Paper Group ANR 214
Federated Learning over Wireless Fading Channels. Towards the Enhancement of Body Standing Balance Recovery by Means of a Wireless Audio-Biofeedback System. Unsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment. DeepHuman: 3D Human Reconstruction from a Single Image. Multi-View Multi-Instanc …
Federated Learning over Wireless Fading Channels
| Title | Federated Learning over Wireless Fading Channels |
| Authors | Mohammad Mohammadi Amiri, Deniz Gunduz |
| Abstract | We study federated machine learning at the wireless network edge, where limited power wireless devices, each with its own dataset, build a joint model with the help of a remote parameter server (PS). We consider a bandwidth-limited fading multiple access channel (MAC) from the wireless devices to the PS, and propose various techniques to implement distributed stochastic gradient descent (DSGD). We first propose a digital DSGD (D-DSGD) scheme, in which one device is selected opportunistically for transmission at each iteration based on the channel conditions; the scheduled device quantizes its gradient estimate to a finite number of bits imposed by the channel condition, and transmits these bits to the PS in a reliable manner. Next, motivated by the additive nature of the wireless MAC, we propose a novel analog communication scheme, referred to as the compressed analog DSGD (CA-DSGD), where the devices first sparsify their gradient estimates while accumulating error, and project the resultant sparse vector into a low-dimensional vector for bandwidth reduction. Numerical results show that D-DSGD outperforms other digital approaches in the literature; however, in general the proposed CA-DSGD algorithm converges faster than the D-DSGD scheme and other schemes in the literature, and reaches a higher level of accuracy. We have observed that the gap between the analog and digital schemes increases when the datasets of devices are not independent and identically distributed (i.i.d.). Furthermore, the performance of the CA-DSGD scheme is shown to be robust against imperfect channel state information (CSI) at the devices. Overall these results show clear advantages for the proposed analog over-the-air DSGD scheme, which suggests that learning and communication algorithms should be designed jointly to achieve the best end-to-end performance in machine learning applications at the wireless edge. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09769v2 |
| https://arxiv.org/pdf/1907.09769v2.pdf | |
| PWC | https://paperswithcode.com/paper/federated-learning-over-wireless-fading |
| Repo | |
| Framework | |
Towards the Enhancement of Body Standing Balance Recovery by Means of a Wireless Audio-Biofeedback System
| Title | Towards the Enhancement of Body Standing Balance Recovery by Means of a Wireless Audio-Biofeedback System |
| Authors | Giovanni Costantini, Daniele Casali, Fabio Paolizzo, Marco Alessandrini, Alessandro Micarelli, Andrea Viziano, Giovanni Saggio |
| Abstract | Human maintain their body balance by sensorimotor controls mainly based on information gathered from vision, proprioception and vestibular systems. When there is a lack of information, caused by pathologies, diseases or aging, the subject may fall. In this context, we developed a system to augment information gathering, providing the subject with warning audio-feedback signals related to his/her equilibrium. The system comprises an inertial measurement unit (IMU), a data processing unit, a headphone audio device and a software application. The IMU is a low-weight, small-size wireless instrument that, body-back located between the L2 and L5 lumbar vertebrae, measures the subject’s trunk kinematics. The application drives the data processing unit to feeding the headphone with electric signals related to the kinematic measures. Consequently, the user is audio-alerted, via headphone, of his/her own equilibrium, hearing a pleasant sound when in a stable equilibrium, or an increasing bothering sound when in an increasing unstable condition. Tests were conducted on a group of six older subjects (59y-61y, SD = 2.09y) and a group of four young subjects (21y-26y, SD = 2.88y) to underline difference in effectiveness of the system, if any, related to the age of the users. For each subject, standing balance tests were performed in normal or altered conditions, such as, open or closed eyes, and on a solid or foam surface The system was evaluated in terms of usability, reliability, and effectiveness in improving the subject’s balance in all conditions. As a result, the system successfully helped the subjects in reducing the body swaying within 10.65%-65.90%, differences depending on subjects’ age and test conditions. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11542v1 |
| https://arxiv.org/pdf/1907.11542v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-the-enhancement-of-body-standing |
| Repo | |
| Framework | |
Unsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment
| Title | Unsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment |
| Authors | Artjom Zern, Matthias Zisler, Stefania Petra, Christoph Schnörr |
| Abstract | This paper introduces the unsupervised assignment flow that couples the assignment flow for supervised image labeling with Riemannian gradient flows for label evolution on feature manifolds. The latter component of the approach encompasses extensions of state-of-the-art clustering approaches to manifold-valued data. Coupling label evolution with the spatially regularized assignment flow induces a sparsifying effect that enables to learn compact label dictionaries in an unsupervised manner. Our approach alleviates the requirement for supervised labeling to have proper labels at hand, because an initial set of labels can evolve and adapt to better values while being assigned to given data. The separation between feature and assignment manifolds enables the flexible application which is demonstrated for three scenarios with manifold-valued features. Experiments demonstrate a beneficial effect in both directions: adaptivity of labels improves image labeling, and steering label evolution by spatially regularized assignments leads to proper labels, because the assignment flow for supervised labeling is exactly used without any approximation for label learning. |
| Tasks | |
| Published | 2019-04-24 |
| URL | https://arxiv.org/abs/1904.10863v3 |
| https://arxiv.org/pdf/1904.10863v3.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-assignment-flow-label-learning |
| Repo | |
| Framework | |
DeepHuman: 3D Human Reconstruction from a Single Image
| Title | DeepHuman: 3D Human Reconstruction from a Single Image |
| Authors | Zerong Zheng, Tao Yu, Yixuan Wei, Qionghai Dai, Yebin Liu |
| Abstract | We propose DeepHuman, an image-guided volume-to-volume translation CNN for 3D human reconstruction from a single RGB image. To reduce the ambiguities associated with the surface geometry reconstruction, even for the reconstruction of invisible areas, we propose and leverage a dense semantic representation generated from SMPL model as an additional input. One key feature of our network is that it fuses different scales of image features into the 3D space through volumetric feature transformation, which helps to recover accurate surface geometry. The visible surface details are further refined through a normal refinement network, which can be concatenated with the volume generation network using our proposed volumetric normal projection layer. We also contribute THuman, a 3D real-world human model dataset containing about 7000 models. The network is trained using training data generated from the dataset. Overall, due to the specific design of our network and the diversity in our dataset, our method enables 3D human model estimation given only a single image and outperforms state-of-the-art approaches. |
| Tasks | Pose Estimation |
| Published | 2019-03-15 |
| URL | http://arxiv.org/abs/1903.06473v2 |
| http://arxiv.org/pdf/1903.06473v2.pdf | |
| PWC | https://paperswithcode.com/paper/deephuman-3d-human-reconstruction-from-a |
| Repo | |
| Framework | |
Multi-View Multi-Instance Multi-Label Learning based on Collaborative Matrix Factorization
| Title | Multi-View Multi-Instance Multi-Label Learning based on Collaborative Matrix Factorization |
| Authors | Yuying Xing, Guoxian Yu, Carlotta Domeniconi, Jun Wang, Zili Zhang, Maozu Guo |
| Abstract | Multi-view Multi-instance Multi-label Learning(M3L) deals with complex objects encompassing diverse instances, represented with different feature views, and annotated with multiple labels. Existing M3L solutions only partially explore the inter or intra relations between objects (or bags), instances, and labels, which can convey important contextual information for M3L. As such, they may have a compromised performance. In this paper, we propose a collaborative matrix factorization based solution called M3Lcmf. M3Lcmf first uses a heterogeneous network composed of nodes of bags, instances, and labels, to encode different types of relations via multiple relational data matrices. To preserve the intrinsic structure of the data matrices, M3Lcmf collaboratively factorizes them into low-rank matrices, explores the latent relationships between bags, instances, and labels, and selectively merges the data matrices. An aggregation scheme is further introduced to aggregate the instance-level labels into bag-level and to guide the factorization. An empirical study on benchmark datasets show that M3Lcmf outperforms other related competitive solutions both in the instance-level and bag-level prediction. |
| Tasks | Multi-Label Learning |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.05061v2 |
| https://arxiv.org/pdf/1905.05061v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-multi-instance-multi-label |
| Repo | |
| Framework | |
Synthetic Oversampling of Multi-Label Data based on Local Label Distribution
| Title | Synthetic Oversampling of Multi-Label Data based on Local Label Distribution |
| Authors | Bin Liu, Grigorios Tsoumakas |
| Abstract | Class-imbalance is an inherent characteristic of multi-label data which affects the prediction accuracy of most multi-label learning methods. One efficient strategy to deal with this problem is to employ resampling techniques before training the classifier. Existing multilabel sampling methods alleviate the (global) imbalance of multi-label datasets. However, performance degradation is mainly due to rare subconcepts and overlapping of classes that could be analysed by looking at the local characteristics of the minority examples, rather than the imbalance of the whole dataset. We propose a new method for synthetic oversampling of multi-label data that focuses on local label distribution to generate more diverse and better labeled instances. Experimental results on 13 multi-label datasets demonstrate the effectiveness of the proposed approach in a variety of evaluation measures, particularly in the case of an ensemble of classifiers trained on repeated samples of the original data. |
| Tasks | Multi-Label Learning |
| Published | 2019-05-02 |
| URL | https://arxiv.org/abs/1905.00609v2 |
| https://arxiv.org/pdf/1905.00609v2.pdf | |
| PWC | https://paperswithcode.com/paper/synthetic-oversampling-of-multi-label-data |
| Repo | |
| Framework | |
Answering Conversational Questions on Structured Data without Logical Forms
| Title | Answering Conversational Questions on Structured Data without Logical Forms |
| Authors | Thomas Müller, Francesco Piccinno, Massimo Nicosia, Peter Shaw, Yasemin Altun |
| Abstract | We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation. We encode tables as graphs using a graph neural network model based on the Transformer architecture. The answers are then selected from the encoded graph using a pointer network. This model is appropriate for processing conversations around structured data, where the attention mechanism that selects the answers to a question can also be used to resolve conversational references. We demonstrate the validity of this approach with competitive results on the Sequential Question Answering (SQA) task (Iyyer et al., 2017). |
| Tasks | Question Answering |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1908.11787v1 |
| https://arxiv.org/pdf/1908.11787v1.pdf | |
| PWC | https://paperswithcode.com/paper/answering-conversational-questions-on |
| Repo | |
| Framework | |
Private Stochastic Convex Optimization with Optimal Rates
| Title | Private Stochastic Convex Optimization with Optimal Rates |
| Authors | Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Thakurta |
| Abstract | We study differentially private (DP) algorithms for stochastic convex optimization (SCO). In this problem the goal is to approximately minimize the population loss given i.i.d. samples from a distribution over convex and Lipschitz loss functions. A long line of existing work on private convex optimization focuses on the empirical loss and derives asymptotically tight bounds on the excess empirical loss. However a significant gap exists in the known bounds for the population loss. We show that, up to logarithmic factors, the optimal excess population loss for DP algorithms is equal to the larger of the optimal non-private excess population loss, and the optimal excess empirical loss of DP algorithms. This implies that, contrary to intuition based on private ERM, private SCO has asymptotically the same rate of $1/\sqrt{n}$ as non-private SCO in the parameter regime most common in practice. The best previous result in this setting gives rate of $1/n^{1/4}$. Our approach builds on existing differentially private algorithms and relies on the analysis of algorithmic stability to ensure generalization. |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.09970v1 |
| https://arxiv.org/pdf/1908.09970v1.pdf | |
| PWC | https://paperswithcode.com/paper/private-stochastic-convex-optimization-with |
| Repo | |
| Framework | |
An Efficient Approach for Cell Segmentation in Phase Contrast Microscopy Images
| Title | An Efficient Approach for Cell Segmentation in Phase Contrast Microscopy Images |
| Authors | Lin Zhang |
| Abstract | In this paper, we propose a new model to segment cells in phase contrast microscopy images. Cell images collected from the similar scenario share a similar background. Inspired by this, we separate cells from the background in images by formulating the problem as a low-rank and structured sparse matrix decomposition problem. Then, we propose the inverse diffraction pattern filtering method to further segment individual cells in the images. This is a deconvolution process that has a much lower computational complexity when compared to the other restoration methods. Experiments demonstrate the effectiveness of the proposed model when it is compared with recent works. |
| Tasks | Cell Segmentation |
| Published | 2019-03-31 |
| URL | http://arxiv.org/abs/1904.00328v1 |
| http://arxiv.org/pdf/1904.00328v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-approach-for-cell-segmentation |
| Repo | |
| Framework | |
Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing
| Title | Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing |
| Authors | Yuta Koreeda, Gaku Morio, Terufumi Morishita, Hiroaki Ozaki, Kohsuke Yanai |
| Abstract | This paper describes the proposed system of the Hitachi team for the Cross-Framework Meaning Representation Parsing (MRP 2019) shared task. In this shared task, the participating systems were asked to predict nodes, edges and their attributes for five frameworks, each with different order of “abstraction” from input tokens. We proposed a unified encoder-to-biaffine network for all five frameworks, which effectively incorporates a shared encoder to extract rich input features, decoder networks to generate anchorless nodes in UCCA and AMR, and biaffine networks to predict edges. Our system was ranked fifth with the macro-averaged MRP F1 score of 0.7604, and outperformed the baseline unified transition-based MRP. Furthermore, post-evaluation experiments showed that we can boost the performance of the proposed system by incorporating multi-task learning, whereas the baseline could not. These imply efficacy of incorporating the biaffine network to the shared architecture for MRP and that learning heterogeneous meaning representations at once can boost the system performance. |
| Tasks | Multi-Task Learning |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.01299v3 |
| https://arxiv.org/pdf/1910.01299v3.pdf | |
| PWC | https://paperswithcode.com/paper/hitachi-at-mrp-2019-unified-encoder-to |
| Repo | |
| Framework | |
Framelet Pooling Aided Deep Learning Network : The Method to Process High Dimensional Medical Data
| Title | Framelet Pooling Aided Deep Learning Network : The Method to Process High Dimensional Medical Data |
| Authors | Chang Min Hyun, Kang Cheol Kim, Hyun Cheol Cho, Jae Kyu Cho, Jin Keun Seo |
| Abstract | Machine learning-based analysis of medical images often faces several hurdles, such as the lack of training data, the curse of dimensionality problem, and the generalization issues. One of the main difficulties is that there exists computational cost problem in dealing with input data of large size matrices which represent medical images. The purpose of this paper is to introduce a framelet-pooling aided deep learning method for mitigating computational bundle, caused by large dimensionality. By transforming high dimensional data into low dimensional components by filter banks with preserving detailed information, the proposed method aims to reduce the complexity of the neural network and computational costs significantly during the learning process. Various experiments show that our method is comparable to the standard unreduced learning method, while reducing computational burdens by decomposing large-sized learning tasks into several small-scale learning tasks. |
| Tasks | |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.10834v1 |
| https://arxiv.org/pdf/1907.10834v1.pdf | |
| PWC | https://paperswithcode.com/paper/framelet-pooling-aided-deep-learning-network |
| Repo | |
| Framework | |
MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension
| Title | MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension |
| Authors | Di Jin, Shuyang Gao, Jiun-Yu Kao, Tagyoung Chung, Dilek Hakkani-tur |
| Abstract | Machine Reading Comprehension (MRC) for question answering (QA), which aims to answer a question given the relevant context passages, is an important way to test the ability of intelligence systems to understand human language. Multiple-Choice QA (MCQA) is one of the most difficult tasks in MRC because it often requires more advanced reading comprehension skills such as logical reasoning, summarization, and arithmetic operations, compared to the extractive counterpart where answers are usually spans of text within given passages. Moreover, most existing MCQA datasets are small in size, making the learning task even harder. We introduce MMM, a Multi-stage Multi-task learning framework for Multi-choice reading comprehension. Our method involves two sequential stages: coarse-tuning stage using out-of-domain datasets and multi-task learning stage using a larger in-domain dataset to help model generalize better with limited data. Furthermore, we propose a novel multi-step attention network (MAN) as the top-level classifier for this task. We demonstrate MMM significantly advances the state-of-the-art on four representative MCQA datasets. |
| Tasks | Machine Reading Comprehension, Multi-Task Learning, Question Answering, Reading Comprehension |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00458v2 |
| https://arxiv.org/pdf/1910.00458v2.pdf | |
| PWC | https://paperswithcode.com/paper/mmm-multi-stage-multi-task-learning-for-multi |
| Repo | |
| Framework | |
Shear Stress Distribution Prediction in Symmetric Compound Channels Using Data Mining and Machine Learning Models
| Title | Shear Stress Distribution Prediction in Symmetric Compound Channels Using Data Mining and Machine Learning Models |
| Authors | Zohreh Sheikh Khozani, Khabat Khosravi, Mohammadamin Torabi, Amir Mosavi, Bahram Rezaei, Timon Rabczuk |
| Abstract | Shear stress distribution prediction in open channels is of utmost importance in hydraulic structural engineering as it directly affects the design of stable channels. In this study, at first, a series of experimental tests were conducted to assess the shear stress distribution in prismatic compound channels. The shear stress values around the whole wetted perimeter were measured in the compound channel with different floodplain widths also in different flow depths in subcritical and supercritical conditions. A set of, data mining and machine learning models including Random Forest (RF), M5P, Random Committee (RC), KStar and Additive Regression Model (AR) implemented on attained data to predict the shear stress distribution in the compound channel. Results indicated among these five models, RF method indicated the most precise results with the highest R2 value of 0.9. Finally, the most powerful data mining method which studied in this research (RF) compared with two well-known analytical models of Shiono and Knight Method (SKM) and Shannon method to acquire the proposed model functioning in predicting the shear stress distribution. The results showed that the RF model has the best prediction performance compared to SKM and Shannon models. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/2001.01558v1 |
| https://arxiv.org/pdf/2001.01558v1.pdf | |
| PWC | https://paperswithcode.com/paper/shear-stress-distribution-prediction-in |
| Repo | |
| Framework | |
Topical Keyphrase Extraction with Hierarchical Semantic Networks
| Title | Topical Keyphrase Extraction with Hierarchical Semantic Networks |
| Authors | Yoo yeon Sung, Seoung Bum Kim |
| Abstract | Topical keyphrase extraction is used to summarize large collections of text documents. However, traditional methods cannot properly reflect the intrinsic semantics and relationships of keyphrases because they rely on a simple term-frequency-based process. Consequently, these methods are not effective in obtaining significant contextual knowledge. To resolve this, we propose a topical keyphrase extraction method based on a hierarchical semantic network and multiple centrality network measures that together reflect the hierarchical semantics of keyphrases. We conduct experiments on real data to examine the practicality of the proposed method and to compare its performance with that of existing topical keyphrase extraction methods. The results confirm that the proposed method outperforms state-of-the-art topical keyphrase extraction methods in terms of the representativeness of the selected keyphrases for each topic. The proposed method can effectively reflect intrinsic keyphrase semantics and interrelationships. |
| Tasks | |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.07848v1 |
| https://arxiv.org/pdf/1910.07848v1.pdf | |
| PWC | https://paperswithcode.com/paper/topical-keyphrase-extraction-with |
| Repo | |
| Framework | |
Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection
| Title | Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection |
| Authors | Xiaoyi Gu, Leman Akoglu, Alessandro Rinaldo |
| Abstract | Nearest-neighbor (NN) procedures are well studied and widely used in both supervised and unsupervised learning problems. In this paper we are concerned with investigating the performance of NN-based methods for anomaly detection. We first show through extensive simulations that NN methods compare favorably to some of the other state-of-the-art algorithms for anomaly detection based on a set of benchmark synthetic datasets. We further consider the performance of NN methods on real datasets, and relate it to the dimensionality of the problem. Next, we analyze the theoretical properties of NN-methods for anomaly detection by studying a more general quantity called distance-to-measure (DTM), originally developed in the literature on robust geometric and topological inference. We provide finite-sample uniform guarantees for the empirical DTM and use them to derive misclassification rates for anomalous observations under various settings. In our analysis we rely on Huber’s contamination model and formulate mild geometric regularity assumptions on the underlying distribution of the data. |
| Tasks | Anomaly Detection |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.03813v1 |
| https://arxiv.org/pdf/1907.03813v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-analysis-of-nearest-neighbor |
| Repo | |
| Framework | |
