Framework | |
Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs
| Title | Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs |
| Authors | Lior Shani, Yonathan Efroni, Shie Mannor |
| Abstract | Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be ‘close’ to one another, is iteratively solved. Nevertheless, TRPO has been considered a heuristic algorithm inspired by Conservative Policy Iteration (CPI). We show that the adaptive scaling mechanism used in TRPO is in fact the natural “RL version” of traditional trust-region methods from convex analysis. We first analyze TRPO in the planning setting, in which we have access to the model and the entire state space. Then, we consider sample-based TRPO and establish $\tilde O(1/\sqrt{N})$ convergence rate to the global optimum. Importantly, the adaptive scaling mechanism allows us to analyze TRPO in regularized MDPs for which we prove fast rates of $\tilde O(1/N)$, much like results in convex optimization. This is the first result in RL of better rates when regularizing the instantaneous cost or reward. |
| Tasks | |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.02769v2 |
| https://arxiv.org/pdf/1909.02769v2.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-trust-region-policy-optimization |
| Repo | |
| Framework | |
