October 20, 2019

3062 words 15 mins read

Paper Group AWR 272

Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson’s Disease. Speech waveform synthesis from MFCC sequences with generative adversarial networks. MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization. Hypothesis Only Baselines in Natural Language Inference. Relative Pairwise …

Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson’s Disease


Title	Multi-View Graph Convolutional Network and Its Applications on Neuroimage Analysis for Parkinson’s Disease
Authors	Xi Sheryl Zhang, Lifang He, Kun Chen, Yuan Luo, Jiayu Zhou, Fei Wang
Abstract	Parkinson’s Disease (PD) is one of the most prevalent neurodegenerative diseases that affects tens of millions of Americans. PD is highly progressive and heterogeneous. Quite a few studies have been conducted in recent years on predictive or disease progression modeling of PD using clinical and biomarkers data. Neuroimaging, as another important information source for neurodegenerative disease, has also arisen considerable interests from the PD community. In this paper, we propose a deep learning method based on Graph Convolutional Networks (GCN) for fusing multiple modalities of brain images in relationship prediction which is useful for distinguishing PD cases from controls. On Parkinson’s Progression Markers Initiative (PPMI) cohort, our approach achieved $0.9537\pm 0.0587$ AUC, compared with $0.6443\pm 0.0223$ AUC achieved by traditional approaches such as PCA.
Tasks
Published	2018-05-22
URL	https://arxiv.org/abs/1805.08801v4
PDF	https://arxiv.org/pdf/1805.08801v4.pdf
PWC	https://paperswithcode.com/paper/multi-view-graph-convolutional-network-and
Repo	https://github.com/sheryl-ai/MVGCN
Framework	tf

Speech waveform synthesis from MFCC sequences with generative adversarial networks


Title	Speech waveform synthesis from MFCC sequences with generative adversarial networks
Authors	Lauri Juvela, Bajibabu Bollepalli, Xin Wang, Hirokazu Kameoka, Manu Airaksinen, Junichi Yamagishi, Paavo Alku
Abstract	This paper proposes a method for generating speech from filterbank mel frequency cepstral coefficients (MFCC), which are widely used in speech applications, such as ASR, but are generally considered unusable for speech synthesis. First, we predict fundamental frequency and voicing information from MFCCs with an autoregressive recurrent neural net. Second, the spectral envelope information contained in MFCCs is converted to all-pole filters, and a pitch-synchronous excitation model matched to these filters is trained. Finally, we introduce a generative adversarial network -based noise model to add a realistic high-frequency stochastic component to the modeled excitation signal. The results show that high quality speech reconstruction can be obtained, given only MFCC information at test time.
Tasks	Speech Synthesis
Published	2018-04-03
URL	http://arxiv.org/abs/1804.00920v1
PDF	http://arxiv.org/pdf/1804.00920v1.pdf
PWC	https://paperswithcode.com/paper/speech-waveform-synthesis-from-mfcc-sequences
Repo	https://github.com/ljuvela/ResGAN
Framework	tf

MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization


Title	MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization
Authors	Eric Chu, Peter J. Liu
Abstract	Abstractive summarization has been studied using neural sequence transduction methods with datasets of large, paired document-summary examples. However, such datasets are rare and the models trained from them do not generalize to other domains. Recently, some progress has been made in learning sequence-to-sequence mappings with only unpaired examples. In our work, we consider the setting where there are only documents (product or business reviews) with no summaries provided, and propose an end-to-end, neural model architecture to perform unsupervised abstractive summarization. Our proposed model consists of an auto-encoder where the mean of the representations of the input reviews decodes to a reasonable summary-review while not relying on any review-specific features. We consider variants of the proposed architecture and perform an ablation study to show the importance of specific components. We show through automated metrics and human evaluation that the generated summaries are highly abstractive, fluent, relevant, and representative of the average sentiment of the input reviews. Finally, we collect a reference evaluation dataset and show that our model outperforms a strong extractive baseline.
Tasks	Abstractive Text Summarization
Published	2018-10-12
URL	https://arxiv.org/abs/1810.05739v4
PDF	https://arxiv.org/pdf/1810.05739v4.pdf
PWC	https://paperswithcode.com/paper/meansum-a-neural-model-for-unsupervised-multi
Repo	https://github.com/sosuperic/MeanSum
Framework	pytorch

Hypothesis Only Baselines in Natural Language Inference


Title	Hypothesis Only Baselines in Natural Language Inference
Authors	Adam Poliak, Jason Naradowsky, Aparajita Haldar, Rachel Rudinger, Benjamin Van Durme
Abstract	We propose a hypothesis only baseline for diagnosing Natural Language Inference (NLI). Especially when an NLI dataset assumes inference is occurring based purely on the relationship between a context and a hypothesis, it follows that assessing entailment relations while ignoring the provided context is a degenerate solution. Yet, through experiments on ten distinct NLI datasets, we find that this approach, which we refer to as a hypothesis-only model, is able to significantly outperform a majority class baseline across a number of NLI datasets. Our analysis suggests that statistical irregularities may allow a model to perform NLI in some datasets beyond what should be achievable without access to the context.
Tasks	Natural Language Inference
Published	2018-05-02
URL	http://arxiv.org/abs/1805.01042v1
PDF	http://arxiv.org/pdf/1805.01042v1.pdf
PWC	https://paperswithcode.com/paper/hypothesis-only-baselines-in-natural-language
Repo	https://github.com/azpoliak/hypothesis-only-NLI
Framework	pytorch

Relative Pairwise Relationship Constrained Non-negative Matrix Factorisation


Title	Relative Pairwise Relationship Constrained Non-negative Matrix Factorisation
Authors	Shuai Jiang, Kan Li, Richard Yida Xu
Abstract	Non-negative Matrix Factorisation (NMF) has been extensively used in machine learning and data analytics applications. Most existing variations of NMF only consider how each row/column vector of factorised matrices should be shaped, and ignore the relationship among pairwise rows or columns. In many cases, such pairwise relationship enables better factorisation, for example, image clustering and recommender systems. In this paper, we propose an algorithm named, Relative Pairwise Relationship constrained Non-negative Matrix Factorisation (RPR-NMF), which places constraints over relative pairwise distances amongst features by imposing penalties in a triplet form. Two distance measures, squared Euclidean distance and Symmetric divergence, are used, and exponential and hinge loss penalties are adopted for the two measures respectively. It is well known that the so-called “multiplicative update rules” result in a much faster convergence than gradient descend for matrix factorisation. However, applying such update rules to RPR-NMF and also proving its convergence is not straightforward. Thus, we use reasonable approximations to relax the complexity brought by the penalties, which are practically verified. Experiments on both synthetic datasets and real datasets demonstrate that our algorithms have advantages on gaining close approximation, satisfying a high proportion of expected constraints, and achieving superior performance compared with other algorithms.
Tasks	Image Clustering, Recommendation Systems
Published	2018-03-05
URL	http://arxiv.org/abs/1803.02218v1
PDF	http://arxiv.org/pdf/1803.02218v1.pdf
PWC	https://paperswithcode.com/paper/relative-pairwise-relationship-constrained
Repo	https://github.com/shawn-jiang/RPRNMF
Framework	none

Challenges in the Automatic Analysis of Students’ Diagnostic Reasoning


Title	Challenges in the Automatic Analysis of Students’ Diagnostic Reasoning
Authors	Claudia Schulz, Christian M. Meyer, Michael Sailer, Jan Kiesewetter, Elisabeth Bauer, Frank Fischer, Martin R. Fischer, Iryna Gurevych
Abstract	Diagnostic reasoning is a key component of many professions. To improve students’ diagnostic reasoning skills, educational psychologists analyse and give feedback on epistemic activities used by these students while diagnosing, in particular, hypothesis generation, evidence generation, evidence evaluation, and drawing conclusions. However, this manual analysis is highly time-consuming. We aim to enable the large-scale adoption of diagnostic reasoning analysis and feedback by automating the epistemic activity identification. We create the first corpus for this task, comprising diagnostic reasoning self-explanations of students from two domains annotated with epistemic activities. Based on insights from the corpus creation and the task’s characteristics, we discuss three challenges for the automatic identification of epistemic activities using AI methods: the correct identification of epistemic activity spans, the reliable distinction of similar epistemic activities, and the detection of overlapping epistemic activities. We propose a separate performance metric for each challenge and thus provide an evaluation framework for future research. Indeed, our evaluation of various state-of-the-art recurrent neural network architectures reveals that current techniques fail to address some of these challenges.
Tasks
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10550v1
PDF	http://arxiv.org/pdf/1811.10550v1.pdf
PWC	https://paperswithcode.com/paper/challenges-in-the-automatic-analysis-of
Repo	https://github.com/UKPLab/aaai19-diagnostic-reasoning
Framework	none

Joint Voxel and Coordinate Regression for Accurate 3D Facial Landmark Localization


Title	Joint Voxel and Coordinate Regression for Accurate 3D Facial Landmark Localization
Authors	Hongwen Zhang, Qi Li, Zhenan Sun
Abstract	3D face shape is more expressive and viewpoint-consistent than its 2D counterpart. However, 3D facial landmark localization in a single image is challenging due to the ambiguous nature of landmarks under 3D perspective. Existing approaches typically adopt a suboptimal two-step strategy, performing 2D landmark localization followed by depth estimation. In this paper, we propose the Joint Voxel and Coordinate Regression (JVCR) method for 3D facial landmark localization, addressing it more effectively in an end-to-end fashion. First, a compact volumetric representation is proposed to encode the per-voxel likelihood of positions being the 3D landmarks. The dimensionality of such a representation is fixed regardless of the number of target landmarks, so that the curse of dimensionality could be avoided. Then, a stacked hourglass network is adopted to estimate the volumetric representation from coarse to fine, followed by a 3D convolution network that takes the estimated volume as input and regresses 3D coordinates of the face shape. In this way, the 3D structural constraints between landmarks could be learned by the neural network in a more efficient manner. Moreover, the proposed pipeline enables end-to-end training and improves the robustness and accuracy of 3D facial landmark localization. The effectiveness of our approach is validated on the 3DFAW and AFLW2000-3D datasets. Experimental results show that the proposed method achieves state-of-the-art performance in comparison with existing methods.
Tasks	Depth Estimation, Face Alignment
Published	2018-01-28
URL	http://arxiv.org/abs/1801.09242v1
PDF	http://arxiv.org/pdf/1801.09242v1.pdf
PWC	https://paperswithcode.com/paper/joint-voxel-and-coordinate-regression-for
Repo	https://github.com/HongwenZhang/JVCR-3Dlandmark
Framework	pytorch

Overcoming catastrophic forgetting with hard attention to the task


Title	Overcoming catastrophic forgetting with hard attention to the task
Authors	Joan Serrà, Dídac Surís, Marius Miron, Alexandros Karatzoglou
Abstract	Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks’ information without affecting the current task’s learning. A hard attention mask is learned concurrently to every task, through stochastic gradient descent, and previous masks are exploited to condition such learning. We show that the proposed mechanism is effective for reducing catastrophic forgetting, cutting current rates by 45 to 80%. We also show that it is robust to different hyperparameter choices, and that it offers a number of monitoring capabilities. The approach features the possibility to control both the stability and compactness of the learned knowledge, which we believe makes it also attractive for online learning or network compression applications.
Tasks
Published	2018-01-04
URL	http://arxiv.org/abs/1801.01423v3
PDF	http://arxiv.org/pdf/1801.01423v3.pdf
PWC	https://paperswithcode.com/paper/overcoming-catastrophic-forgetting-with-hard
Repo	https://github.com/joansj/hat
Framework	pytorch

Robust Estimation and Generative Adversarial Nets


Title	Robust Estimation and Generative Adversarial Nets
Authors	Chao Gao, Jiyi Liu, Yuan Yao, Weizhi Zhu
Abstract	Robust estimation under Huber’s $\epsilon$-contamination model has become an important topic in statistics and theoretical computer science. Statistically optimal procedures such as Tukey’s median and other estimators based on depth functions are impractical because of their computational intractability. In this paper, we establish an intriguing connection between $f$-GANs and various depth functions through the lens of $f$-Learning. Similar to the derivation of $f$-GANs, we show that these depth functions that lead to statistically optimal robust estimators can all be viewed as variational lower bounds of the total variation distance in the framework of $f$-Learning. This connection opens the door of computing robust estimators using tools developed for training GANs. In particular, we show in both theory and experiments that some appropriate structures of discriminator networks with hidden layers in GANs lead to statistically optimal robust location estimators for both Gaussian distribution and general elliptical distributions where first moment may not exist.
Tasks
Published	2018-10-04
URL	http://arxiv.org/abs/1810.02030v3
PDF	http://arxiv.org/pdf/1810.02030v3.pdf
PWC	https://paperswithcode.com/paper/robust-estimation-and-generative-adversarial
Repo	https://github.com/zhuwzh/Robust-GAN-Center
Framework	pytorch

Applicability and interpretation of the deterministic weighted cepstral distance


Title	Applicability and interpretation of the deterministic weighted cepstral distance
Authors	Oliver Lauwers, Bart De Moor
Abstract	Quantifying similarity between data objects is an important part of modern data science. Deciding what similarity measure to use is very application dependent. In this paper, we combine insights from systems theory and machine learning, and investigate the weighted cepstral distance, which was previously defined for signals coming from ARMA models. We provide an extension of this distance to invertible deterministic linear time invariant single input single output models, and assess its applicability. We show that it can always be interpreted in terms of the poles and zeros of the underlying model, and that, in the case of stable, minimum-phase, or unstable, maximum-phase models, a geometrical interpretation in terms of subspace angles can be given. We then devise a method to assess stability and phase-type of the generating models, using only input/output signal information. In this way, we prove a connection between the extended weighted cepstral distance and a weighted cepstral model norm. In this way, we provide a purely data-driven way to assess different underlying dynamics of input/output signal pairs, without the need for any system identification step. This can be useful in machine learning tasks such as time series clustering. An iPython tutorial is published complementary to this paper, containing implementations of the various methods and algorithms presented here, as well as some numerical illustrations of the equivalences proven here.
Tasks	Time Series, Time Series Clustering
Published	2018-03-08
URL	http://arxiv.org/abs/1803.03104v1
PDF	http://arxiv.org/pdf/1803.03104v1.pdf
PWC	https://paperswithcode.com/paper/applicability-and-interpretation-of-the
Repo	https://github.com/Olauwers/Applicability-and-interpretation-of-the-deterministic-weighted-cepstral-distance
Framework	none

Stroke-based Character Reconstruction


Title	Stroke-based Character Reconstruction
Authors	Zhewei Huang, Wen Heng, Yuanzheng Tao, Shuchang Zhou
Abstract	Background elimination for noisy character images or character images from real scene is still a challenging problem, due to the bewildering backgrounds, uneven illumination, low resolution and different distortions. We propose a stroke-based character reconstruction(SCR) method that use a weighted quadratic Bezier curve(WQBC) to represent strokes of a character. Only training on our synthetic data, our stroke extractor can achieve excellent reconstruction effect in real scenes. Meanwhile. It can also help achieve great ability in defending adversarial attacks of character recognizers.
Tasks
Published	2018-06-23
URL	http://arxiv.org/abs/1806.08990v3
PDF	http://arxiv.org/pdf/1806.08990v3.pdf
PWC	https://paperswithcode.com/paper/stroke-based-character-reconstruction
Repo	https://github.com/hzwer/Stroke-basedCharacterReconstruction
Framework	pytorch

Object Detection in Equirectangular Panorama


Title	Object Detection in Equirectangular Panorama
Authors	Wenyan Yang, Yanlin Qian, Francesco Cricri, Lixin Fan, Joni-Kristian Kamarainen
Abstract	We introduced a high-resolution equirectangular panorama (360-degree, virtual reality) dataset for object detection and propose a multi-projection variant of YOLO detector. The main challenge with equirectangular panorama image are i) the lack of annotated training data, ii) high-resolution imagery and iii) severe geometric distortions of objects near the panorama projection poles. In this work, we solve the challenges by i) using training examples available in the “conventional datasets” (ImageNet and COCO), ii) employing only low-resolution images that require only moderate GPU computing power and memory, and iii) our multi-projection YOLO handles projection distortions by making multiple stereographic sub-projections. In our experiments, YOLO outperforms the other state-of-art detector, Faster RCNN and our multi-projection YOLO achieves the best accuracy with low-resolution input.
Tasks	Object Detection
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08009v1
PDF	http://arxiv.org/pdf/1805.08009v1.pdf
PWC	https://paperswithcode.com/paper/object-detection-in-equirectangular-panorama
Repo	https://github.com/keevin60907/mp-YOLO
Framework	none

A hybrid machine-learning algorithm for designing quantum experiments


Title	A hybrid machine-learning algorithm for designing quantum experiments
Authors	L. O’Driscoll, R. Nichols, P. A. Knott
Abstract	We introduce a hybrid machine-learning algorithm for designing quantum optics experiments that produce specific quantum states. Our algorithm successfully found experimental schemes to produce all 5 states we asked it to, including Schr"odinger cat states and cubic phase states, all to a fidelity of over $96%$. Here we specifically focus on designing realistic experiments, and hence all of the algorithm’s designs only contain experimental elements that are available with current technology. The core of our algorithm is a genetic algorithm that searches for optimal arrangements of the experimental elements, but to speed up the initial search we incorporate a neural network that classifies quantum states. The latter is of independent interest, as it quickly learned to accurately classify quantum states given their photon-number distributions.
Tasks
Published	2018-12-07
URL	http://arxiv.org/abs/1812.03183v2
PDF	http://arxiv.org/pdf/1812.03183v2.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-machine-learning-algorithm-for
Repo	https://github.com/lewis-od/Quantum-Optics
Framework	tf

Fast Super-Paramagnetic Clustering


Title	Fast Super-Paramagnetic Clustering
Authors	Lionel Yelibi, Tim Gebbie
Abstract	We map stock market interactions to spin models to recover their hierarchical structure using a simulated annealing based Super-Paramagnetic Clustering (SPC) algorithm. This is directly compared to a modified implementation of a maximum likelihood approach we call Fast Super-Paramagnetic Clustering (f-SPC). The methods are first applied standard toy test-case problems, and then to a data-set of 447 stocks traded on the New York Stock Exchange (NYSE) over 1249 days. The signal to noise ratio of stock market correlation matrices is briefly considered. Our result recover approximately clusters representative of standard economic sectors and mixed ones whose dynamics shine light on the adaptive nature of financial markets and raise concerns relating to the effectiveness of industry based static financial market classification in the world of real-time data analytics. A key result is that we show that f-SPC maximum likelihood solutions converge to ones found within the Super-Paramagnetic Phase where the entropy is maximum, and those solutions are qualitatively better for high dimensionality data-sets.
Tasks
Published	2018-10-05
URL	https://arxiv.org/abs/1810.02529v2
PDF	https://arxiv.org/pdf/1810.02529v2.pdf
PWC	https://paperswithcode.com/paper/an-introduction-to-fast-super-paramagnetic
Repo	https://github.com/tehraio/potts-model-clustering
Framework	none

Model Cards for Model Reporting


Title	Model Cards for Model Reporting
Authors	Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, Timnit Gebru
Abstract	Trained machine learning models are increasingly used to perform high-impact tasks in areas such as law enforcement, medicine, education, and employment. In order to clarify the intended use cases of machine learning models and minimize their usage in contexts for which they are not well suited, we recommend that released models be accompanied by documentation detailing their performance characteristics. In this paper, we propose a framework that we call model cards, to encourage such transparent model reporting. Model cards are short documents accompanying trained machine learning models that provide benchmarked evaluation in a variety of conditions, such as across different cultural, demographic, or phenotypic groups (e.g., race, geographic location, sex, Fitzpatrick skin type) and intersectional groups (e.g., age and race, or sex and Fitzpatrick skin type) that are relevant to the intended application domains. Model cards also disclose the context in which models are intended to be used, details of the performance evaluation procedures, and other relevant information. While we focus primarily on human-centered machine learning models in the application fields of computer vision and natural language processing, this framework can be used to document any trained machine learning model. To solidify the concept, we provide cards for two supervised models: One trained to detect smiling faces in images, and one trained to detect toxic comments in text. We propose model cards as a step towards the responsible democratization of machine learning and related AI technology, increasing transparency into how well AI technology works. We hope this work encourages those releasing trained machine learning models to accompany model releases with similar detailed evaluation numbers and other relevant documentation.
Tasks
Published	2018-10-05
URL	http://arxiv.org/abs/1810.03993v2
PDF	http://arxiv.org/pdf/1810.03993v2.pdf
PWC	https://paperswithcode.com/paper/model-cards-for-model-reporting
Repo	https://github.com/SachaIZADI/Misc-Machine-Learning
Framework	tf