October 19, 2019

3262 words 16 mins read

Paper Group ANR 255

Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering. Identifying The Most Informative Features Using A Structurally Interacting Elastic Net. Robustness via Deep Low-Rank Representations. Behavior Trees as a Representation for Medical Procedures. Facilitating the Manual Annotatio …

Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering


Title	Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering
Authors	Valentin Stanev, Velimir V. Vesselinov, A. Gilad Kusne, Graham Antoszewski, Ichiro Takeuchi, Boian S. Alexandrov
Abstract	Analyzing large X-ray diffraction (XRD) datasets is a key step in high-throughput mapping of the compositional phase diagrams of combinatorial materials libraries. Optimizing and automating this task can help accelerate the process of discovery of materials with novel and desirable properties. Here, we report a new method for pattern analysis and phase extraction of XRD datasets. The method expands the Nonnegative Matrix Factorization method, which has been used previously to analyze such datasets, by combining it with custom clustering and cross-correlation algorithms. This new method is capable of robust determination of the number of basis patterns present in the data which, in turn, enables straightforward identification of any possible peak-shifted patterns. Peak-shifting arises due to continuous change in the lattice constants as a function of composition, and is ubiquitous in XRD datasets from composition spread libraries. Successful identification of the peak-shifted patterns allows proper quantification and classification of the basis XRD patterns, which is necessary in order to decipher the contribution of each unique single-phase structure to the multi-phase regions. The process can be utilized to determine accurately the compositional phase diagram of a system under study. The presented method is applied to one synthetic and one experimental dataset, and demonstrates robust accuracy and identification abilities.
Tasks	X-Ray Diffraction (XRD)
Published	2018-02-20
URL	http://arxiv.org/abs/1802.07307v1
PDF	http://arxiv.org/pdf/1802.07307v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-phase-mapping-of-x-ray
Repo
Framework

Identifying The Most Informative Features Using A Structurally Interacting Elastic Net


Title	Identifying The Most Informative Features Using A Structurally Interacting Elastic Net
Authors	Lixin Cui, Lu Bai, Zhihong Zhang, Yue Wang, Edwin R. Hancock
Abstract	Feature selection can efficiently identify the most informative features with respect to the target feature used in training. However, state-of-the-art vector-based methods are unable to encapsulate the relationships between feature samples into the feature selection process, thus leading to significant information loss. To address this problem, we propose a new graph-based structurally interacting elastic net method for feature selection. Specifically, we commence by constructing feature graphs that can incorporate pairwise relationship between samples. With the feature graphs to hand, we propose a new information theoretic criterion to measure the joint relevance of different pairwise feature combinations with respect to the target feature graph representation. This measure is used to obtain a structural interaction matrix where the elements represent the proposed information theoretic measure between feature pairs. We then formulate a new optimization model through the combination of the structural interaction matrix and an elastic net regression model for the feature subset selection problem. This allows us to a) preserve the information of the original vectorial space, b) remedy the information loss of the original feature space caused by using graph representation, and c) promote a sparse solution and also encourage correlated features to be selected. Because the proposed optimization problem is non-convex, we develop an efficient alternating direction multiplier method (ADMM) to locate the optimal solutions. Extensive experiments on various datasets demonstrate the effectiveness of the proposed methods.
Tasks	Feature Selection
Published	2018-09-08
URL	http://arxiv.org/abs/1809.02860v1
PDF	http://arxiv.org/pdf/1809.02860v1.pdf
PWC	https://paperswithcode.com/paper/identifying-the-most-informative-features
Repo
Framework

Robustness via Deep Low-Rank Representations


Title	Robustness via Deep Low-Rank Representations
Authors	Amartya Sanyal, Varun Kanade, Philip H. S. Torr, Puneet K. Dokania
Abstract	We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations, we propose an easy-to-use, end-to-end trainable, low-rank regularizer (LR) that can be applied to any intermediate layer representation of a DNN. This regularizer forces the feature representations to (mostly) lie in a low-dimensional linear subspace. We perform a wide range of experiments that demonstrate that the LR indeed induces low rank on the representations, while providing modest improvements to accuracy as an added benefit. Furthermore, the learned features make the trained model significantly more robust to input perturbations such as Gaussian and adversarial noise (even without adversarial training). Lastly, the low-dimensionality means that the learned features are highly compressible; thus discriminative features of the data can be stored using very little memory. Our experiments indicate that models trained using the LR learn robust classifiers by discovering subspaces that avoid non-robust features. Algorithmically, the LR is scalable, generic, and straightforward to implement into existing deep learning frameworks.
Tasks	Image Classification, Transfer Learning
Published	2018-04-19
URL	https://arxiv.org/abs/1804.07090v5
PDF	https://arxiv.org/pdf/1804.07090v5.pdf
PWC	https://paperswithcode.com/paper/intriguing-properties-of-learned
Repo
Framework

Behavior Trees as a Representation for Medical Procedures


Title	Behavior Trees as a Representation for Medical Procedures
Authors	Blake Hannaford, Randall Bly, Ian Humphreys, Mark Whipple
Abstract	Objective: Effective collaboration between machines and clinicians requires flexible data structures to represent medical processes and clinical practice guidelines. Such a data structure could enable effective turn-taking between human and automated components of a complex treatment, accurate on-line monitoring of clinical treatments (for example to detect medical errors), or automated treatment systems (such as future medical robots) whose overall treatment plan is understandable and auditable by human experts. Materials and Methods: Behavior trees (BTs) emerged from video game development as a graphical language for modeling intelligent agent behavior. BTs have several properties which are attractive for modeling medical procedures including human-readability, authoring tools, and composability. Results: This paper will illustrate construction of BTs for exemplary medical procedures and clinical protocols. Discussion and Conclusion: Behavior Trees thus form a useful, and human authorable/readable bridge between clinical practice guidelines and AI systems.
Tasks
Published	2018-08-27
URL	http://arxiv.org/abs/1808.08954v1
PDF	http://arxiv.org/pdf/1808.08954v1.pdf
PWC	https://paperswithcode.com/paper/behavior-trees-as-a-representation-for
Repo
Framework

Facilitating the Manual Annotation of Sounds When Using Large Taxonomies


Title	Facilitating the Manual Annotation of Sounds When Using Large Taxonomies
Authors	Xavier Favory, Eduardo Fonseca, Frederic Font, Xavier Serra
Abstract	Properly annotated multimedia content is crucial for supporting advances in many Information Retrieval applications. It enables, for instance, the development of automatic tools for the annotation of large and diverse multimedia collections. In the context of everyday sounds and online collections, the content to describe is very diverse and involves many different types of concepts, often organised in large hierarchical structures called taxonomies. This makes the task of manually annotating content arduous. In this paper, we present our user-centered development of two tools for the manual annotation of audio content from a wide range of types. We conducted a preliminary evaluation of functional prototypes involving real users. The goal is to evaluate them in a real context, engage in discussions with users, and inspire new ideas. A qualitative analysis was carried out including usability questionnaires and semi-structured interviews. This revealed interesting aspects to consider when developing tools for the manual annotation of audio content with labels drawn from large hierarchical taxonomies.
Tasks	Information Retrieval
Published	2018-11-21
URL	http://arxiv.org/abs/1811.10988v1
PDF	http://arxiv.org/pdf/1811.10988v1.pdf
PWC	https://paperswithcode.com/paper/facilitating-the-manual-annotation-of-sounds
Repo
Framework

ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation


Title	ConnNet: A Long-Range Relation-Aware Pixel-Connectivity Network for Salient Segmentation
Authors	Michael Kampffmeyer, Nanqing Dong, Xiaodan Liang, Yujia Zhang, Eric P. Xing
Abstract	Salient segmentation aims to segment out attention-grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and benefits from the utilization of global multi-scale contexts to achieve good local reasoning. Previous works often address it as two-class segmentation problems utilizing complicated multi-step procedures including refinement networks and complex graphical models. We argue that semantic salient segmentation can instead be effectively resolved by reformulating it as a simple yet intuitive pixel-pair based connectivity prediction task. Following the intuition that salient objects can be naturally grouped via semantic-aware connectivity between neighboring pixels, we propose a pure Connectivity Net (ConnNet). ConnNet predicts connectivity probabilities of each pixel with its neighboring pixels by leveraging multi-level cascade contexts embedded in the image and long-range pixel relations. We investigate our approach on two tasks, namely salient object segmentation and salient instance-level segmentation, and illustrate that consistent improvements can be obtained by modeling these tasks as connectivity instead of binary segmentation tasks for a variety of network architectures. We achieve state-of-the-art performance, outperforming or being comparable to existing approaches while reducing inference time due to our less complex approach.
Tasks	Semantic Segmentation
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07836v2
PDF	http://arxiv.org/pdf/1804.07836v2.pdf
PWC	https://paperswithcode.com/paper/connnet-a-long-range-relation-aware-pixel
Repo
Framework


Title	Revisit Batch Normalization: New Understanding from an Optimization View and a Refinement via Composition Optimization
Authors	Xiangru Lian, Ji Liu
Abstract	Batch Normalization (BN) has been used extensively in deep learning to achieve faster training process and better resulting models. However, whether BN works strongly depends on how the batches are constructed during training and it may not converge to a desired solution if the statistics on a batch are not close to the statistics over the whole dataset. In this paper, we try to understand BN from an optimization perspective by formulating the optimization problem which motivates BN. We show when BN works and when BN does not work by analyzing the optimization problem. We then propose a refinement of BN based on compositional optimization techniques called Full Normalization (FN) to alleviate the issues of BN when the batches are not constructed ideally. We provide convergence analysis for FN and empirically study its effectiveness to refine BN.
Tasks
Published	2018-10-15
URL	http://arxiv.org/abs/1810.06177v1
PDF	http://arxiv.org/pdf/1810.06177v1.pdf
PWC	https://paperswithcode.com/paper/revisit-batch-normalization-new-understanding
Repo
Framework

Term Set Expansion based NLP Architect by Intel AI Lab


Title	Term Set Expansion based NLP Architect by Intel AI Lab
Authors	Jonathan Mamou, Oren Pereg, Moshe Wasserblat, Alon Eirew, Yael Green, Shira Guskin, Peter Izsak, Daniel Korat
Abstract	We present SetExpander, a corpus-based system for expanding a seed set of terms into amore complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to-end workflow. It enables users to easily select a seed set of terms, expand it, view the expanded set, validate it, re-expand the validated set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes.SetExpander has been used successfully in real-life use cases including integration into an automated recruitment system and an issues and defects resolution system. A video demo of SetExpander is available at https://drive.google.com/open?id=1e545bB87Autsch36DjnJHmq3HWfSd1Rv (some images were blurred for privacy reasons)
Tasks
Published	2018-08-27
URL	http://arxiv.org/abs/1808.08953v2
PDF	http://arxiv.org/pdf/1808.08953v2.pdf
PWC	https://paperswithcode.com/paper/term-set-expansion-based-nlp-architect-by
Repo
Framework

Term Set Expansion based on Multi-Context Term Embeddings: an End-to-end Workflow


Title	Term Set Expansion based on Multi-Context Term Embeddings: an End-to-end Workflow
Authors	Jonathan Mamou, Oren Pereg, Moshe Wasserblat, Ido Dagan, Yoav Goldberg, Alon Eirew, Yael Green, Shira Guskin, Peter Izsak, Daniel Korat
Abstract	We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to end workflow for term set expansion. It enables users to easily select a seed set of terms, expand it, view the expanded set, validate it, re-expand the validated set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes. SetExpander has been used for solving real-life use cases including integration in an automated recruitment system and an issues and defects resolution system. A video demo of SetExpander is available at https://drive.google.com/open?id=1e545bB87Autsch36DjnJHmq3HWfSd1Rv (some images were blurred for privacy reasons).
Tasks
Published	2018-07-26
URL	http://arxiv.org/abs/1807.10104v1
PDF	http://arxiv.org/pdf/1807.10104v1.pdf
PWC	https://paperswithcode.com/paper/term-set-expansion-based-on-multi-context
Repo
Framework

Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning


Title	Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning
Authors	Yunlong Yu, Zhong Ji, Yanwei Fu, Jichang Guo, Yanwei Pang, Zhongfei Zhang
Abstract	Zero-Shot Learning (ZSL) is achieved via aligning the semantic relationships between the global image feature vector and the corresponding class semantic descriptions. However, using the global features to represent fine-grained images may lead to sub-optimal results since they neglect the discriminative differences of local regions. Besides, different regions contain distinct discriminative information. The important regions should contribute more to the prediction. To this end, we propose a novel stacked semantics-guided attention (S2GA) model to obtain semantic relevant features by using individual class semantic features to progressively guide the visual features to generate an attention map for weighting the importance of different local regions. Feeding both the integrated visual features and the class semantic features into a multi-class classification architecture, the proposed framework can be trained end-to-end. Extensive experimental results on CUB and NABird datasets show that the proposed approach has a consistent improvement on both fine-grained zero-shot classification and retrieval tasks.
Tasks	Zero-Shot Learning
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08113v1
PDF	http://arxiv.org/pdf/1805.08113v1.pdf
PWC	https://paperswithcode.com/paper/stacked-semantic-guided-attention-model-for
Repo
Framework

Automatic catheter detection in pediatric X-ray images using a scale-recurrent network and synthetic data


Title	Automatic catheter detection in pediatric X-ray images using a scale-recurrent network and synthetic data
Authors	Xin Yi, Scott Adams, Paul Babyn, Abdul Elnajmi
Abstract	Catheters are commonly inserted life supporting devices. X-ray images are used to assess the position of a catheter immediately after placement as serious complications can arise from malpositioned catheters. Previous computer vision approaches to detect catheters on X-ray images either relied on low-level cues that are not sufficiently robust or only capable of processing a limited number or type of catheters. With the resurgence of deep learning, supervised training approaches are begining to showing promising results. However, dense annotation maps are required, and the work of a human annotator is hard to scale. In this work, we proposed a simple way of synthesizing catheters on X-ray images and a scale recurrent network for catheter detection. By training on adult chest X-rays, the proposed network exhibits promising detection results on pediatric chest/abdomen X-rays in terms of both precision and recall.
Tasks
Published	2018-06-04
URL	http://arxiv.org/abs/1806.00921v1
PDF	http://arxiv.org/pdf/1806.00921v1.pdf
PWC	https://paperswithcode.com/paper/automatic-catheter-detection-in-pediatric-x
Repo
Framework

Multi-Task Deep Learning for Legal Document Translation, Summarization and Multi-Label Classification


Title	Multi-Task Deep Learning for Legal Document Translation, Summarization and Multi-Label Classification
Authors	Ahmed Elnaggar, Christoph Gebendorfer, Ingo Glaser, Florian Matthes
Abstract	The digitalization of the legal domain has been ongoing for a couple of years. In that process, the application of different machine learning (ML) techniques is crucial. Tasks such as the classification of legal documents or contract clauses as well as the translation of those are highly relevant. On the other side, digitized documents are barely accessible in this field, particularly in Germany. Today, deep learning (DL) is one of the hot topics with many publications and various applications. Sometimes it provides results outperforming the human level. Hence this technique may be feasible for the legal domain as well. However, DL requires thousands of samples to provide decent results. A potential solution to this problem is multi-task DL to enable transfer learning. This approach may be able to overcome the data scarcity problem in the legal domain, specifically for the German language. We applied the state of the art multi-task model on three tasks: translation, summarization, and multi-label classification. The experiments were conducted on legal document corpora utilizing several task combinations as well as various model parameters. The goal was to find the optimal configuration for the tasks at hand within the legal domain. The multi-task DL approach outperformed the state of the art results in all three tasks. This opens a new direction to integrate DL technology more efficiently in the legal domain.
Tasks	Legal Document Translation, Multi-Label Classification, Transfer Learning
Published	2018-10-16
URL	http://arxiv.org/abs/1810.07513v1
PDF	http://arxiv.org/pdf/1810.07513v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-deep-learning-for-legal-document
Repo
Framework

Self-Similar Epochs: Value in Arrangement


Title	Self-Similar Epochs: Value in Arrangement
Authors	Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias
Abstract	Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples. This practice means that sub-epochs comprise of independent random samples of the training data that may not preserve informative structure present in the full data. We hypothesize that the training can be more effective with {\em self-similar} arrangements that potentially allow each epoch to provide benefits of multiple ones. We study this for “matrix factorization” – the common task of learning metric embeddings of entities such as queries, videos, or words from example pairwise associations. We construct arrangements that preserve the weighted Jaccard similarities of rows and columns and experimentally observe training acceleration of 3%-37% on synthetic and recommendation datasets. Principled arrangements of training examples emerge as a novel and potentially powerful enhancement to SGD that merits further exploration.
Tasks
Published	2018-03-14
URL	https://arxiv.org/abs/1803.05389v3
PDF	https://arxiv.org/pdf/1803.05389v3.pdf
PWC	https://paperswithcode.com/paper/lsh-microbatches-for-stochastic-gradients
Repo
Framework

Predicting Diabetes Disease Evolution Using Financial Records and Recurrent Neural Networks


Title	Predicting Diabetes Disease Evolution Using Financial Records and Recurrent Neural Networks
Authors	Rafael T. Sousa, Lucas A. Pereira, Anderson S. Soares
Abstract	Managing patients with chronic diseases is a major and growing healthcare challenge in several countries. A chronic condition, such as diabetes, is an illness that lasts a long time and does not go away, and often leads to the patient’s health gradually getting worse. While recent works involve raw electronic health record (EHR) from hospitals, this work uses only financial records from health plan providers (medical claims) to predict diabetes disease evolution with a self-attentive recurrent neural network. The use of financial data is due to the possibility of being an interface to international standards, as the records standard encodes medical procedures. The main goal was to assess high risk diabetics, so we predict records related to diabetes acute complications such as amputations and debridements, revascularization and hemodialysis. Our work succeeds to anticipate complications between 60 to 240 days with an area under ROC curve ranging from 0.81 to 0.94. In this paper we describe the first half of a work-in-progress developed within a health plan provider with ROC curve ranging from 0.81 to 0.83. This assessment will give healthcare providers the chance to intervene earlier and head off hospitalizations. We are aiming to deliver personalized predictions and personalized recommendations to individual patients, with the goal of improving outcomes and reducing costs
Tasks
Published	2018-11-23
URL	https://arxiv.org/abs/1811.09350v2
PDF	https://arxiv.org/pdf/1811.09350v2.pdf
PWC	https://paperswithcode.com/paper/predicting-diabetes-disease-evolution-using
Repo
Framework

Enhancing Multi-Class Classification of Random Forest using Random Vector Functional Neural Network and Oblique Decision Surfaces


Title	Enhancing Multi-Class Classification of Random Forest using Random Vector Functional Neural Network and Oblique Decision Surfaces
Authors	Rakesh Katuwal, P. N. Suganthan
Abstract	Both neural networks and decision trees are popular machine learning methods and are widely used to solve problems from diverse domains. These two classifiers are commonly used base classifiers in an ensemble framework. In this paper, we first present a new variant of oblique decision tree based on a linear classifier, then construct an ensemble classifier based on the fusion of a fast neural network, random vector functional link network and oblique decision trees. Random Vector Functional Link Network has an elegant closed form solution with extremely short training time. The neural network partitions each training bag (obtained using bagging) at the root level into C subsets where C is the number of classes in the dataset and subsequently, C oblique decision trees are trained on such partitions. The proposed method provides a rich insight into the data by grouping the confusing or hard to classify samples for each class and thus, provides an opportunity to employ fine-grained classification rule over the data. The performance of the ensemble classifier is evaluated on several multi-class datasets where it demonstrates a superior performance compared to other state-of- the-art classifiers.
Tasks
Published	2018-02-05
URL	http://arxiv.org/abs/1802.01240v1
PDF	http://arxiv.org/pdf/1802.01240v1.pdf
PWC	https://paperswithcode.com/paper/enhancing-multi-class-classification-of
Repo
Framework