Paper Group ANR 433
Unorganized Malicious Attacks Detection. Streaming Gibbs Sampling for LDA Model. Gated Word-Character Recurrent Language Model. The face-space duality hypothesis: a computational model. Towards the Limit of Network Quantization. A Unified Framework for Compositional Fitting of Active Appearance Models. Mapping Out Narrative Structures and Dynamics …
Unorganized Malicious Attacks Detection
| Title | Unorganized Malicious Attacks Detection |
| Authors | Ming Pang, Wei Gao, Min Tao, Zhi-Hua Zhou |
| Abstract | Recommender system has attracted much attention during the past decade. Many attack detection algorithms have been developed for better recommendations, mostly focusing on shilling attacks, where an attack organizer produces a large number of user profiles by the same strategy to promote or demote an item. This work considers a different attack style: unorganized malicious attacks, where attackers individually utilize a small number of user profiles to attack different items without any organizer. This attack style occurs in many real applications, yet relevant study remains open. We first formulate the unorganized malicious attacks detection as a matrix completion problem, and propose the Unorganized Malicious Attacks detection (UMA) approach, a proximal alternating splitting augmented Lagrangian method. We verify, both theoretically and empirically, the effectiveness of our proposed approach. |
| Tasks | Matrix Completion, Recommendation Systems |
| Published | 2016-10-13 |
| URL | http://arxiv.org/abs/1610.04086v3 |
| http://arxiv.org/pdf/1610.04086v3.pdf | |
| PWC | https://paperswithcode.com/paper/unorganized-malicious-attacks-detection |
| Repo | |
| Framework | |
Streaming Gibbs Sampling for LDA Model
| Title | Streaming Gibbs Sampling for LDA Model |
| Authors | Yang Gao, Jianfei Chen, Jun Zhu |
| Abstract | Streaming variational Bayes (SVB) is successful in learning LDA models in an online manner. However previous attempts toward developing online Monte-Carlo methods for LDA have little success, often by having much worse perplexity than their batch counterparts. We present a streaming Gibbs sampling (SGS) method, an online extension of the collapsed Gibbs sampling (CGS). Our empirical study shows that SGS can reach similar perplexity as CGS, much better than SVB. Our distributed version of SGS, DSGS, is much more scalable than SVB mainly because the updates’ communication complexity is small. |
| Tasks | |
| Published | 2016-01-06 |
| URL | http://arxiv.org/abs/1601.01142v1 |
| http://arxiv.org/pdf/1601.01142v1.pdf | |
| PWC | https://paperswithcode.com/paper/streaming-gibbs-sampling-for-lda-model |
| Repo | |
| Framework | |
Gated Word-Character Recurrent Language Model
| Title | Gated Word-Character Recurrent Language Model |
| Authors | Yasumasa Miyamoto, Kyunghyun Cho |
| Abstract | We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has a gate that adaptively finds the optimal mixture of the character-level and word-level inputs. The gate creates the final vector representation of a word by combining two distinct representations of the word. The character-level inputs are converted into vector representations of words using a bidirectional LSTM. The word-level inputs are projected into another high-dimensional space by a word lookup table. The final vector representations of words are used in the LSTM language model which predicts the next word given all the preceding words. Our model with the gating mechanism effectively utilizes the character-level inputs for rare and out-of-vocabulary words and outperforms word-level language models on several English corpora. |
| Tasks | Language Modelling |
| Published | 2016-06-06 |
| URL | http://arxiv.org/abs/1606.01700v2 |
| http://arxiv.org/pdf/1606.01700v2.pdf | |
| PWC | https://paperswithcode.com/paper/gated-word-character-recurrent-language-model |
| Repo | |
| Framework | |
The face-space duality hypothesis: a computational model
| Title | The face-space duality hypothesis: a computational model |
| Authors | Jonathan Vitale, Mary-Anne Williams, Benjamin Johnston |
| Abstract | Valentine’s face-space suggests that faces are represented in a psychological multidimensional space according to their perceived properties. However, the proposed framework was initially designed as an account of invariant facial features only, and explanations for dynamic features representation were neglected. In this paper we propose, develop and evaluate a computational model for a twofold structure of the face-space, able to unify both identity and expression representations in a single implemented model. To capture both invariant and dynamic facial features we introduce the face-space duality hypothesis and subsequently validate it through a mathematical presentation using a general approach to dimensionality reduction. Two experiments with real facial images show that the proposed face-space: (1) supports both identity and expression recognition, and (2) has a twofold structure anticipated by our formal argument. |
| Tasks | Dimensionality Reduction |
| Published | 2016-09-23 |
| URL | http://arxiv.org/abs/1609.07371v1 |
| http://arxiv.org/pdf/1609.07371v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-face-space-duality-hypothesis-a |
| Repo | |
| Framework | |
Towards the Limit of Network Quantization
| Title | Towards the Limit of Network Quantization |
| Authors | Yoojin Choi, Mostafa El-Khamy, Jungwon Lee |
| Abstract | Network quantization is one of network compression techniques to reduce the redundancy of deep neural networks. It reduces the number of distinct network parameter values by quantization in order to save the storage for them. In this paper, we design network quantization schemes that minimize the performance loss due to quantization given a compression ratio constraint. We analyze the quantitative relation of quantization errors to the neural network loss function and identify that the Hessian-weighted distortion measure is locally the right objective function for the optimization of network quantization. As a result, Hessian-weighted k-means clustering is proposed for clustering network parameters to quantize. When optimal variable-length binary codes, e.g., Huffman codes, are employed for further compression, we derive that the network quantization problem can be related to the entropy-constrained scalar quantization (ECSQ) problem in information theory and consequently propose two solutions of ECSQ for network quantization, i.e., uniform quantization and an iterative solution similar to Lloyd’s algorithm. Finally, using the simple uniform quantization followed by Huffman coding, we show from our experiments that the compression ratios of 51.25, 22.17 and 40.65 are achievable for LeNet, 32-layer ResNet and AlexNet, respectively. |
| Tasks | Quantization |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.01543v2 |
| http://arxiv.org/pdf/1612.01543v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-the-limit-of-network-quantization |
| Repo | |
| Framework | |
A Unified Framework for Compositional Fitting of Active Appearance Models
| Title | A Unified Framework for Compositional Fitting of Active Appearance Models |
| Authors | Joan Alabort-i-Medina, Stefanos Zafeiriou |
| Abstract | Active Appearance Models (AAMs) are one of the most popular and well-established techniques for modeling deformable objects in computer vision. In this paper, we study the problem of fitting AAMs using Compositional Gradient Descent (CGD) algorithms. We present a unified and complete view of these algorithms and classify them with respect to three main characteristics: i) cost function; ii) type of composition; and iii) optimization method. Furthermore, we extend the previous view by: a) proposing a novel Bayesian cost function that can be interpreted as a general probabilistic formulation of the well-known project-out loss; b) introducing two new types of composition, asymmetric and bidirectional, that combine the gradients of both image and appearance model to derive better conver- gent and more robust CGD algorithms; and c) providing new valuable insights into existent CGD algorithms by reinterpreting them as direct applications of the Schur complement and the Wiberg method. Finally, in order to encourage open research and facilitate future comparisons with our work, we make the implementa- tion of the algorithms studied in this paper publicly available as part of the Menpo Project. |
| Tasks | |
| Published | 2016-01-02 |
| URL | http://arxiv.org/abs/1601.00199v1 |
| http://arxiv.org/pdf/1601.00199v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-framework-for-compositional-fitting |
| Repo | |
| Framework | |
Mapping Out Narrative Structures and Dynamics Using Networks and Textual Information
| Title | Mapping Out Narrative Structures and Dynamics Using Networks and Textual Information |
| Authors | Semi Min, Juyong Park |
| Abstract | Human communication is often executed in the form of a narrative, an account of connected events composed of characters, actions, and settings. A coherent narrative structure is therefore a requisite for a well-formulated narrative – be it fictional or nonfictional – for informative and effective communication, opening up the possibility of a deeper understanding of a narrative by studying its structural properties. In this paper we present a network-based framework for modeling and analyzing the structure of a narrative, which is further expanded by incorporating methods from computational linguistics to utilize the narrative text. Modeling a narrative as a dynamically unfolding system, we characterize its progression via the growth patterns of the character network, and use sentiment analysis and topic modeling to represent the actual content of the narrative in the form of interaction maps between characters with associated sentiment values and keywords. This is a network framework advanced beyond the simple occurrence-based one most often used until now, allowing one to utilize the unique characteristics of a given narrative to a high degree. Given the ubiquity and importance of narratives, such advanced network-based representation and analysis framework may lead to a more systematic modeling and understanding of narratives for social interactions, expression of human sentiments, and communication. |
| Tasks | Sentiment Analysis |
| Published | 2016-03-24 |
| URL | http://arxiv.org/abs/1604.03029v1 |
| http://arxiv.org/pdf/1604.03029v1.pdf | |
| PWC | https://paperswithcode.com/paper/mapping-out-narrative-structures-and-dynamics |
| Repo | |
| Framework | |
Are Accuracy and Robustness Correlated?
| Title | Are Accuracy and Robustness Correlated? |
| Authors | Andras Rozsa, Manuel Günther, Terrance E. Boult |
| Abstract | Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial example generation approaches with multiple deep convolutional neural networks including Residual Networks, the best performing models on ImageNet Large-Scale Visual Recognition Challenge 2015. We compare the adversarial example generation techniques with respect to the quality of the produced images, and measure the robustness of the tested machine learning models to adversarial examples. Finally, we conduct large-scale experiments on cross-model adversarial portability. We find that adversarial examples are mostly transferable across similar network topologies, and we demonstrate that better machine learning models are less vulnerable to adversarial examples. |
| Tasks | Object Recognition |
| Published | 2016-10-14 |
| URL | http://arxiv.org/abs/1610.04563v2 |
| http://arxiv.org/pdf/1610.04563v2.pdf | |
| PWC | https://paperswithcode.com/paper/are-accuracy-and-robustness-correlated |
| Repo | |
| Framework | |
A comparative study of complexity of handwritten Bharati characters with that of major Indian scripts
| Title | A comparative study of complexity of handwritten Bharati characters with that of major Indian scripts |
| Authors | Manali Naik, V. Srinivasa Chakravarthy |
| Abstract | We present Bharati, a simple, novel script that can represent the characters of a majority of contemporary Indian scripts. The shapes/motifs of Bharati characters are drawn from some of the simplest characters of existing Indian scripts. Bharati characters are designed such that they strictly reflect the underlying phonetic organization, thereby attributing to the script qualities of simplicity, familiarity, ease of acquisition and use. Thus, employing Bharati script as a common script for a majority of Indian languages can ameliorate several existing communication bottlenecks in India. We perform a complexity analysis of handwritten Bharati script and compare its complexity with that of 9 major Indian scripts. The measures of complexity are derived from a theory of handwritten characters based on Catastrophe theory. Bharati script is shown to be simpler than the 9 major Indian scripts in most measures of complexity. |
| Tasks | |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09227v1 |
| http://arxiv.org/pdf/1609.09227v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparative-study-of-complexity-of |
| Repo | |
| Framework | |
Constructive neural network learning
| Title | Constructive neural network learning |
| Authors | Shaobo Lin, Jinshan Zeng, Xiaoqin Zhang |
| Abstract | In this paper, we aim at developing scalable neural network-type learning systems. Motivated by the idea of “constructive neural networks” in approximation theory, we focus on “constructing” rather than “training” feed-forward neural networks (FNNs) for learning, and propose a novel FNNs learning system called the constructive feed-forward neural network (CFN). Theoretically, we prove that the proposed method not only overcomes the classical saturation problem for FNN approximation, but also reaches the optimal learning rate when the regression function is smooth, while the state-of-the-art learning rates established for traditional FNNs are only near optimal (up to a logarithmic factor). A series of numerical simulations are provided to show the efficiency and feasibility of CFN via comparing with the well-known regularized least squares (RLS) with Gaussian kernel and extreme learning machine (ELM). |
| Tasks | |
| Published | 2016-04-30 |
| URL | http://arxiv.org/abs/1605.00079v1 |
| http://arxiv.org/pdf/1605.00079v1.pdf | |
| PWC | https://paperswithcode.com/paper/constructive-neural-network-learning |
| Repo | |
| Framework | |
Modeling Electrical Daily Demand in Presence of PHEVs in Smart Grids with Supervised Learning
| Title | Modeling Electrical Daily Demand in Presence of PHEVs in Smart Grids with Supervised Learning |
| Authors | Marco Pellegrini, Farshad Rassaei |
| Abstract | Replacing a portion of current light duty vehicles (LDV) with plug-in hybrid electric vehicles (PHEVs) offers the possibility to reduce the dependence on petroleum fuels together with environmental and economic benefits. The charging activity of PHEVs will certainly introduce new load to the power grid. In the framework of the development of a smarter grid, the primary focus of the present study is to propose a model for the electrical daily demand in presence of PHEVs charging. Expected PHEV demand is modeled by the PHEV charging time and the starting time of charge according to real world data. A normal distribution for starting time of charge is assumed. Several distributions for charging time are considered: uniform distribution, Gaussian with positive support, Rician distribution and a non-uniform distribution coming from driving patterns in real-world data. We generate daily demand profiles by using real-world residential profiles throughout 2014 in the presence of different expected PHEV demand models. Support vector machines (SVMs), a set of supervised machine learning models, are employed in order to find the best model to fit the data. SVMs with radial basis function (RBF) and polynomial kernels were tested. Model performances are evaluated by means of mean squared error (MSE) and mean absolute percentage error (MAPE). Best results are obtained with RBF kernel: maximum (worst) values for MSE and MAPE were about 2.89 10-8 and 0.023, respectively. |
| Tasks | |
| Published | 2016-04-14 |
| URL | http://arxiv.org/abs/1604.04213v1 |
| http://arxiv.org/pdf/1604.04213v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-electrical-daily-demand-in-presence |
| Repo | |
| Framework | |
Algorithms for item categorization based on ordinal ranking data
| Title | Algorithms for item categorization based on ordinal ranking data |
| Authors | Josh Girson, Shuchin Aeron |
| Abstract | We present a new method for identifying the latent categorization of items based on their rankings. Complimenting a recent work that uses a Dirichlet prior on preference vectors and variational inference, we show that this problem can be effectively dealt with using existing community detection algorithms, with the communities corresponding to item categories. In particular we convert the bipartite ranking data to a unipartite graph of item affinities, and apply community detection algorithms. In this context we modify an existing algorithm - namely the label propagation algorithm to a variant that uses the distance between the nodes for weighting the label propagation - to identify the categories. We propose and analyze a synthetic ordinal ranking model and show its relation to the recently much studied stochastic block model. We test our algorithms on synthetic data and compare performance with several popular community detection algorithms. We also test the method on real data sets of movie categorization from the Movie Lens database. In all of the cases our algorithm is able to identify the categories for a suitable choice of tuning parameter. |
| Tasks | Community Detection |
| Published | 2016-09-29 |
| URL | http://arxiv.org/abs/1609.09544v1 |
| http://arxiv.org/pdf/1609.09544v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithms-for-item-categorization-based-on |
| Repo | |
| Framework | |
Quantitative Entropy Study of Language Complexity
| Title | Quantitative Entropy Study of Language Complexity |
| Authors | R. R. Xie, W. B. Deng, D. J. Wang, L. P. Csernai |
| Abstract | We study the entropy of Chinese and English texts, based on characters in case of Chinese texts and based on words for both languages. Significant differences are found between the languages and between different personal styles of debating partners. The entropy analysis points in the direction of lower entropy, that is of higher complexity. Such a text analysis would be applied for individuals of different styles, a single individual at different age, as well as different groups of the population. |
| Tasks | |
| Published | 2016-11-14 |
| URL | http://arxiv.org/abs/1611.04841v2 |
| http://arxiv.org/pdf/1611.04841v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantitative-entropy-study-of-language |
| Repo | |
| Framework | |
On Detection and Structural Reconstruction of Small-World Random Networks
| Title | On Detection and Structural Reconstruction of Small-World Random Networks |
| Authors | T. Tony Cai, Tengyuan Liang, Alexander Rakhlin |
| Abstract | In this paper, we study detection and fast reconstruction of the celebrated Watts-Strogatz (WS) small-world random graph model \citep{watts1998collective} which aims to describe real-world complex networks that exhibit both high clustering and short average length properties. The WS model with neighborhood size $k$ and rewiring probability probability $\beta$ can be viewed as a continuous interpolation between a deterministic ring lattice graph and the Erd\H{o}s-R'{e}nyi random graph. We study both the computational and statistical aspects of detecting the deterministic ring lattice structure (or local geographical links, strong ties) in the presence of random connections (or long range links, weak ties), and for its recovery. The phase diagram in terms of $(k,\beta)$ is partitioned into several regions according to the difficulty of the problem. We propose distinct methods for the various regions. |
| Tasks | |
| Published | 2016-04-21 |
| URL | http://arxiv.org/abs/1604.06474v1 |
| http://arxiv.org/pdf/1604.06474v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-detection-and-structural-reconstruction-of |
| Repo | |
| Framework | |
MCMC Louvain for Online Community Detection
| Title | MCMC Louvain for Online Community Detection |
| Authors | Yves Darmaillac, Sébastien Loustau |
| Abstract | We introduce a novel algorithm of community detection that maintains dynamically a community structure of a large network that evolves with time. The algorithm maximizes the modularity index thanks to the construction of a randomized hierarchical clustering based on a Monte Carlo Markov Chain (MCMC) method. Interestingly, it could be seen as a dynamization of Louvain algorithm (see Blondel et Al, 2008) where the aggregation step is replaced by the hierarchical instrumental probability. |
| Tasks | Community Detection, Online Community Detection |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.01489v1 |
| http://arxiv.org/pdf/1612.01489v1.pdf | |
| PWC | https://paperswithcode.com/paper/mcmc-louvain-for-online-community-detection |
| Repo | |
| Framework | |
