July 27, 2019

3282 words 16 mins read

Paper Group ANR 549

BT-Nets: Simplifying Deep Neural Networks via Block Term Decomposition. Triaging Content Severity in Online Mental Health Forums. Predicting Native Language from Gaze. Sequence-based Multimodal Apprenticeship Learning For Robot Perception and Decision Making. Topic Compositional Neural Language Model. Modelling Preference Data with the Wallenius Di …

BT-Nets: Simplifying Deep Neural Networks via Block Term Decomposition


Title	BT-Nets: Simplifying Deep Neural Networks via Block Term Decomposition
Authors	Guangxi Li, Jinmian Ye, Haiqin Yang, Di Chen, Shuicheng Yan, Zenglin Xu
Abstract	Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification. Despite the success, the huge number of parameters blocks its deployment to situations with light computing resources. Researchers resort to the redundancy in the weights of DNNs and attempt to find how fewer parameters can be chosen while preserving the accuracy at the same time. Although several promising results have been shown along this research line, most existing methods either fail to significantly compress a well-trained deep network or require a heavy fine-tuning process for the compressed network to regain the original performance. In this paper, we propose the \textit{Block Term} networks (BT-nets) in which the commonly used fully-connected layers (FC-layers) are replaced with block term layers (BT-layers). In BT-layers, the inputs and the outputs are reshaped into two low-dimensional high-order tensors, then block-term decomposition is applied as tensor operators to connect them. We conduct extensive experiments on benchmark datasets to demonstrate that BT-layers can achieve a very large compression ratio on the number of parameters while preserving the representation power of the original FC-layers as much as possible. Specifically, we can get a higher performance while requiring fewer parameters compared with the tensor train method.
Tasks	Image Classification
Published	2017-12-15
URL	http://arxiv.org/abs/1712.05689v1
PDF	http://arxiv.org/pdf/1712.05689v1.pdf
PWC	https://paperswithcode.com/paper/bt-nets-simplifying-deep-neural-networks-via
Repo
Framework

Triaging Content Severity in Online Mental Health Forums


Title	Triaging Content Severity in Online Mental Health Forums
Authors	Arman Cohan, Sydney Young, Andrew Yates, Nazli Goharian
Abstract	Mental health forums are online communities where people express their issues and seek help from moderators and other users. In such forums, there are often posts with severe content indicating that the user is in acute distress and there is a risk of attempted self-harm. Moderators need to respond to these severe posts in a timely manner to prevent potential self-harm. However, the large volume of daily posted content makes it difficult for the moderators to locate and respond to these critical posts. We present a framework for triaging user content into four severity categories which are defined based on indications of self-harm ideation. Our models are based on a feature-rich classification framework which includes lexical, psycholinguistic, contextual and topic modeling features. Our approaches improve the state of the art in triaging the content severity in mental health forums by large margins (up to 17% improvement over the F-1 scores). Using the proposed model, we analyze the mental state of users and we show that overall, long-term users of the forum demonstrate a decreased severity of risk over time. Our analysis on the interaction of the moderators with the users further indicates that without an automatic way to identify critical content, it is indeed challenging for the moderators to provide timely response to the users in need.
Tasks
Published	2017-02-22
URL	http://arxiv.org/abs/1702.06875v1
PDF	http://arxiv.org/pdf/1702.06875v1.pdf
PWC	https://paperswithcode.com/paper/triaging-content-severity-in-online-mental
Repo
Framework

Predicting Native Language from Gaze


Title	Predicting Native Language from Gaze
Authors	Yevgeni Berzak, Chie Nakamura, Suzanne Flynn, Boris Katz
Abstract	A fundamental question in language learning concerns the role of a speaker’s first language in second language acquisition. We present a novel methodology for studying this question: analysis of eye-movement patterns in second language reading of free-form text. Using this methodology, we demonstrate for the first time that the native language of English learners can be predicted from their gaze fixations when reading English. We provide analysis of classifier uncertainty and learned features, which indicates that differences in English reading are likely to be rooted in linguistic divergences across native languages. The presented framework complements production studies and offers new ground for advancing research on multilingualism.
Tasks	Language Acquisition
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07398v2
PDF	http://arxiv.org/pdf/1704.07398v2.pdf
PWC	https://paperswithcode.com/paper/predicting-native-language-from-gaze
Repo
Framework

Sequence-based Multimodal Apprenticeship Learning For Robot Perception and Decision Making


Title	Sequence-based Multimodal Apprenticeship Learning For Robot Perception and Decision Making
Authors	Fei Han, Xue Yang, Yu Zhang, Hao Zhang
Abstract	Apprenticeship learning has recently attracted a wide attention due to its capability of allowing robots to learn physical tasks directly from demonstrations provided by human experts. Most previous techniques assumed that the state space is known a priori or employed simple state representations that usually suffer from perceptual aliasing. Different from previous research, we propose a novel approach named Sequence-based Multimodal Apprenticeship Learning (SMAL), which is capable to simultaneously fusing temporal information and multimodal data, and to integrate robot perception with decision making. To evaluate the SMAL approach, experiments are performed using both simulations and real-world robots in the challenging search and rescue scenarios. The empirical study has validated that our SMAL approach can effectively learn plans for robots to make decisions using sequence of multimodal observations. Experimental results have also showed that SMAL outperforms the baseline methods using individual images.
Tasks	Decision Making
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07475v1
PDF	http://arxiv.org/pdf/1702.07475v1.pdf
PWC	https://paperswithcode.com/paper/sequence-based-multimodal-apprenticeship
Repo
Framework

Topic Compositional Neural Language Model


Title	Topic Compositional Neural Language Model
Authors	Wenlin Wang, Zhe Gan, Wenqi Wang, Dinghan Shen, Jiaji Huang, Wei Ping, Sanjeev Satheesh, Lawrence Carin
Abstract	We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word ordering structure in a document. The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence. In order to train the MoE model efficiently, a matrix factorization method is applied, by extending each weight matrix of the RNN to be an ensemble of topic-dependent weight matrices. The degree to which each member of the ensemble is used is tied to the document-dependent probability of the corresponding topics. Experimental results on several corpora show that the proposed approach outperforms both a pure RNN-based model and other topic-guided language models. Further, our model yields sensible topics, and also has the capacity to generate meaningful sentences conditioned on given topics.
Tasks	Language Modelling
Published	2017-12-28
URL	http://arxiv.org/abs/1712.09783v3
PDF	http://arxiv.org/pdf/1712.09783v3.pdf
PWC	https://paperswithcode.com/paper/topic-compositional-neural-language-model
Repo
Framework

Modelling Preference Data with the Wallenius Distribution


Title	Modelling Preference Data with the Wallenius Distribution
Authors	Clara Grazian, Fabrizio Leisen, Brunero Liseo
Abstract	The Wallenius distribution is a generalisation of the Hypergeometric distribution where weights are assigned to balls of different colours. This naturally defines a model for ranking categories which can be used for classification purposes. Since, in general, the resulting likelihood is not analytically available, we adopt an approximate Bayesian computational (ABC) approach for estimating the importance of the categories. We illustrate the performance of the estimation procedure on simulated datasets. Finally, we use the new model for analysing two datasets about movies ratings and Italian academic statisticians’ journal preferences. The latter is a novel dataset collected by the authors.
Tasks
Published	2017-01-27
URL	http://arxiv.org/abs/1701.08142v5
PDF	http://arxiv.org/pdf/1701.08142v5.pdf
PWC	https://paperswithcode.com/paper/modelling-preference-data-with-the-wallenius
Repo
Framework

Fast Low-Rank Matrix Estimation without the Condition Number


Title	Fast Low-Rank Matrix Estimation without the Condition Number
Authors	Mohammadreza Soltani, Chinmay Hegde
Abstract	In this paper, we study the general problem of optimizing a convex function $F(L)$ over the set of $p \times p$ matrices, subject to rank constraints on $L$. However, existing first-order methods for solving such problems either are too slow to converge, or require multiple invocations of singular value decompositions. On the other hand, factorization-based non-convex algorithms, while being much faster, require stringent assumptions on the \emph{condition number} of the optimum. In this paper, we provide a novel algorithmic framework that achieves the best of both worlds: asymptotically as fast as factorization methods, while requiring no dependency on the condition number. We instantiate our general framework for three important matrix estimation problems that impact several practical applications; (i) a \emph{nonlinear} variant of affine rank minimization, (ii) logistic PCA, and (iii) precision matrix estimation in probabilistic graphical model learning. We then derive explicit bounds on the sample complexity as well as the running time of our approach, and show that it achieves the best possible bounds for both cases. We also provide an extensive range of experimental results, and demonstrate that our algorithm provides a very attractive tradeoff between estimation accuracy and running time.
Tasks
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03281v1
PDF	http://arxiv.org/pdf/1712.03281v1.pdf
PWC	https://paperswithcode.com/paper/fast-low-rank-matrix-estimation-without-the
Repo
Framework


Title	Machine Learning Based Detection of Clickbait Posts in Social Media
Authors	Xinyue Cao, Thai Le, Jason, Zhang
Abstract	Clickbait (headlines) make use of misleading titles that hide critical information from or exaggerate the content on the landing target pages to entice clicks. As clickbaits often use eye-catching wording to attract viewers, target contents are often of low quality. Clickbaits are especially widespread on social media such as Twitter, adversely impacting user experience by causing immense dissatisfaction. Hence, it has become increasingly important to put forward a widely applicable approach to identify and detect clickbaits. In this paper, we make use of a dataset from the clickbait challenge 2017 (clickbait-challenge.com) comprising of over 21,000 headlines/titles, each of which is annotated by at least five judgments from crowdsourcing on how clickbait it is. We attempt to build an effective computational clickbait detection model on this dataset. We first considered a total of 331 features, filtered out many features to avoid overfitting and improve the running time of learning, and eventually selected the 60 most important features for our final model. Using these features, Random Forest Regression achieved the following results: MSE=0.035 MSE, Accuracy=0.82, and F1-sore=0.61 on the clickbait class.
Tasks	Clickbait Detection
Published	2017-10-05
URL	http://arxiv.org/abs/1710.01977v1
PDF	http://arxiv.org/pdf/1710.01977v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-based-detection-of-clickbait
Repo
Framework

Revisiting knowledge transfer for training object class detectors


Title	Revisiting knowledge transfer for training object class detectors
Authors	Jasper Uijlings, Stefan Popov, Vittorio Ferrari
Abstract	We propose to revisit knowledge transfer for training object detectors on target classes from weakly supervised training images, helped by a set of source classes with bounding-box annotations. We present a unified knowledge transfer framework based on training a single neural network multi-class object detector over all source classes, organized in a semantic hierarchy. This generates proposals with scores at multiple levels in the hierarchy, which we use to explore knowledge transfer over a broad range of generality, ranging from class-specific (bicycle to motorbike) to class-generic (objectness to any class). Experiments on the 200 object classes in the ILSVRC 2013 detection dataset show that our technique: (1) leads to much better performance on the target classes (70.3% CorLoc, 36.9% mAP) than a weakly supervised baseline which uses manually engineered objectness [11] (50.5% CorLoc, 25.4% mAP). (2) delivers target object detectors reaching 80% of the mAP of their fully supervised counterparts. (3) outperforms the best reported transfer learning results on this dataset (+41% CorLoc and +3% mAP over [18, 46], +16.2% mAP over [32]). Moreover, we also carry out several across-dataset knowledge transfer experiments [27, 24, 35] and find that (4) our technique outperforms the weakly supervised baseline in all dataset pairs by 1.5x-1.9x, establishing its general applicability.
Tasks	Transfer Learning
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06128v3
PDF	http://arxiv.org/pdf/1708.06128v3.pdf
PWC	https://paperswithcode.com/paper/revisiting-knowledge-transfer-for-training
Repo
Framework

Identifying Clickbait: A Multi-Strategy Approach Using Neural Networks


Title	Identifying Clickbait: A Multi-Strategy Approach Using Neural Networks
Authors	Vaibhav Kumar, Dhruv Khattar, Siddhartha Gairola, Yash Kumar Lal, Vasudeva Varma
Abstract	Online media outlets, in a bid to expand their reach and subsequently increase revenue through ad monetisation, have begun adopting clickbait techniques to lure readers to click on articles. The article fails to fulfill the promise made by the headline. Traditional methods for clickbait detection have relied heavily on feature engineering which, in turn, is dependent on the dataset it is built for. The application of neural networks for this task has only been explored partially. We propose a novel approach considering all information found in a social media post. We train a bidirectional LSTM with an attention mechanism to learn the extent to which a word contributes to the post’s clickbait score in a differential manner. We also employ a Siamese net to capture the similarity between source and target information. Information gleaned from images has not been considered in previous approaches. We learn image embeddings from large amounts of data using Convolutional Neural Networks to add another layer of complexity to our model. Finally, we concatenate the outputs from the three separate components, serving it as input to a fully connected layer. We conduct experiments over a test corpus of 19538 social media posts, attaining an F1 score of 65.37% on the dataset bettering the previous state-of-the-art, as well as other proposed approaches, feature engineering or otherwise.
Tasks	Clickbait Detection, Feature Engineering
Published	2017-10-04
URL	http://arxiv.org/abs/1710.01507v4
PDF	http://arxiv.org/pdf/1710.01507v4.pdf
PWC	https://paperswithcode.com/paper/identifying-clickbait-a-multi-strategy
Repo
Framework

Metaheuristic Design of Feedforward Neural Networks: A Review of Two Decades of Research


Title	Metaheuristic Design of Feedforward Neural Networks: A Review of Two Decades of Research
Authors	Varun Kumar Ojha, Ajith Abraham, Václav Snášel
Abstract	Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN’s generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN’s application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.
Tasks
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05584v1
PDF	http://arxiv.org/pdf/1705.05584v1.pdf
PWC	https://paperswithcode.com/paper/metaheuristic-design-of-feedforward-neural
Repo
Framework

Remote Sensing Image Fusion Based on Two-stream Fusion Network


Title	Remote Sensing Image Fusion Based on Two-stream Fusion Network
Authors	Xiangyu Liu, Qingjie Liu, Yunhong Wang
Abstract	Remote sensing image fusion (also known as pan-sharpening) aims at generating high resolution multi-spectral (MS) image from inputs of a high spatial resolution single band panchromatic (PAN) image and a low spatial resolution multi-spectral image. Inspired by the astounding achievements of convolutional neural networks (CNNs) in a variety of computer vision tasks, in this paper, we propose a two-stream fusion network (TFNet) to address the problem of pan-sharpening. Unlike previous CNN based methods that consider pan-sharpening as a super resolution problem and perform pan-sharpening in pixel level, the proposed TFNet aims to fuse PAN and MS images in feature level and reconstruct the pan-sharpened image from the fused features. The TFNet mainly consists of three parts. The first part is comprised of two networks extracting features from PAN and MS images, respectively. The subsequent network fuses them together to form compact features that represent both spatial and spectral information of PAN and MS images, simultaneously. Finally, the desired high spatial resolution MS image is recovered from the fused features through an image reconstruction network. Experiments on Quickbird and \mbox{GaoFen-1} satellite images demonstrate that the proposed TFNet can fuse PAN and MS images, effectively, and produce pan-sharpened images competitive with even superior to state of the arts.
Tasks	Image Reconstruction, Super-Resolution
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02549v3
PDF	http://arxiv.org/pdf/1711.02549v3.pdf
PWC	https://paperswithcode.com/paper/remote-sensing-image-fusion-based-on-two
Repo
Framework

Cell Segmentation in 3D Confocal Images using Supervoxel Merge-Forests with CNN-based Hypothesis Selection


Title	Cell Segmentation in 3D Confocal Images using Supervoxel Merge-Forests with CNN-based Hypothesis Selection
Authors	Johannes Stegmaier, Thiago V. Spina, Alexandre X. Falcão, Andreas Bartschat, Ralf Mikut, Elliot Meyerowitz, Alexandre Cunha
Abstract	Automated segmentation approaches are crucial to quantitatively analyze large-scale 3D microscopy images. Particularly in deep tissue regions, automatic methods still fail to provide error-free segmentations. To improve the segmentation quality throughout imaged samples, we present a new supervoxel-based 3D segmentation approach that outperforms current methods and reduces the manual correction effort. The algorithm consists of gentle preprocessing and a conservative super-voxel generation method followed by supervoxel agglomeration based on local signal properties and a postprocessing step to fix under-segmentation errors using a Convolutional Neural Network. We validate the functionality of the algorithm on manually labeled 3D confocal images of the plant Arabidopis thaliana and compare the results to a state-of-the-art meristem segmentation algorithm.
Tasks	Cell Segmentation
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06608v1
PDF	http://arxiv.org/pdf/1710.06608v1.pdf
PWC	https://paperswithcode.com/paper/cell-segmentation-in-3d-confocal-images-using
Repo
Framework

Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classification


Title	Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classification
Authors	Rushil Anirudh, Jayaraman J. Thiagarajan
Abstract	Using predictive models to identify patterns that can act as biomarkers for different neuropathoglogical conditions is becoming highly prevalent. In this paper, we consider the problem of Autism Spectrum Disorder (ASD) classification where previous work has shown that it can be beneficial to incorporate a wide variety of meta features, such as socio-cultural traits, into predictive modeling. A graph-based approach naturally suits these scenarios, where a contextual graph captures traits that characterize a population, while the specific brain activity patterns are utilized as a multivariate signal at the nodes. Graph neural networks have shown improvements in inferencing with graph-structured data. Though the underlying graph strongly dictates the overall performance, there exists no systematic way of choosing an appropriate graph in practice, thus making predictive models non-robust. To address this, we propose a bootstrapped version of graph convolutional neural networks (G-CNNs) that utilizes an ensemble of weakly trained G-CNNs, and reduce the sensitivity of models on the choice of graph construction. We demonstrate its effectiveness on the challenging Autism Brain Imaging Data Exchange (ABIDE) dataset and show that our approach improves upon recently proposed graph-based neural networks. We also show that our method remains more robust to noisy graphs.
Tasks	graph construction
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07487v2
PDF	http://arxiv.org/pdf/1704.07487v2.pdf
PWC	https://paperswithcode.com/paper/bootstrapping-graph-convolutional-neural
Repo
Framework

Scalable Nearest Neighbor Search based on kNN Graph


Title	Scalable Nearest Neighbor Search based on kNN Graph
Authors	Wan-Lei Zhao, Jie Yang, Cheng-Hao Deng
Abstract	Nearest neighbor search is known as a challenging issue that has been studied for several decades. Recently, this issue becomes more and more imminent in viewing that the big data problem arises from various fields. In this paper, a scalable solution based on hill-climbing strategy with the support of k-nearest neighbor graph (kNN) is presented. Two major issues have been considered in the paper. Firstly, an efficient kNN graph construction method based on two means tree is presented. For the nearest neighbor search, an enhanced hill-climbing procedure is proposed, which sees considerable performance boost over original procedure. Furthermore, with the support of inverted indexing derived from residue vector quantization, our method achieves close to 100% recall with high speed efficiency in two state-of-the-art evaluation benchmarks. In addition, a comparative study on both the compressional and traditional nearest neighbor search methods is presented. We show that our method achieves the best trade-off between search quality, efficiency and memory complexity.
Tasks	graph construction, Quantization
Published	2017-01-30
URL	http://arxiv.org/abs/1701.08475v2
PDF	http://arxiv.org/pdf/1701.08475v2.pdf
PWC	https://paperswithcode.com/paper/scalable-nearest-neighbor-search-based-on-knn
Repo
Framework