October 19, 2019

3073 words 15 mins read

Paper Group ANR 379

DeepWrinkles: Accurate and Realistic Clothing Modeling. Stable Opponent Shaping in Differentiable Games. A small Griko-Italian speech translation corpus. Some Theoretical Properties of GANs. Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending. Learning Cross-Lingual Sentence Representations via a Multi-task Dual-En …

DeepWrinkles: Accurate and Realistic Clothing Modeling


Title	DeepWrinkles: Accurate and Realistic Clothing Modeling
Authors	Zorah Laehner, Daniel Cremers, Tony Tung
Abstract	We present a novel method to generate accurate and realistic clothing deformation from real data capture. Previous methods for realistic cloth modeling mainly rely on intensive computation of physics-based simulation (with numerous heuristic parameters), while models reconstructed from visual observations typically suffer from lack of geometric details. Here, we propose an original framework consisting of two modules that work jointly to represent global shape deformation as well as surface details with high fidelity. Global shape deformations are recovered from a subspace model learned from 3D data of clothed people in motion, while high frequency details are added to normal maps created using a conditional Generative Adversarial Network whose architecture is designed to enforce realism and temporal consistency. This leads to unprecedented high-quality rendering of clothing deformation sequences, where fine wrinkles from (real) high resolution observations can be recovered. In addition, as the model is learned independently from body shape and pose, the framework is suitable for applications that require retargeting (e.g., body animation). Our experiments show original high quality results with a flexible model. We claim an entirely data-driven approach to realistic cloth wrinkle generation is possible.
Tasks
Published	2018-08-10
URL	http://arxiv.org/abs/1808.03417v1
PDF	http://arxiv.org/pdf/1808.03417v1.pdf
PWC	https://paperswithcode.com/paper/deepwrinkles-accurate-and-realistic-clothing
Repo
Framework

Stable Opponent Shaping in Differentiable Games


Title	Stable Opponent Shaping in Differentiable Games
Authors	Alistair Letcher, Jakob Foerster, David Balduzzi, Tim Rocktäschel, Shimon Whiteson
Abstract	A growing number of learning methods are actually differentiable games whose players optimise multiple, interdependent objectives in parallel – from GANs and intrinsic curiosity to multi-agent RL. Opponent shaping is a powerful approach to improve learning dynamics in these games, accounting for player influence on others’ updates. Learning with Opponent-Learning Awareness (LOLA) is a recent algorithm that exploits this response and leads to cooperation in settings like the Iterated Prisoner’s Dilemma. Although experimentally successful, we show that LOLA agents can exhibit ‘arrogant’ behaviour directly at odds with convergence. In fact, remarkably few algorithms have theoretical guarantees applying across all (n-player, non-convex) games. In this paper we present Stable Opponent Shaping (SOS), a new method that interpolates between LOLA and a stable variant named LookAhead. We prove that LookAhead converges locally to equilibria and avoids strict saddles in all differentiable games. SOS inherits these essential guarantees, while also shaping the learning of opponents and consistently either matching or outperforming LOLA experimentally.
Tasks
Published	2018-11-20
URL	http://arxiv.org/abs/1811.08469v2
PDF	http://arxiv.org/pdf/1811.08469v2.pdf
PWC	https://paperswithcode.com/paper/stable-opponent-shaping-in-differentiable
Repo
Framework

A small Griko-Italian speech translation corpus


Title	A small Griko-Italian speech translation corpus
Authors	Marcely Zanon Boito, Antonios Anastasopoulos, Marika Lekakou, Aline Villavicencio, Laurent Besacier
Abstract	This paper presents an extension to a very low-resource parallel corpus collected in an endangered language, Griko, making it useful for computational research. The corpus consists of 330 utterances (about 20 minutes of speech) which have been transcribed and translated in Italian, with annotations for word-level speech-to-transcription and speech-to-translation alignments. The corpus also includes morphosyntactic tags and word-level glosses. Applying an automatic unit discovery method, pseudo-phones were also generated. We detail how the corpus was collected, cleaned and processed, and we illustrate its use on zero-resource tasks by presenting some baseline results for the task of speech-to-translation alignment and unsupervised word discovery. The dataset is available online, aiming to encourage replicability and diversity in computational language documentation experiments.
Tasks
Published	2018-07-27
URL	http://arxiv.org/abs/1807.10740v1
PDF	http://arxiv.org/pdf/1807.10740v1.pdf
PWC	https://paperswithcode.com/paper/a-small-griko-italian-speech-translation
Repo
Framework

Some Theoretical Properties of GANs


Title	Some Theoretical Properties of GANs
Authors	G. Biau, B. Cadre, M. Sangnier, U. Tanielian
Abstract	Generative Adversarial Networks (GANs) are a class of generative algorithms that have been shown to produce state-of-the art samples, especially in the domain of image creation. The fundamental principle of GANs is to approximate the unknown distribution of a given data set by optimizing an objective function through an adversarial game between a family of generators and a family of discriminators. In this paper, we offer a better theoretical understanding of GANs by analyzing some of their mathematical and statistical properties. We study the deep connection between the adversarial principle underlying GANs and the Jensen-Shannon divergence, together with some optimality characteristics of the problem. An analysis of the role of the discriminator family via approximation arguments is also provided. In addition, taking a statistical point of view, we study the large sample properties of the estimated distribution and prove in particular a central limit theorem. Some of our results are illustrated with simulated examples.
Tasks
Published	2018-03-21
URL	http://arxiv.org/abs/1803.07819v1
PDF	http://arxiv.org/pdf/1803.07819v1.pdf
PWC	https://paperswithcode.com/paper/some-theoretical-properties-of-gans
Repo
Framework

Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending


Title	Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending
Authors	Cong Feng, Jie Zhang
Abstract	With the increasing penetration of solar power into power systems, forecasting becomes critical in power system operations. In this paper, an hourly-similarity (HS) based method is developed for 1-hour-ahead (1HA) global horizontal irradiance (GHI) forecasting. This developed method utilizes diurnal patterns, statistical distinctions between different hours, and hourly similarities in solar data to improve the forecasting accuracy. The HS-based method is built by training multiple two-layer multi-model forecasting framework (MMFF) models independently with the same-hour subsets. The final optimal model is a combination of MMFF models with the best-performed blending algorithm at every hour. At the forecasting stage, the most suitable model is selected to perform the forecasting subtask of a certain hour. The HS-based method is validated by 1-year data with six solar features collected by the National Renewable Energy Laboratory (NREL). Results show that the HS-based method outperforms the non-HS (all-in-one) method significantly with the same MMFF architecture, wherein the optimal HS- based method outperforms the best all-in-one method by 10.94% and 7.74% based on the normalized mean absolute error and normalized root mean square error, respectively.
Tasks
Published	2018-03-09
URL	http://arxiv.org/abs/1803.03623v1
PDF	http://arxiv.org/pdf/1803.03623v1.pdf
PWC	https://paperswithcode.com/paper/hourly-similarity-based-solar-forecasting
Repo
Framework

Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model


Title	Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model
Authors	Muthuraman Chidambaram, Yinfei Yang, Daniel Cer, Steve Yuan, Yun-Hsuan Sung, Brian Strope, Ray Kurzweil
Abstract	A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the performance from training on English tasks to non-English tasks, despite little to no task-specific non-English data. In this paper, we explore a natural setup for learning cross-lingual sentence representations: the dual-encoder. We provide a comprehensive evaluation of our cross-lingual representations on a number of monolingual, cross-lingual, and zero-shot/few-shot learning tasks, and also give an analysis of different learned cross-lingual embedding spaces.
Tasks	Few-Shot Learning, Language Modelling
Published	2018-10-30
URL	https://arxiv.org/abs/1810.12836v4
PDF	https://arxiv.org/pdf/1810.12836v4.pdf
PWC	https://paperswithcode.com/paper/learning-cross-lingual-sentence
Repo
Framework

Root-cause Analysis for Time-series Anomalies via Spatiotemporal Graphical Modeling in Distributed Complex Systems


Title	Root-cause Analysis for Time-series Anomalies via Spatiotemporal Graphical Modeling in Distributed Complex Systems
Authors	Chao Liu, Kin Gwn Lore, Zhanhong Jiang, Soumik Sarkar
Abstract	Performance monitoring, anomaly detection, and root-cause analysis in complex cyber-physical systems (CPSs) are often highly intractable due to widely diverse operational modes, disparate data types, and complex fault propagation mechanisms. This paper presents a new data-driven framework for root-cause analysis, based on a spatiotemporal graphical modeling approach built on the concept of symbolic dynamics for discovering and representing causal interactions among sub-systems of complex CPSs. We formulate the root-cause analysis problem as a minimization problem via the proposed inference based metric and present two approximate approaches for root-cause analysis, namely the sequential state switching ($S^3$, based on free energy concept of a restricted Boltzmann machine, RBM) and artificial anomaly association ($A^3$, a classification framework using deep neural networks, DNN). Synthetic data from cases with failed pattern(s) and anomalous node(s) are simulated to validate the proposed approaches. Real dataset based on Tennessee Eastman process (TEP) is also used for comparison with other approaches. The results show that: (1) $S^3$ and $A^3$ approaches can obtain high accuracy in root-cause analysis under both pattern-based and node-based fault scenarios, in addition to successfully handling multiple nominal operating modes, (2) the proposed tool-chain is shown to be scalable while maintaining high accuracy, and (3) the proposed framework is robust and adaptive in different fault conditions and performs better in comparison with the state-of-the-art methods.
Tasks	Anomaly Detection, Time Series
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12296v1
PDF	http://arxiv.org/pdf/1805.12296v1.pdf
PWC	https://paperswithcode.com/paper/root-cause-analysis-for-time-series-anomalies
Repo
Framework

Alzheimer’s Disease Diagnosis Based on Cognitive Methods in Virtual Environments and Emotions Analysis


Title	Alzheimer’s Disease Diagnosis Based on Cognitive Methods in Virtual Environments and Emotions Analysis
Authors	Juan Manuel Fernández Montenegro
Abstract	Dementia is a syndrome characterised by the decline of different cognitive abilities. Alzheimer’s Disease (AD) is the most common dementia affecting cognitive domains such as memory and learning, perceptual-motion or executive function. High rate of deaths and high cost for detection, treatments and patient’s care count amongst its consequences. Early detection of AD is considered of high importance for improving the quality of life of patients and their families. The aim of this thesis is to introduce novel non-invasive early diagnosis methods in order to speed the diagnosis, reduce the associated costs and make them widely accessible. Novel AD’s screening tests based on virtual environments using new immersive technologies combined with advanced Human Computer Interaction (HCI) systems are introduced. Four tests demonstrate the wide range of screening mechanisms based on cognitive domain impairments that can be designed using virtual environments. The use of emotion recognition to analyse AD symptoms has been also proposed. A novel multimodal dataset was specifically created to remark the autobiographical memory deficits of AD patients. Data from this dataset is used to introduce novel descriptors for Electroencephalogram (EEG) and facial images data. EEG features are based on quaternions in order to keep the correlation information between sensors, whereas, for facial expression recognition, a preprocessing method for motion magnification and descriptors based on origami crease pattern algorithm are proposed to enhance facial micro-expressions. These features have been proved on classifiers such as SVM and Adaboost for the classification of reactions to autobiographical stimuli such as long and short term memories.
Tasks	EEG, Emotion Recognition, Facial Expression Recognition
Published	2018-10-25
URL	http://arxiv.org/abs/1810.10941v1
PDF	http://arxiv.org/pdf/1810.10941v1.pdf
PWC	https://paperswithcode.com/paper/alzheimers-disease-diagnosis-based-on
Repo
Framework

Feature Propagation on Graph: A New Perspective to Graph Representation Learning


Title	Feature Propagation on Graph: A New Perspective to Graph Representation Learning
Authors	Biao Xiang, Ziqi Liu, Jun Zhou, Xiaolong Li
Abstract	We study feature propagation on graph, an inference process involved in graph representation learning tasks. It’s to spread the features over the whole graph to the $t$-th orders, thus to expand the end’s features. The process has been successfully adopted in graph embedding or graph neural networks, however few works studied the convergence of feature propagation. Without convergence guarantees, it may lead to unexpected numerical overflows and task failures. In this paper, we first define the concept of feature propagation on graph formally, and then study its convergence conditions to equilibrium states. We further link feature propagation to several established approaches such as node2vec and structure2vec. In the end of this paper, we extend existing approaches from represent nodes to edges (edge2vec) and demonstrate its applications on fraud transaction detection in real world scenario. Experiments show that it is quite competitive.
Tasks	Graph Embedding, Graph Representation Learning, Representation Learning
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06111v1
PDF	http://arxiv.org/pdf/1804.06111v1.pdf
PWC	https://paperswithcode.com/paper/feature-propagation-on-graph-a-new
Repo
Framework

Fast Subspace Clustering Based on the Kronecker Product


Title	Fast Subspace Clustering Based on the Kronecker Product
Authors	Lei Zhou, Xiao Bai, Xianglong Liu, Jun Zhou, Hancock Edwin
Abstract	Subspace clustering is a useful technique for many computer vision applications in which the intrinsic dimension of high-dimensional data is often smaller than the ambient dimension. Spectral clustering, as one of the main approaches to subspace clustering, often takes on a sparse representation or a low-rank representation to learn a block diagonal self-representation matrix for subspace generation. However, existing methods require solving a large scale convex optimization problem with a large set of data, with computational complexity reaches O(N^3) for N data points. Therefore, the efficiency and scalability of traditional spectral clustering methods can not be guaranteed for large scale datasets. In this paper, we propose a subspace clustering model based on the Kronecker product. Due to the property that the Kronecker product of a block diagonal matrix with any other matrix is still a block diagonal matrix, we can efficiently learn the representation matrix which is formed by the Kronecker product of k smaller matrices. By doing so, our model significantly reduces the computational complexity to O(kN^{3/k}). Furthermore, our model is general in nature, and can be adapted to different regularization based subspace clustering methods. Experimental results on two public datasets show that our model significantly improves the efficiency compared with several state-of-the-art methods. Moreover, we have conducted experiments on synthetic data to verify the scalability of our model for large scale datasets.
Tasks
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05657v1
PDF	http://arxiv.org/pdf/1803.05657v1.pdf
PWC	https://paperswithcode.com/paper/fast-subspace-clustering-based-on-the
Repo
Framework

Generating Sentences Using a Dynamic Canvas


Title	Generating Sentences Using a Dynamic Canvas
Authors	Harshil Shah, Bowen Zheng, David Barber
Abstract	We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a word level generative model for natural language. It uses a recurrent neural network with a dynamic attention and canvas memory mechanism to iteratively construct sentences. By viewing the state of the memory at intermediate stages and where the model is placing its attention, we gain insight into how it constructs sentences. We demonstrate that AUTR learns a meaningful latent representation for each sentence, and achieves competitive log-likelihood lower bounds whilst being computationally efficient. It is effective at generating and reconstructing sentences, as well as imputing missing words.
Tasks
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05178v1
PDF	http://arxiv.org/pdf/1806.05178v1.pdf
PWC	https://paperswithcode.com/paper/generating-sentences-using-a-dynamic-canvas
Repo
Framework


Title	Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts
Authors	Samuel Carton, Qiaozhu Mei, Paul Resnick
Abstract	We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the important domain of detecting personal attacks in social media comments, we additionally demonstrate the importance of manually setting a semantically appropriate `default’ behavior for the model by explicitly manipulating its bias term. We develop a validation set of human-annotated personal attacks to evaluate the impact of these changes. \|
Tasks
Published	2018-09-01
URL	http://arxiv.org/abs/1809.01499v2
PDF	http://arxiv.org/pdf/1809.01499v2.pdf
PWC	https://paperswithcode.com/paper/extractive-adversarial-networks-high-recall
Repo
Framework

CoNet: Collaborative Cross Networks for Cross-Domain Recommendation


Title	CoNet: Collaborative Cross Networks for Cross-Domain Recommendation
Authors	Guangneng Hu, Yu Zhang, Qiang Yang
Abstract	The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these techniques. In this paper, we propose a novel transfer learning approach for cross-domain recommendation by using neural networks as the base model. In contrast to the matrix factorization based cross-domain techniques, our method is deep transfer learning, which can learn complex user-item interaction relationships. We assume that hidden layers in two base networks are connected by cross mappings, leading to the collaborative cross networks (CoNet). CoNet enables dual knowledge transfer across domains by introducing cross connections from one base network to another and vice versa. CoNet is achieved in multi-layer feedforward networks by adding dual connections and joint loss functions, which can be trained efficiently by back-propagation. The proposed model is thoroughly evaluated on two large real-world datasets. It outperforms baselines by relative improvements of 7.84% in NDCG. We demonstrate the necessity of adaptively selecting representations to transfer. Our model can reduce tens of thousands training examples comparing with non-transfer methods and still has the competitive performance with them.
Tasks	Recommendation Systems, Transfer Learning
Published	2018-04-18
URL	http://arxiv.org/abs/1804.06769v3
PDF	http://arxiv.org/pdf/1804.06769v3.pdf
PWC	https://paperswithcode.com/paper/conet-collaborative-cross-networks-for-cross
Repo
Framework

Convolutional neural networks with extra-classical receptive fields


Title	Convolutional neural networks with extra-classical receptive fields
Authors	Brian Hu, Stefan Mihalas
Abstract	Convolutional neural networks (CNNs) have had great success in many real-world applications and have also been used to model visual processing in the brain. However, these networks are quite brittle - small changes in the input image can dramatically change a network’s output prediction. In contrast to what is known from biology, these networks largely rely on feedforward connections, ignoring the influence of recurrent connections. They also focus on supervised rather than unsupervised learning. To address these issues, we combine traditional supervised learning via backpropagation with a specialized unsupervised learning rule to learn lateral connections between neurons within a convolutional neural network. These connections have been shown to optimally integrate information from the surround, generating extra-classical receptive fields for the neurons in our new proposed model (CNNEx). Models with optimal lateral connections are more robust to noise and achieve better performance on noisy versions of the MNIST and CIFAR-10 datasets. Resistance to noise can be further improved by combining our model with additional regularization techniques such as dropout and weight decay. Although the image statistics of MNIST and CIFAR-10 differ greatly, the same unsupervised learning rule generalized to both datasets. Our results demonstrate the potential usefulness of combining supervised and unsupervised learning techniques and suggest that the integration of lateral connections into convolutional neural networks is an important area of future research.
Tasks
Published	2018-10-27
URL	http://arxiv.org/abs/1810.11594v1
PDF	http://arxiv.org/pdf/1810.11594v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-with-extra
Repo
Framework

Learning to Fuse Things and Stuff


Title	Learning to Fuse Things and Stuff
Authors	Jie Li, Allan Raventos, Arjun Bhargava, Takaaki Tagawa, Adrien Gaidon
Abstract	We propose an end-to-end learning approach for panoptic segmentation, a novel task unifying instance (things) and semantic (stuff) segmentation. Our model, TASCNet, uses feature maps from a shared backbone network to predict in a single feed-forward pass both things and stuff segmentations. We explicitly constrain these two output distributions through a global things and stuff binary mask to enforce cross-task consistency. Our proposed unified network is competitive with the state of the art on several benchmarks for panoptic segmentation as well as on the individual semantic and instance segmentation tasks.
Tasks	Instance Segmentation, Panoptic Segmentation, Semantic Segmentation
Published	2018-12-04
URL	https://arxiv.org/abs/1812.01192v2
PDF	https://arxiv.org/pdf/1812.01192v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-fuse-things-and-stuff
Repo
Framework