October 17, 2019

3118 words 15 mins read

Paper Group ANR 907

Multi Instance Learning For Unbalanced Data. Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline. Whole Brain Susceptibility Mapping Using Harmonic Incompatibility Removal. Graph Convolutional Neural Networks based on Quantum Vertex Saliency. Rethinking clinical prediction: Wh …

Multi Instance Learning For Unbalanced Data


Title	Multi Instance Learning For Unbalanced Data
Authors	Mark Kozdoba, Edward Moroshko, Lior Shani, Takuya Takagi, Takashi Katoh, Shie Mannor, Koby Crammer
Abstract	In the context of Multi Instance Learning, we analyze the Single Instance (SI) learning objective. We show that when the data is unbalanced and the family of classifiers is sufficiently rich, the SI method is a useful learning algorithm. In particular, we show that larger data imbalance, a quality that is typically perceived as negative, in fact implies a better resilience of the algorithm to the statistical dependencies of the objects in bags. In addition, our results shed new light on some known issues with the SI method in the setting of linear classifiers, and we show that these issues are significantly less likely to occur in the setting of neural networks. We demonstrate our results on a synthetic dataset, and on the COCO dataset for the problem of patch classification with weak image level labels derived from captions.
Tasks
Published	2018-12-17
URL	http://arxiv.org/abs/1812.07010v1
PDF	http://arxiv.org/pdf/1812.07010v1.pdf
PWC	https://paperswithcode.com/paper/multi-instance-learning-for-unbalanced-data
Repo
Framework

Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline


Title	Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline
Authors	Szu-Jui Chen, Aswin Shanmugam Subramanian, Hainan Xu, Shinji Watanabe
Abstract	This paper describes a new baseline system for automatic speech recognition (ASR) in the CHiME-4 challenge to promote the development of noisy ASR in speech processing communities by providing 1) state-of-the-art system with a simplified single system comparable to the complicated top systems in the challenge, 2) publicly available and reproducible recipe through the main repository in the Kaldi speech recognition toolkit. The proposed system adopts generalized eigenvalue beamforming with bidirectional long short-term memory (LSTM) mask estimation. We also propose to use a time delay neural network (TDNN) based on the lattice-free version of the maximum mutual information (LF-MMI) trained with augmented all six microphones plus the enhanced data after beamforming. Finally, we use a LSTM language model for lattice and n-best re-scoring. The final system achieved 2.74% WER for the real test set in the 6-channel track, which corresponds to the 2nd place in the challenge. In addition, the proposed baseline recipe includes four different speech enhancement measures, short-time objective intelligibility measure (STOI), extended STOI (eSTOI), perceptual evaluation of speech quality (PESQ) and speech distortion ratio (SDR) for the simulation test set. Thus, the recipe also provides an experimental platform for speech enhancement studies with these performance measures.
Tasks	Distant Speech Recognition, Language Modelling, Noisy Speech Recognition, Speech Enhancement, Speech Recognition
Published	2018-03-27
URL	http://arxiv.org/abs/1803.10109v1
PDF	http://arxiv.org/pdf/1803.10109v1.pdf
PWC	https://paperswithcode.com/paper/building-state-of-the-art-distant-speech
Repo
Framework

Whole Brain Susceptibility Mapping Using Harmonic Incompatibility Removal


Title	Whole Brain Susceptibility Mapping Using Harmonic Incompatibility Removal
Authors	Chenglong Bao, Jae Kyu Choi, Bin Dong
Abstract	Quantitative susceptibility mapping (QSM) aims to visualize the three dimensional susceptibility distribution by solving the field-to-source inverse problem using the phase data in magnetic resonance signal. However, the inverse problem is ill-posed since the Fourier transform of integral kernel has zeroes in the frequency domain. Although numerous regularization based models have been proposed to overcome this problem, the incompatibility in the field data has not received enough attention, which leads to deterioration of the recovery. In this paper, we show that the data acquisition process of QSM inherently generates a harmonic incompatibility in the measured local field. Based on such discovery, we propose a novel regularization based susceptibility reconstruction model with an additional sparsity based regularization term on the harmonic incompatibility. Numerical experiments show that the proposed method achieves better performance than the existing approaches.
Tasks
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12521v2
PDF	http://arxiv.org/pdf/1805.12521v2.pdf
PWC	https://paperswithcode.com/paper/whole-brain-susceptibility-mapping-using
Repo
Framework

Graph Convolutional Neural Networks based on Quantum Vertex Saliency


Title	Graph Convolutional Neural Networks based on Quantum Vertex Saliency
Authors	Lu Bai, Yuhang Jiao, Luca Rossi, Lixin Cui, Jian Cheng, Edwin R. Hancock
Abstract	This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs, and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. In order to learn representative graph characteristics, a new quantum spatial graph convolution is proposed and employed to extract multi-scale vertex features, in terms of quantum information propagation between grid vertices of each graph. Since the quantum spatial convolution preserves the grid structures of the input vertices (i.e., the convolution layer does not change the original spatial sequence of vertices), the proposed QSGCNN model allows to directly employ the traditional convolutional neural network architecture to further learn from the global graph topology, providing an end-to-end deep learning architecture that integrates the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications. We demonstrate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. The proposed QSGCNN model addresses the shortcomings of information loss and imprecise information representation arising in existing GCN models associated with the use of SortPooling or SumPooling layers. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model.
Tasks	Graph Classification
Published	2018-09-04
URL	http://arxiv.org/abs/1809.01090v2
PDF	http://arxiv.org/pdf/1809.01090v2.pdf
PWC	https://paperswithcode.com/paper/graph-convolutional-neural-networks-based-on
Repo
Framework

Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation


Title	Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation
Authors	Bret Nestor, Matthew B. A. McDermott, Geeticka Chauhan, Tristan Naumann, Michael C. Hughes, Anna Goldenberg, Marzyeh Ghassemi
Abstract	Machine learning for healthcare often trains models on de-identified datasets with randomly-shifted calendar dates, ignoring the fact that data were generated under hospital operation practices that change over time. These changing practices induce definitive changes in observed data which confound evaluations which do not account for dates and limit the generalisability of date-agnostic models. In this work, we establish the magnitude of this problem on MIMIC, a public hospital dataset, and showcase a simple solution. We augment MIMIC with the year in which care was provided and show that a model trained using standard feature representations will significantly degrade in quality over time. We find a deterioration of 0.3 AUC when evaluating mortality prediction on data from 10 years later. We find a similar deterioration of 0.15 AUC for length-of-stay. In contrast, we demonstrate that clinically-oriented aggregates of raw features significantly mitigate future deterioration. Our suggested aggregated representations, when retrained yearly, have prediction quality comparable to year-agnostic models.
Tasks	Mortality Prediction
Published	2018-11-30
URL	http://arxiv.org/abs/1811.12583v1
PDF	http://arxiv.org/pdf/1811.12583v1.pdf
PWC	https://paperswithcode.com/paper/rethinking-clinical-prediction-why-machine
Repo
Framework

Deep learning for affective computing: text-based emotion recognition in decision support


Title	Deep learning for affective computing: text-based emotion recognition in decision support
Authors	Bernhard Kratzwald, Suzana Ilic, Mathias Kraus, Stefan Feuerriegel, Helmut Prendinger
Abstract	Emotions widely affect human decision-making. This fact is taken into account by affective computing with the goal of tailoring decision support to the emotional states of individuals. However, the accurate recognition of emotions within narrative documents presents a challenging undertaking due to the complexity and ambiguity of language. Performance improvements can be achieved through deep learning; yet, as demonstrated in this paper, the specific nature of this task requires the customization of recurrent neural networks with regard to bidirectional processing, dropout layers as a means of regularization, and weighted loss functions. In addition, we propose sent2affect, a tailored form of transfer learning for affective computing: here the network is pre-trained for a different task (i.e. sentiment analysis), while the output layer is subsequently tuned to the task of emotion recognition. The resulting performance is evaluated in a holistic setting across 6 benchmark datasets, where we find that both recurrent neural networks and transfer learning consistently outperform traditional machine learning. Altogether, the findings have considerable implications for the use of affective computing.
Tasks	Decision Making, Emotion Recognition, Sentiment Analysis, Transfer Learning
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06397v6
PDF	http://arxiv.org/pdf/1803.06397v6.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-affective-computing-text
Repo
Framework

Deep Ensemble Tensor Factorization for Longitudinal Patient Trajectories Classification


Title	Deep Ensemble Tensor Factorization for Longitudinal Patient Trajectories Classification
Authors	Edward De Brouwer, Jaak Simm, Adam Arany, Yves Moreau
Abstract	We present a generative approach to classify scarcely observed longitudinal patient trajectories. The available time series are represented as tensors and factorized using generative deep recurrent neural networks. The learned factors represent the patient data in a compact way and can then be used in a downstream classification task. For more robustness and accuracy in the predictions, we used an ensemble of those deep generative models to mimic Bayesian posterior sampling. We illustrate the performance of our architecture on an intensive-care case study of in-hospital mortality prediction with 96 longitudinal measurement types measured across the first 48-hour from admission. Our combination of generative and ensemble strategies achieves an AUC of over 0.85, and outperforms the SAPS-II mortality score and GRU baselines.
Tasks	Mortality Prediction, Time Series
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10501v2
PDF	http://arxiv.org/pdf/1811.10501v2.pdf
PWC	https://paperswithcode.com/paper/deep-ensemble-tensor-factorization-for
Repo
Framework

Towards an Understanding of Neural Networks in Natural-Image Spaces


Title	Towards an Understanding of Neural Networks in Natural-Image Spaces
Authors	Yifei Fan, Anthony Yezzi
Abstract	Two major uncertainties, dataset bias and adversarial examples, prevail in state-of-the-art AI algorithms with deep neural networks. In this paper, we present an intuitive explanation for these issues as well as an interpretation of the performance of deep networks in a natural-image space. The explanation consists of two parts: the philosophy of neural networks and a hypothetical model of natural-image spaces. Following the explanation, we 1) demonstrate that the values of training samples differ, 2) provide incremental boost to the accuracy of a CIFAR-10 classifier by introducing an additional “random-noise” category during training, 3) alleviate over-fitting thereby enhancing the robustness against adversarial examples by detecting and excluding illusive training samples that are consistently misclassified. Our overall contribution is therefore twofold. First, while most existing algorithms treat data equally and have a strong appetite for more data, we demonstrate in contrast that an individual datum can sometimes have disproportionate and counterproductive influence and that it is not always better to train neural networks with more data. Next, we consider more thoughtful strategies by taking into account the geometric and topological properties of natural-image spaces to which deep networks are applied.
Tasks
Published	2018-01-27
URL	http://arxiv.org/abs/1801.09097v2
PDF	http://arxiv.org/pdf/1801.09097v2.pdf
PWC	https://paperswithcode.com/paper/towards-an-understanding-of-neural-networks
Repo
Framework

Text Classification based on Multiple Block Convolutional Highways


Title	Text Classification based on Multiple Block Convolutional Highways
Authors	Seyed Mahdi Rezaeinia, Ali Ghodsi, Rouhollah Rahmani
Abstract	In the Text Classification areas of Sentiment Analysis, Subjectivity/Objectivity Analysis, and Opinion Polarity, Convolutional Neural Networks have gained special attention because of their performance and accuracy. In this work, we applied recent advances in CNNs and propose a novel architecture, Multiple Block Convolutional Highways (MBCH), which achieves improved accuracy on multiple popular benchmark datasets, compared to previous architectures. The MBCH is based on new techniques and architectures including highway networks, DenseNet, batch normalization and bottleneck layers. In addition, to cope with the limitations of existing pre-trained word vectors which are used as inputs for the CNN, we propose a novel method, Improved Word Vectors (IWV). The IWV improves the accuracy of CNNs which are used for text classification tasks.
Tasks	Sentiment Analysis, Text Classification
Published	2018-07-23
URL	http://arxiv.org/abs/1807.09602v1
PDF	http://arxiv.org/pdf/1807.09602v1.pdf
PWC	https://paperswithcode.com/paper/text-classification-based-on-multiple-block
Repo
Framework

Deep Contextual Multi-armed Bandits


Title	Deep Contextual Multi-armed Bandits
Authors	Mark Collier, Hector Urdiales Llorens
Abstract	Contextual multi-armed bandit problems arise frequently in important industrial applications. Existing solutions model the context either linearly, which enables uncertainty driven (principled) exploration, or non-linearly, by using epsilon-greedy exploration policies. Here we present a deep learning framework for contextual multi-armed bandits that is both non-linear and enables principled exploration at the same time. We tackle the exploration vs. exploitation trade-off through Thompson sampling by exploiting the connection between inference time dropout and sampling from the posterior over the weights of a Bayesian neural network. In order to adjust the level of exploration automatically as more data is made available to the model, the dropout rate is learned rather than considered a hyperparameter. We demonstrate that our approach substantially reduces regret on two tasks (the UCI Mushroom task and the Casino Parity task) when compared to 1) non-contextual bandits, 2) epsilon-greedy deep contextual bandits, and 3) fixed dropout rate deep contextual bandits. Our approach is currently being applied to marketing optimization problems at HubSpot.
Tasks	Multi-Armed Bandits
Published	2018-07-25
URL	http://arxiv.org/abs/1807.09809v1
PDF	http://arxiv.org/pdf/1807.09809v1.pdf
PWC	https://paperswithcode.com/paper/deep-contextual-multi-armed-bandits
Repo
Framework

Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior


Title	Explicability? Legibility? Predictability? Transparency? Privacy? Security? The Emerging Landscape of Interpretable Agent Behavior
Authors	Tathagata Chakraborti, Anagha Kulkarni, Sarath Sreedharan, David E. Smith, Subbarao Kambhampati
Abstract	There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for “explicable”, “legible”, “predictable” and “transparent” planning with overlapping, and sometimes conflicting, semantics all aimed at some notion of understanding what intentions the observer will ascribe to an agent by observing its behavior. This is also true for the recent works on “security” and “privacy” of plans which are also trying to answer the same question, but from the opposite point of view – i.e. when the agent is trying to hide instead of revealing its intentions. This paper attempts to provide a workable taxonomy of relevant concepts in this exciting and emerging field of inquiry.
Tasks
Published	2018-11-23
URL	http://arxiv.org/abs/1811.09722v1
PDF	http://arxiv.org/pdf/1811.09722v1.pdf
PWC	https://paperswithcode.com/paper/explicability-legibility-predictability
Repo
Framework

Partial recovery bounds for clustering with the relaxed $K$means


Title	Partial recovery bounds for clustering with the relaxed $K$means
Authors	Christophe Giraud, Nicolas Verzelen
Abstract	We investigate the clustering performances of the relaxed $K$means in the setting of sub-Gaussian Mixture Model (sGMM) and Stochastic Block Model (SBM). After identifying the appropriate signal-to-noise ratio (SNR), we prove that the misclassification error decay exponentially fast with respect to this SNR. These partial recovery bounds for the relaxed $K$means improve upon results currently known in the sGMM setting. In the SBM setting, applying the relaxed $K$means SDP allows to handle general connection probabilities whereas other SDPs investigated in the literature are restricted to the assortative case (where within group probabilities are larger than between group probabilities). Again, this partial recovery bound complements the state-of-the-art results. All together, these results put forward the versatility of the relaxed $K$means.
Tasks
Published	2018-07-19
URL	http://arxiv.org/abs/1807.07547v3
PDF	http://arxiv.org/pdf/1807.07547v3.pdf
PWC	https://paperswithcode.com/paper/partial-recovery-bounds-for-clustering-with
Repo
Framework

Towards Understanding Linear Word Analogies


Title	Towards Understanding Linear Word Analogies
Authors	Kawin Ethayarajh, David Duvenaud, Graeme Hirst
Abstract	A surprising property of word vectors is that word analogies can often be solved with vector arithmetic. However, it is unclear why arithmetic operators correspond to non-linear embedding models such as skip-gram with negative sampling (SGNS). We provide a formal explanation of this phenomenon without making the strong assumptions that past theories have made about the vector space and word distribution. Our theory has several implications. Past work has conjectured that linear substructures exist in vector spaces because relations can be represented as ratios; we prove that this holds for SGNS. We provide novel justification for the addition of SGNS word vectors by showing that it automatically down-weights the more frequent word, as weighting schemes do ad hoc. Lastly, we offer an information theoretic interpretation of Euclidean distance in vector spaces, justifying its use in capturing word dissimilarity.
Tasks
Published	2018-10-11
URL	https://arxiv.org/abs/1810.04882v7
PDF	https://arxiv.org/pdf/1810.04882v7.pdf
PWC	https://paperswithcode.com/paper/towards-understanding-linear-word-analogies
Repo
Framework

A Unified Perspective of Evolutionary Game Dynamics Using Generalized Growth Transforms


Title	A Unified Perspective of Evolutionary Game Dynamics Using Generalized Growth Transforms
Authors	Oindrila Chatterjee, Shantanu Chakrabartty
Abstract	In this paper, we show that different types of evolutionary game dynamics are, in principle, special cases of a dynamical system model based on our previously reported framework of generalized growth transforms. The framework shows that different dynamics arise as a result of minimizing a population energy such that the population as a whole evolves to reach the most stable state. By introducing a population dependent time-constant in the generalized growth transform model, the proposed framework can be used to explain a vast repertoire of evolutionary dynamics, including some novel forms of game dynamics with non-linear payoffs.
Tasks
Published	2018-11-05
URL	http://arxiv.org/abs/1811.02010v1
PDF	http://arxiv.org/pdf/1811.02010v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-perspective-of-evolutionary-game
Repo
Framework

Improving QED-Tutrix by Automating the Generation of Proofs


Title	Improving QED-Tutrix by Automating the Generation of Proofs
Authors	Ludovic Font, Philippe R. Richard, Michel Gagnon
Abstract	The idea of assisting teachers with technological tools is not new. Mathematics in general, and geometry in particular, provide interesting challenges when developing educative softwares, both in the education and computer science aspects. QED-Tutrix is an intelligent tutor for geometry offering an interface to help high school students in the resolution of demonstration problems. It focuses on specific goals: 1) to allow the student to freely explore the problem and its figure, 2) to accept proofs elements in any order, 3) to handle a variety of proofs, which can be customized by the teacher, and 4) to be able to help the student at any step of the resolution of the problem, if the need arises. The software is also independent from the intervention of the teacher. QED-Tutrix offers an interesting approach to geometry education, but is currently crippled by the lengthiness of the process of implementing new problems, a task that must still be done manually. Therefore, one of the main focuses of the QED-Tutrix’ research team is to ease the implementation of new problems, by automating the tedious step of finding all possible proofs for a given problem. This automation must follow fundamental constraints in order to create problems compatible with QED-Tutrix: 1) readability of the proofs, 2) accessibility at a high school level, and 3) possibility for the teacher to modify the parameters defining the “acceptability” of a proof. We present in this paper the result of our preliminary exploration of possible avenues for this task. Automated theorem proving in geometry is a widely studied subject, and various provers exist. However, our constraints are quite specific and some adaptation would be required to use an existing prover. We have therefore implemented a prototype of automated prover to suit our needs. The future goal is to compare performances and usability in our specific use-case between the existing provers and our implementation.
Tasks	Automated Theorem Proving
Published	2018-03-05
URL	http://arxiv.org/abs/1803.01468v1
PDF	http://arxiv.org/pdf/1803.01468v1.pdf
PWC	https://paperswithcode.com/paper/improving-qed-tutrix-by-automating-the
Repo
Framework