October 16, 2019

3166 words 15 mins read

Paper Group ANR 1004

CoupleNet: Paying Attention to Couples with Coupled Attention for Relationship Recommendation. Efficient Fastest-Path Computations in Road Maps. Genesis of Basic and Multi-Layer Echo State Network Recurrent Autoencoders for Efficient Data Representations. Fast Training Algorithms for Deep Convolutional Fuzzy Systems with Application to Stock Index …

CoupleNet: Paying Attention to Couples with Coupled Attention for Relationship Recommendation


Title	CoupleNet: Paying Attention to Couples with Coupled Attention for Relationship Recommendation
Authors	Yi Tay, Anh Tuan Luu, Siu Cheung Hui
Abstract	Dating and romantic relationships not only play a huge role in our personal lives but also collectively influence and shape society. Today, many romantic partnerships originate from the Internet, signifying the importance of technology and the web in modern dating. In this paper, we present a text-based computational approach for estimating the relationship compatibility of two users on social media. Unlike many previous works that propose reciprocal recommender systems for online dating websites, we devise a distant supervision heuristic to obtain real world couples from social platforms such as Twitter. Our approach, the CoupleNet is an end-to-end deep learning based estimator that analyzes the social profiles of two users and subsequently performs a similarity match between the users. Intuitively, our approach performs both user profiling and match-making within a unified end-to-end framework. CoupleNet utilizes hierarchical recurrent neural models for learning representations of user profiles and subsequently coupled attention mechanisms to fuse information aggregated from two users. To the best of our knowledge, our approach is the first data-driven deep learning approach for our novel relationship recommendation problem. We benchmark our CoupleNet against several machine learning and deep learning baselines. Experimental results show that our approach outperforms all approaches significantly in terms of precision. Qualitative analysis shows that our model is capable of also producing explainable results to users.
Tasks	Recommendation Systems
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11535v1
PDF	http://arxiv.org/pdf/1805.11535v1.pdf
PWC	https://paperswithcode.com/paper/couplenet-paying-attention-to-couples-with
Repo
Framework

Efficient Fastest-Path Computations in Road Maps


Title	Efficient Fastest-Path Computations in Road Maps
Authors	Renjie Chen, Craig Gotsman
Abstract	In the age of real-time online traffic information and GPS-enabled devices, fastest-path computations between two points in a road network modeled as a directed graph, where each directed edge is weighted by a “travel time” value, are becoming a standard feature of many navigation-related applications. To support this, very efficient computation of these paths in very large road networks is critical. Fastest paths may be computed as minimal-cost paths in a weighted directed graph, but traditional minimal-cost path algorithms based on variants of the classic Dijkstra algorithm do not scale well, as in the worst case they may traverse the entire graph. A common improvement, which can dramatically reduce the number of traversed graph vertices, is the A* algorithm, which requires a good heuristic lower bound on the minimal cost. We introduce a simple, but very effective, heuristic function based on a small number of values assigned to each graph vertex. The values are based on graph separators and computed efficiently in a preprocessing stage. We present experimental results demonstrating that our heuristic provides estimates of the minimal cost which are superior to those of other heuristics. Our experiments show that when used in the A* algorithm, this heuristic can reduce the number of vertices traversed by an order of magnitude compared to other heuristics.
Tasks
Published	2018-10-02
URL	http://arxiv.org/abs/1810.01776v1
PDF	http://arxiv.org/pdf/1810.01776v1.pdf
PWC	https://paperswithcode.com/paper/efficient-fastest-path-computations-in-road
Repo
Framework

Genesis of Basic and Multi-Layer Echo State Network Recurrent Autoencoders for Efficient Data Representations


Title	Genesis of Basic and Multi-Layer Echo State Network Recurrent Autoencoders for Efficient Data Representations
Authors	Naima Chouikhi, Boudour Ammar, Adel M. Alimi
Abstract	It is a widely accepted fact that data representations intervene noticeably in machine learning tools. The more they are well defined the better the performance results are. Feature extraction-based methods such as autoencoders are conceived for finding more accurate data representations from the original ones. They efficiently perform on a specific task in terms of 1) high accuracy, 2) large short term memory and 3) low execution time. Echo State Network (ESN) is a recent specific kind of Recurrent Neural Network which presents very rich dynamics thanks to its reservoir-based hidden layer. It is widely used in dealing with complex non-linear problems and it has outperformed classical approaches in a number of tasks including regression, classification, etc. In this paper, the noticeable dynamism and the large memory provided by ESN and the strength of Autoencoders in feature extraction are gathered within an ESN Recurrent Autoencoder (ESN-RAE). In order to bring up sturdier alternative to conventional reservoir-based networks, not only single layer basic ESN is used as an autoencoder, but also Multi-Layer ESN (ML-ESN-RAE). The new features, once extracted from ESN’s hidden layer, are applied to classification tasks. The classification rates rise considerably compared to those obtained when applying the original data features. An accuracy-based comparison is performed between the proposed recurrent AEs and two variants of an ELM feed-forward AEs (Basic and ML) in both of noise free and noisy environments. The empirical study reveals the main contribution of recurrent connections in improving the classification performance results.
Tasks
Published	2018-04-24
URL	http://arxiv.org/abs/1804.08996v2
PDF	http://arxiv.org/pdf/1804.08996v2.pdf
PWC	https://paperswithcode.com/paper/genesis-of-basic-and-multi-layer-echo-state
Repo
Framework

Fast Training Algorithms for Deep Convolutional Fuzzy Systems with Application to Stock Index Prediction


Title	Fast Training Algorithms for Deep Convolutional Fuzzy Systems with Application to Stock Index Prediction
Authors	Li-Xin Wang
Abstract	A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multi-layer connection of many low-dimensional fuzzy systems, where the input variables to the low-dimensional fuzzy systems are selected through a moving window across the input spaces of the layers. To design the DCFS based on input-output data pairs, we propose a bottom-up layer-by-layer scheme. Specifically, by viewing each of the first-layer fuzzy systems as a weak estimator of the output based only on a very small portion of the input variables, we design these fuzzy systems using the WM Method. After the first-layer fuzzy systems are designed, we pass the data through the first layer to form a new data set and design the second-layer fuzzy systems based on this new data set in the same way as designing the first-layer fuzzy systems. Repeating this process layer-by-layer we design the whole DCFS. We also propose a DCFS with parameter sharing to save memory and computation. We apply the DCFS models to predict a synthetic chaotic plus random time-series and the real Hang Seng Index of the Hong Kong stock market.
Tasks	Time Series
Published	2018-12-07
URL	https://arxiv.org/abs/1812.11226v2
PDF	https://arxiv.org/pdf/1812.11226v2.pdf
PWC	https://paperswithcode.com/paper/fast-training-algorithms-for-deep
Repo
Framework

Learning with Correntropy-induced Losses for Regression with Mixture of Symmetric Stable Noise


Title	Learning with Correntropy-induced Losses for Regression with Mixture of Symmetric Stable Noise
Authors	Yunlong Feng, Yiming Ying
Abstract	In recent years, correntropy and its applications in machine learning have been drawing continuous attention owing to its merits in dealing with non-Gaussian noise and outliers. However, theoretical understanding of correntropy, especially in the statistical learning context, is still limited. In this study, within the statistical learning framework, we investigate correntropy based regression in the presence of non-Gaussian noise or outliers. Motivated by the practical way of generating non-Gaussian noise or outliers, we introduce mixture of symmetric stable noise, which include Gaussian noise, Cauchy noise, and their mixture as special cases, to model non-Gaussian noise or outliers. We demonstrate that under the mixture of symmetric stable noise assumption, correntropy based regression can learn the conditional mean function or the conditional median function well without resorting to the finite-variance or even the finite first-order moment condition on the noise. In particular, for the above two cases, we establish asymptotic optimal learning rates for correntropy based regression estimators that are asymptotically of type $\mathcal{O}(n^{-1})$. These results justify the effectiveness of the correntropy based regression estimators in dealing with outliers as well as non-Gaussian noise. We believe that the present study completes our understanding towards correntropy based regression from a statistical learning viewpoint, and may also shed some light on robust statistical learning for regression.
Tasks
Published	2018-03-01
URL	https://arxiv.org/abs/1803.00183v5
PDF	https://arxiv.org/pdf/1803.00183v5.pdf
PWC	https://paperswithcode.com/paper/learning-with-correntropy-induced-losses-for
Repo
Framework

Real Time Emulation of Parametric Guitar Tube Amplifier With Long Short Term Memory Neural Network


Title	Real Time Emulation of Parametric Guitar Tube Amplifier With Long Short Term Memory Neural Network
Authors	Thomas Schmitz, Jean-Jacques Embrechts
Abstract	Numerous audio systems for musicians are expensive and bulky. Therefore, it could be advantageous to model them and to replace them by computer emulation. In guitar players’ world, audio systems could have a desirable nonlinear behavior (distortion effects). It is thus difficult to find a simple model to emulate them in real time. Volterra series model and its subclass are usual ways to model nonlinear systems. Unfortunately, these systems are difficult to identify in an analytic way. In this paper we propose to take advantage of the new progress made in neural networks to emulate them in real time. We show that an accurate emulation can be reached with less than 1% of root mean square error between the signal coming from a tube amplifier and the output of the neural network. Moreover, the research has been extended to model the Gain parameter of the amplifier.
Tasks
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07145v1
PDF	http://arxiv.org/pdf/1804.07145v1.pdf
PWC	https://paperswithcode.com/paper/real-time-emulation-of-parametric-guitar-tube
Repo
Framework

Responsible team players wanted: an analysis of soft skill requirements in job advertisements


Title	Responsible team players wanted: an analysis of soft skill requirements in job advertisements
Authors	Federica Calanca, Luiza Sayfullina, Lara Minkus, Claudia Wagner, Eric Malmi
Abstract	During the past decades the importance of soft skills for labour market outcomes has grown substantially. This carries implications for labour market inequality, since previous research shows that soft skills are not valued equally across race and gender. This work explores the role of soft skills in job advertisements by drawing on methods from computational science as well as on theoretical and empirical insights from economics, sociology and psychology. We present a semi-automatic approach based on crowdsourcing and text mining for extracting a list of soft skills. We find that soft skills are a crucial component of job ads, especially of low-paid jobs and jobs in female-dominated professions. Our work shows that soft skills can serve as partial predictors of the gender composition in job categories and that not all soft skills receive equal wage returns at the labour market. Especially “female” skills are frequently associated with wage penalties. Our results expand the growing literature on the association of soft skills on wage inequality and highlight their importance for occupational gender segregation at labour markets.
Tasks
Published	2018-10-13
URL	http://arxiv.org/abs/1810.07781v2
PDF	http://arxiv.org/pdf/1810.07781v2.pdf
PWC	https://paperswithcode.com/paper/responsible-team-players-wanted-an-analysis
Repo
Framework

Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation


Title	Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
Authors	Tianyi Zhang, Guosheng Lin, Jianfei Cai, Tong Shen, Chunhua Shen, Alex C. Kot
Abstract	Weakly supervised semantic segmentation receives much research attention since it alleviates the need to obtain a large amount of dense pixel-wise ground-truth annotations for the training images. Compared with other forms of weak supervision, image labels are quite efficient to obtain. In our work, we focus on the weakly supervised semantic segmentation with image label annotations. Recent progress for this task has been largely dependent on the quality of generated pseudo-annotations. In this work, inspired by spatial neural-attention for image captioning, we propose a decoupled spatial neural attention network for generating pseudo-annotations. Our decoupled attention structure could simultaneously identify the object regions and localize the discriminative parts which generates high-quality pseudo-annotations in one forward path. The generated pseudo-annotations lead to the segmentation results which achieve the state-of-the-art in weakly-supervised semantic segmentation.
Tasks	Image Captioning, Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02563v1
PDF	http://arxiv.org/pdf/1803.02563v1.pdf
PWC	https://paperswithcode.com/paper/decoupled-spatial-neural-attention-for-weakly
Repo
Framework

PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence


Title	PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
Authors	Jinglan Liu, Jiaxin Zhang, Yukun Ding, Xiaowei Xu, Meng Jiang, Yiyu Shi
Abstract	This work explores the binarization of the deconvolution-based generator in a GAN for memory saving and speedup of image construction. Our study suggests that different from convolutional neural networks (including the discriminator) where all layers can be binarized, only some of the layers in the generator can be binarized without significant performance loss. Supported by theoretical analysis and verified by experiments, a direct metric based on the dimension of deconvolution operations is established, which can be used to quickly decide which layers in the generator can be binarized. Our results also indicate that both the generator and the discriminator should be binarized simultaneously for balanced competition and better performance. Experimental results based on CelebA suggest that directly applying state-of-the-art binarization techniques to all the layers of the generator will lead to 2.83$\times$ performance loss measured by sliced Wasserstein distance compared with the original generator, while applying them to selected layers only can yield up to 25.81$\times$ saving in memory consumption, and 1.96$\times$ and 1.32$\times$ speedup in inference and training respectively with little performance loss.
Tasks
Published	2018-02-26
URL	https://arxiv.org/abs/1802.09153v3
PDF	https://arxiv.org/pdf/1802.09153v3.pdf
PWC	https://paperswithcode.com/paper/pbgen-partial-binarization-of-deconvolution
Repo
Framework

An Introduction to Fuzzy & Annotated Semantic Web Languages


Title	An Introduction to Fuzzy & Annotated Semantic Web Languages
Authors	Umberto Straccia
Abstract	We present the state of the art in representing and reasoning with fuzzy knowledge in Semantic Web Languages such as triple languages RDF/RDFS, conceptual languages of the OWL 2 family and rule languages. We further show how one may generalise them to so-called annotation domains, that cover also e.g. temporal and provenance extensions.
Tasks
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05724v1
PDF	http://arxiv.org/pdf/1811.05724v1.pdf
PWC	https://paperswithcode.com/paper/an-introduction-to-fuzzy-annotated-semantic
Repo
Framework

Minimal Support Vector Machine


Title	Minimal Support Vector Machine
Authors	Shuai Zheng, Chris Ding
Abstract	Support Vector Machine (SVM) is an efficient classification approach, which finds a hyperplane to separate data from different classes. This hyperplane is determined by support vectors. In existing SVM formulations, the objective function uses L2 norm or L1 norm on slack variables. The number of support vectors is a measure of generalization errors. In this work, we propose a Minimal SVM, which uses L0.5 norm on slack variables. The result model further reduces the number of support vectors and increases the classification performance.
Tasks
Published	2018-04-06
URL	http://arxiv.org/abs/1804.02370v1
PDF	http://arxiv.org/pdf/1804.02370v1.pdf
PWC	https://paperswithcode.com/paper/minimal-support-vector-machine
Repo
Framework

Regularizing Matrix Factorization with User and Item Embeddings for Recommendation


Title	Regularizing Matrix Factorization with User and Item Embeddings for Recommendation
Authors	Thanh Tran, Kyumin Lee, Yiming Liao, Dongwon Lee
Abstract	Following recent successes in exploiting both latent factor and word embedding models in recommendation, we propose a novel Regularized Multi-Embedding (RME) based recommendation model that simultaneously encapsulates the following ideas via decomposition: (1) which items a user likes, (2) which two users co-like the same items, (3) which two items users often co-liked, and (4) which two items users often co-disliked. In experimental validation, the RME outperforms competing state-of-the-art models in both explicit and implicit feedback datasets, significantly improving Recall@5 by 5.9~7.0%, NDCG@20 by 4.3~5.6%, and MAP@10 by 7.9~8.9%. In addition, under the cold-start scenario for users with the lowest number of interactions, against the competing models, the RME outperforms NDCG@5 by 20.2% and 29.4% in MovieLens-10M and MovieLens-20M datasets, respectively. Our datasets and source code are available at: https://github.com/thanhdtran/RME.git.
Tasks
Published	2018-08-31
URL	http://arxiv.org/abs/1809.00979v1
PDF	http://arxiv.org/pdf/1809.00979v1.pdf
PWC	https://paperswithcode.com/paper/regularizing-matrix-factorization-with-user
Repo
Framework

Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text Simplification


Title	Inherent Biases in Reference based Evaluation for Grammatical Error Correction and Text Simplification
Authors	Leshem Choshen, Omri Abend
Abstract	The prevalent use of too few references for evaluating text-to-text generation is known to bias estimates of their quality ({\it low coverage bias} or LCB). This paper shows that overcoming LCB in Grammatical Error Correction (GEC) evaluation cannot be attained by re-scaling or by increasing the number of references in any feasible range, contrary to previous suggestions. This is due to the long-tailed distribution of valid corrections for a sentence. Concretely, we show that LCB incentivizes GEC systems to avoid correcting even when they can generate a valid correction. Consequently, existing systems obtain comparable or superior performance compared to humans, by making few but targeted changes to the input. Similar effects on Text Simplification further support our claims.
Tasks	Grammatical Error Correction, Text Generation, Text Simplification
Published	2018-04-30
URL	https://arxiv.org/abs/1804.11254v3
PDF	https://arxiv.org/pdf/1804.11254v3.pdf
PWC	https://paperswithcode.com/paper/inherent-biases-in-reference-based-evaluation
Repo
Framework

The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA


Title	The CORAL+ Algorithm for Unsupervised Domain Adaptation of PLDA
Authors	Kong Aik Lee, Qiongqiong Wang, Takafumi Koshinaka
Abstract	State-of-the-art speaker recognition systems comprise an x-vector (or i-vector) speaker embedding front-end followed by a probabilistic linear discriminant analysis (PLDA) backend. The effectiveness of these components relies on the availability of a large collection of labeled training data. In practice, it is common that the domains (e.g., language, demographic) in which the system are deployed differs from that we trained the system. To close the gap due to the domain mismatch, we propose an unsupervised PLDA adaptation algorithm to learn from a small amount of unlabeled in-domain data. The proposed method was inspired by a prior work on feature-based domain adaptation technique known as the correlation alignment (CORAL). We refer to the model-based adaptation technique proposed in this paper as CORAL+. The efficacy of the proposed technique is experimentally validated on the recent NIST 2016 and 2018 Speaker Recognition Evaluation (SRE’16, SRE’18) datasets.
Tasks	Domain Adaptation, Speaker Recognition, Unsupervised Domain Adaptation
Published	2018-12-26
URL	http://arxiv.org/abs/1812.10260v1
PDF	http://arxiv.org/pdf/1812.10260v1.pdf
PWC	https://paperswithcode.com/paper/the-coral-algorithm-for-unsupervised-domain
Repo
Framework

Named Person Coreference in English News


Title	Named Person Coreference in English News
Authors	Oshin Agarwal, Sanjay Subramanian, Ani Nenkova, Dan Roth
Abstract	People are often entities of interest in tasks such as search and information extraction. In these tasks, the goal is to find as much information as possible about people specified by their name. However in text, some of the references to people are by pronouns (she, his) or generic descriptions (the professor, the German chancellor). It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct person name. Here, we evaluate two state of the art coreference resolution systems on the subtask of Named Person Coreference, in which we are interested in identifying a person mentioned by name, along with all other mentions of the person, by pronoun or generic noun phrase. Our analysis reveals that standard coreference metrics do not reflect adequately the requirements in this task: they do not penalize systems for not identifying any mentions by name and they reward systems even if systems find correctly mentions to the same entity but fail to link these to a proper name (she–the student—no name). We introduce new metrics for evaluating named person coreference that address these discrepancies. We present a simple rule-based named entity recognition driven system, which outperforms the current state-of-the-art systems on these task-specific metrics and performs on par with them on traditional coreference evaluations. Finally, we present similar evaluation for coreference resolution of other named entities and show that the rule-based approach is effective only for person named coreference, not other named entity types.
Tasks	Coreference Resolution, Named Entity Recognition
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11476v2
PDF	http://arxiv.org/pdf/1810.11476v2.pdf
PWC	https://paperswithcode.com/paper/named-person-coreference-in-english-news
Repo
Framework