January 25, 2020

3322 words 16 mins read

Paper Group ANR 1704

A Research and Strategy of Remote Sensing Image Denoising Algorithms. Benchmarking Discrete Optimization Heuristics with IOHprofiler. Community Detection for Power Systems Network Aggregation Considering Renewable Variability. Early Prediction of Sepsis From Clinical Datavia Heterogeneous Event Aggregation. Global optimization via inverse distance …

A Research and Strategy of Remote Sensing Image Denoising Algorithms


Title	A Research and Strategy of Remote Sensing Image Denoising Algorithms
Authors	Ling Li, Junxing Hu, Fengge Wu, Junsuo Zhao
Abstract	Most raw data download from satellites are useless, resulting in transmission waste, one solution is to process data directly on satellites, then only transmit the processed results to the ground. Image processing is the main data processing on satellites, in this paper, we focus on image denoising which is the basic image processing. There are many high-performance denoising approaches at present, however, most of them rely on advanced computing resources or rich images on the ground. Considering the limited computing resources of satellites and the characteristics of remote sensing images, we do some research on these high-performance ground image denoising approaches and compare them in simulation experiments to analyze whether they are suitable for satellites. According to the analysis results, we propose two feasible image denoising strategies for satellites based on satellite TianZhi-1.
Tasks	Denoising, Image Denoising
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10236v1
PDF	https://arxiv.org/pdf/1905.10236v1.pdf
PWC	https://paperswithcode.com/paper/a-research-and-strategy-of-remote-sensing
Repo
Framework

Benchmarking Discrete Optimization Heuristics with IOHprofiler


Title	Benchmarking Discrete Optimization Heuristics with IOHprofiler
Authors	Carola Doerr, Furong Ye, Naama Horesh, Hao Wang, Ofer M. Shir, Thomas Bäck
Abstract	Automated benchmarking environments aim to support researchers in understanding how different algorithms perform on different types of optimization problems. Such comparisons provide insights into the strengths and weaknesses of different approaches, which can be leveraged into designing new algorithms and into the automation of algorithm selection and configuration. With the ultimate goal to create a meaningful benchmark set for iterative optimization heuristics, we have recently released IOHprofiler, a software built to create detailed performance comparisons between iterative optimization heuristics. With this present work we demonstrate that IOHprofiler provides a suitable environment for automated benchmarking. We compile and assess a selection of 23 discrete optimization problems that subscribe to different types of fitness landscapes. For each selected problem we compare performances of twelve different heuristics, which are as of now available as baseline algorithms in IOHprofiler. We also provide a new module for IOHprofiler which extents the fixed-target and fixed-budget results for the individual problems by ECDF results, which allows one to derive aggregated performance statistics for groups of problems.
Tasks
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09237v1
PDF	https://arxiv.org/pdf/1912.09237v1.pdf
PWC	https://paperswithcode.com/paper/benchmarking-discrete-optimization-heuristics
Repo
Framework

Community Detection for Power Systems Network Aggregation Considering Renewable Variability


Title	Community Detection for Power Systems Network Aggregation Considering Renewable Variability
Authors	Raphael Araujo Sampaio, Gerson Couto Oliveira, Luiz Carlos da Costa Jr., Joaquim Dias Garcia
Abstract	The increasing penetration of variable renewable energy (VRE) has brought significant challenges for power systems planning and operation. These highly variable sources are typically distributed in the grid; therefore, a detailed representation of transmission bottlenecks is fundamental to approximate the impact of the transmission network on the dispatch with VRE resources. The fine grain temporal scale of short term and day-ahead dispatch, taking into account the network constraints, also mandatory for mid-term planning studies, combined with the high variability of the VRE has brought the need to represent these uncertainties in stochastic optimization models while taking into account the transmission system. These requirements impose a computational burden to solve the planning and operation models. We propose a methodology based on community detection to aggregate the network representation, capable of preserving the locational marginal price (LMP) differences in multiple VRE scenarios, and describe a real-world operational planning study. The optimal expected cost solution considering aggregated networks is compared with the full network representation. Both representations were embedded in an operation model relying on Stochastic Dual Dynamic Programming (SDDP) to deal with the random variables in a multi-stage problem.
Tasks	Community Detection, Stochastic Optimization
Published	2019-11-08
URL	https://arxiv.org/abs/1911.04279v1
PDF	https://arxiv.org/pdf/1911.04279v1.pdf
PWC	https://paperswithcode.com/paper/community-detection-for-power-systems-network
Repo
Framework

Early Prediction of Sepsis From Clinical Datavia Heterogeneous Event Aggregation


Title	Early Prediction of Sepsis From Clinical Datavia Heterogeneous Event Aggregation
Authors	Luchen Liu, Haoxian Wu, Zichang Wang, Zequn Liu, Ming Zhang
Abstract	Sepsis is a life-threatening condition that seriously endangers millions of people over the world. Hopefully, with the widespread availability of electronic health records (EHR), predictive models that can effectively deal with clinical sequential data increase the possibility to predict sepsis and take early preventive treatment. However, the early prediction is challenging because patients’ sequential data in EHR contains temporal interactions of multiple clinical events. And capturing temporal interactions in the long event sequence is hard for traditional LSTM. Rather than directly applying the LSTM model to the event sequences, our proposed model firstly aggregates heterogeneous clinical events in a short period and then captures temporal interactions of the aggregated representations with LSTM. Our proposed Heterogeneous Event Aggregation can not only shorten the length of clinical event sequence but also help to retain temporal interactions of both categorical and numerical features of clinical events in the multiple heads of the aggregation representations. In the PhysioNet/Computing in Cardiology Challenge 2019, with the team named PKU_DLIB, our proposed model, in high efficiency, achieved utility score (0.321) in the full test set.
Tasks
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06792v1
PDF	https://arxiv.org/pdf/1910.06792v1.pdf
PWC	https://paperswithcode.com/paper/early-prediction-of-sepsis-from-clinical
Repo
Framework

Global optimization via inverse distance weighting and radial basis functions


Title	Global optimization via inverse distance weighting and radial basis functions
Authors	Alberto Bemporad
Abstract	Global optimization problems whose objective function is expensive to evaluate can be solved effectively by recursively fitting a surrogate function to function samples and minimizing an acquisition function to generate new samples. The acquisition step trades off between seeking for a new optimization vector where the surrogate is minimum (exploitation of the surrogate) and looking for regions of the feasible space that have not yet been visited and that may potentially contain better values of the objective function (exploration of the feasible space). This paper proposes a new global optimization algorithm that uses a combination of inverse distance weighting (IDW) and radial basis functions (RBF) to construct the acquisition function. Rather arbitrary constraints that are simple to evaluate can be easily taken into account. Compared to Bayesian optimization, the proposed algorithm, that we call GLIS (GLobal minimum using Inverse distance weighting and Surrogate radial basis functions), is competitive and computationally lighter, as we show in a set of benchmark global optimization and hyperparameter tuning problems. MATLAB and Python implementations of GLIS are available at \url{http://cse.lab.imtlucca.it/~bemporad/glis}.
Tasks
Published	2019-06-15
URL	https://arxiv.org/abs/1906.06498v2
PDF	https://arxiv.org/pdf/1906.06498v2.pdf
PWC	https://paperswithcode.com/paper/global-optimization-via-inverse-distance
Repo
Framework

Haar Graph Pooling


Title	Haar Graph Pooling
Authors	Yu Guang Wang, Ming Li, Zheng Ma, Guido Montufar, Xiaosheng Zhuang, Yanan Fan
Abstract	Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is a critical ingredient by which GNNs adapt to input graphs of varying size and structure. We propose a new graph pooling operation based on compressive Haar transforms — \emph{HaarPooling}. HaarPooling implements a cascade of pooling operations; it is computed by following a sequence of clusterings of the input graph. A HaarPooling layer transforms a given input graph to an output graph with a smaller node number and the same feature dimension; the compressive Haar transform filters out fine detail information in the Haar wavelet domain. In this way, all the HaarPooling layers together synthesize the features of any given input graph into a feature vector of uniform size. Such transforms provide a sparse characterization of the data and preserve the structure information of the input graph. GNNs implemented with standard graph convolution layers and HaarPooling layers achieve state of the art performance on diverse graph classification and regression problems.
Tasks	Graph Classification
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11580v2
PDF	https://arxiv.org/pdf/1909.11580v2.pdf
PWC	https://paperswithcode.com/paper/haarpooling-graph-pooling-with-compressive
Repo
Framework

Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview


Title	Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview
Authors	Jiawei Zhang
Abstract	Graph neural networks denote a group of neural network models introduced for the representation learning tasks on graph data specifically. Graph neural networks have been demonstrated to be effective for capturing network structure information, and the learned representations can achieve the state-of-the-art performance on node and graph classification tasks. Besides the different application scenarios, the architectures of graph neural network models also depend on the studied graph types a lot. Graph data studied in research can be generally categorized into two main types, i.e., small graphs vs. giant networks, which differ from each other a lot in the size, instance number and label annotation. Several different types of graph neural network models have been introduced for learning the representations from such different types of graphs already. In this paper, for these two different types of graph data, we will introduce the graph neural networks introduced in recent years. To be more specific, the graph neural networks introduced in this paper include IsoNN, SDBN, LF&ER, GCN, GAT, DifNN, GNL, GraphSage and seGEN. Among these graph neural network models, IsoNN, SDBN and LF&ER are initially proposed for small graphs and the remaining ones are initially proposed for giant networks instead. The readers are also suggested to refer to these papers for detailed information when reading this tutorial paper.
Tasks	Graph Classification, Representation Learning
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00187v1
PDF	https://arxiv.org/pdf/1908.00187v1.pdf
PWC	https://paperswithcode.com/paper/graph-neural-networks-for-small-graph-and
Repo
Framework

HyPar: Towards Hybrid Parallelism for Deep Learning Accelerator Array


Title	HyPar: Towards Hybrid Parallelism for Deep Learning Accelerator Array
Authors	Linghao Song, Jiachen Mao, Youwei Zhuo, Xuehai Qian, Hai Li, Yiran Chen
Abstract	With the rise of artificial intelligence in recent years, Deep Neural Networks (DNNs) have been widely used in many domains. To achieve high performance and energy efficiency, hardware acceleration (especially inference) of DNNs is intensively studied both in academia and industry. However, we still face two challenges: large DNN models and datasets, which incur frequent off-chip memory accesses; and the training of DNNs, which is not well-explored in recent accelerator designs. To truly provide high throughput and energy efficient acceleration for the training of deep and large models, we inevitably need to use multiple accelerators to explore the coarse-grain parallelism, compared to the fine-grain parallelism inside a layer considered in most of the existing architectures. It poses the key research question to seek the best organization of computation and dataflow among accelerators. In this paper, inspired by recent work in machine learning systems, we propose a solution HyPar to determine layer-wise parallelism for deep neural network training with an array of DNN accelerators. HyPar partitions the feature map tensors (input and output), the kernel tensors, the gradient tensors, and the error tensors for the DNN accelerators. A partition constitutes the choice of parallelism for weighted layers. The optimization target is to search a partition that minimizes the total communication during training a complete DNN. To solve this problem, we propose a communication model to explain the source and amount of communications. Then, we use a hierarchical layer-wise dynamic programming method to search for the partition for each layer.
Tasks
Published	2019-01-07
URL	https://arxiv.org/abs/1901.02067v2
PDF	https://arxiv.org/pdf/1901.02067v2.pdf
PWC	https://paperswithcode.com/paper/hypar-towards-hybrid-parallelism-for-deep
Repo
Framework

Prostate cancer inference via weakly-supervised learning using a large collection of negative MRI


Title	Prostate cancer inference via weakly-supervised learning using a large collection of negative MRI
Authors	Ruiming Cao, Xinran Zhong, Fabien Scalzo, Steven Raman, Kyung hyun Sung
Abstract	Recent advances in medical imaging techniques have led to significant improvements in the management of prostate cancer (PCa). In particular, multi-parametric MRI (mp-MRI) continues to gain clinical acceptance as the preferred imaging technique for non-invasive detection and grading of PCa. However, the machine learning-based diagnosis systems for PCa are often constrained by the limited access to accurate lesion ground truth annotations for training. The performance of the machine learning system is highly dependable on both quality and quantity of lesion annotations associated with histopathologic findings, resulting in limited scalability and clinical validation. Here, we propose the baseline MRI model to alternatively learn the appearance of mp-MRI using radiology-confirmed negative MRI cases via weakly supervised learning. Since PCa lesions are case-specific and highly heterogeneous, it is assumed to be challenging to synthesize PCa lesions using the baseline MRI model, while it would be relatively easier to synthesize the normal appearance in mp-MRI. We then utilize the baseline MRI model to infer the pixel-wise suspiciousness of PCa by comparing the original and synthesized MRI with two distance functions. We trained and validated the baseline MRI model using 1,145 negative prostate mp-MRI scans. For evaluation, we used separated 232 mp-MRI scans, consisting of both positive and negative MRI cases. The 116 positive MRI scans were annotated by radiologists, confirmed with post-surgical whole-gland specimens. The suspiciousness map was evaluated by receiver operating characteristic (ROC) analysis for PCa lesions versus non-PCa regions classification and free-response receiver operating characteristic (FROC) analysis for PCa localization. Our proposed method achieved 0.84 area under the ROC curve and 77.0% sensitivity at one false positive per patient in FROC analysis.
Tasks
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02185v1
PDF	https://arxiv.org/pdf/1910.02185v1.pdf
PWC	https://paperswithcode.com/paper/prostate-cancer-inference-via-weakly
Repo
Framework

Learned Variable-Rate Image Compression with Residual Divisive Normalization


Title	Learned Variable-Rate Image Compression with Residual Divisive Normalization
Authors	Mohammad Akbari, Jie Liang, Jingning Han, Chengjie Tu
Abstract	Recently it has been shown that deep learning-based image compression has shown the potential to outperform traditional codecs. However, most existing methods train multiple networks for multiple bit rates, which increases the implementation complexity. In this paper, we propose a variable-rate image compression framework, which employs more Generalized Divisive Normalization (GDN) layers than previous GDN-based methods. Novel GDN-based residual sub-networks are also developed in the encoder and decoder networks. Our scheme also uses a stochastic rounding-based scalable quantization. To further improve the performance, we encode the residual between the input and the reconstructed image from the decoder network as an enhancement layer. To enable a single model to operate with different bit rates and to learn multi-rate image features, a new objective function is introduced. Experimental results show that the proposed framework trained with variable-rate objective function outperforms all standard codecs such as H.265/HEVC-based BPG and state-of-the-art learning-based variable-rate methods.
Tasks	Image Compression, Quantization
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05688v1
PDF	https://arxiv.org/pdf/1912.05688v1.pdf
PWC	https://paperswithcode.com/paper/learned-variable-rate-image-compression-with
Repo
Framework

Discovering a sparse set of pairwise discriminating features in high dimensional data


Title	Discovering a sparse set of pairwise discriminating features in high dimensional data
Authors	Samuel Melton, Sharad Ramanathan
Abstract	Extracting an understanding of the underlying system from high dimensional data is a growing problem in science. Discovering informative and meaningful features is crucial for clustering, classification, and low dimensional data embedding. Here we propose to construct features based on their ability to discriminate between clusters of the data points. We define a class of problems in which linear separability of clusters is hidden in a low dimensional space. We propose an unsupervised method to identify the subset of features that define a low dimensional subspace in which clustering can be conducted. This is achieved by averaging over discriminators trained on an ensemble of proposed cluster configurations. We then apply our method to single cell RNA-seq data from mouse gastrulation, and identify 27 key transcription factors (out of 409 total), 18 of which are known to define cell states through their expression levels. In this inferred subspace, we find clear signatures of known cell types that eluded classification prior to discovery of the correct low dimensional subspace.
Tasks
Published	2019-10-13
URL	https://arxiv.org/abs/1910.05814v2
PDF	https://arxiv.org/pdf/1910.05814v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-discovery-of-sparse-multimodal
Repo
Framework

Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach


Title	Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach
Authors	Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, In So Kweon
Abstract	Constructing an organized dataset comprised of a large number of images and several captions for each image is a laborious task, which requires vast human effort. On the other hand, collecting a large number of images and sentences separately may be immensely easier. In this paper, we develop a novel data-efficient semi-supervised framework for training an image captioning model. We leverage massive unpaired image and caption data by learning to associate them. To this end, our proposed semi-supervised learning method assigns pseudo-labels to unpaired samples via Generative Adversarial Networks to learn the joint distribution of image and caption. To evaluate, we construct scarcely-paired COCO dataset, a modified version of MS COCO caption dataset. The empirical results show the effectiveness of our method compared to several strong baselines, especially when the amount of the paired samples are scarce.
Tasks	Image Captioning
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02201v2
PDF	https://arxiv.org/pdf/1909.02201v2.pdf
PWC	https://paperswithcode.com/paper/image-captioning-with-very-scarce-supervised
Repo
Framework

Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling


Title	Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling
Authors	Peidong Wang, Ke Tan, DeLiang Wang
Abstract	Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it directly to automatic speech recognition (ASR) systems trained with noisy speech has not produced expected improvements in ASR performance. The lack of an enhancement benefit on recognition, or the gap between monaural speech enhancement and recognition, is often attributed to speech distortions introduced in the enhancement process. In this study, we analyze the distortion problem, compare different acoustic models, and investigate a distortion-independent training scheme for monaural speech recognition. Experimental results suggest that distortion-independent acoustic modeling is able to overcome the distortion problem. Such an acoustic model can also work with speech enhancement models different from the one used during training. Moreover, the models investigated in this paper outperform the previous best system on the CHiME-2 corpus.
Tasks	Speech Enhancement, Speech Recognition
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04567v2
PDF	http://arxiv.org/pdf/1903.04567v2.pdf
PWC	https://paperswithcode.com/paper/bridging-the-gap-between-monaural-speech
Repo
Framework

Knowledge compilation languages as proof systems


Title	Knowledge compilation languages as proof systems
Authors	Florent Capelli
Abstract	In this paper, we study proof systems in the sense of Cook-Reckhow for problems that are higher in the polynomial hierarchy than coNP, in particular, #SAT and maxSAT. We start by explaining how the notion of Cook-Reckhow proof systems can be apply to these problems and show how one can twist existing languages in knowledge compilation such as decision DNNF so that they can be seen as proof systems for problems such as #SAT and maxSAT.
Tasks
Published	2019-03-10
URL	http://arxiv.org/abs/1903.04039v1
PDF	http://arxiv.org/pdf/1903.04039v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-compilation-languages-as-proof
Repo
Framework

An Item Recommendation Approach by Fusing Images based on Neural Networks


Title	An Item Recommendation Approach by Fusing Images based on Neural Networks
Authors	Weibin Lin, Lin Li
Abstract	There are rich formats of information in the network, such as rating, text, image, and so on, which represent different aspects of user preferences. In the field of recommendation, how to use those data effectively has become a difficult subject. With the rapid development of neural network, researching on multi-modal method for recommendation has become one of the major directions. In the existing recommender systems, numerical rating, item description and review are main information to be considered by researchers. However, the characteristics of the item may affect the user’s preferences, which are rarely used for recommendation models. In this work, we propose a novel model to incorporate visual factors into predictors of people’s preferences, namely MF-VMLP, based on the recent developments of neural collaborative filtering (NCF). Firstly, we get visual presentation via a pre-trained convolutional neural network (CNN) model. To obtain the nonlinearities interaction of latent vectors and visual vectors, we propose to leverage a multi-layer perceptron (MLP) to learn. Moreover, the combination of MF and MLP has achieved collaborative filtering recommendation between users and items. Our experiments conduct Amazon’s public dataset for experimental validation and root-mean-square error (RMSE) as evaluation metrics. To some extent, experimental result on a real-world data set demonstrates that our model can boost the recommendation performance.
Tasks	Recommendation Systems
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02203v1
PDF	https://arxiv.org/pdf/1907.02203v1.pdf
PWC	https://paperswithcode.com/paper/an-item-recommendation-approach-by-fusing
Repo
Framework