January 31, 2020

3154 words 15 mins read

Paper Group AWR 423

Paper Group AWR 423

Quantifying Similarity between Relations with Fact Distribution. MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation. BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection. A Literature Study of Embeddings on Source Code. Tropical Cyclone Track Forec …

Quantifying Similarity between Relations with Fact Distribution

Title Quantifying Similarity between Relations with Fact Distribution
Authors Weize Chen, Hao Zhu, Xu Han, Zhiyuan Liu, Maosong Sun
Abstract We introduce a conceptually simple and effective method to quantify the similarity between relations in knowledge bases. Specifically, our approach is based on the divergence between the conditional probability distributions over entity pairs. In this paper, these distributions are parameterized by a very simple neural network. Although computing the exact similarity is in-tractable, we provide a sampling-based method to get a good approximation. We empirically show the outputs of our approach significantly correlate with human judgments. By applying our method to various tasks, we also find that (1) our approach could effectively detect redundant relations extracted by open information extraction (Open IE) models, that (2) even the most competitive models for relational classification still make mistakes among very similar relations, and that (3) our approach could be incorporated into negative sampling and softmax classification to alleviate these mistakes. The source code and experiment details of this paper can be obtained from https://github.com/thunlp/relation-similarity.
Tasks Open Information Extraction
Published 2019-07-21
URL https://arxiv.org/abs/1907.08937v1
PDF https://arxiv.org/pdf/1907.08937v1.pdf
PWC https://paperswithcode.com/paper/quantifying-similarity-between-relations-with
Repo https://github.com/thunlp/relation-similarity
Framework pytorch

MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation

Title MULAN: Multitask Universal Lesion Analysis Network for Joint Lesion Detection, Tagging, and Segmentation
Authors Ke Yan, Youbao Tang, Yifan Peng, Veit Sandfort, Mohammadhadi Bagheri, Zhiyong Lu, Ronald M. Summers
Abstract When reading medical images such as a computed tomography (CT) scan, radiologists generally search across the image to find lesions, characterize and measure them, and then describe them in the radiological report. To automate this process, we propose a multitask universal lesion analysis network (MULAN) for joint detection, tagging, and segmentation of lesions in a variety of body parts, which greatly extends existing work of single-task lesion analysis on specific body parts. MULAN is based on an improved Mask R-CNN framework with three head branches and a 3D feature fusion strategy. It achieves the state-of-the-art accuracy in the detection and tagging tasks on the DeepLesion dataset, which contains 32K lesions in the whole body. We also analyze the relationship between the three tasks and show that tag predictions can improve detection accuracy via a score refinement layer.
Tasks Computed Tomography (CT)
Published 2019-08-12
URL https://arxiv.org/abs/1908.04373v1
PDF https://arxiv.org/pdf/1908.04373v1.pdf
PWC https://paperswithcode.com/paper/mulan-multitask-universal-lesion-analysis
Repo https://github.com/leeh43/MULAN_universal_lesion_analysis
Framework pytorch

BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection

Title BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection
Authors Hedi Ben-younes, Rémi Cadene, Nicolas Thome, Matthieu Cord
Abstract Multimodal representation learning is gaining more and more interest within the deep learning community. While bilinear models provide an interesting framework to find subtle combination of modalities, their number of parameters grows quadratically with the input dimensions, making their practical implementation within classical deep learning pipelines challenging. In this paper, we introduce BLOCK, a new multimodal fusion based on the block-superdiagonal tensor decomposition. It leverages the notion of block-term ranks, which generalizes both concepts of rank and mode ranks for tensors, already used for multimodal fusion. It allows to define new ways for optimizing the tradeoff between the expressiveness and complexity of the fusion model, and is able to represent very fine interactions between modalities while maintaining powerful mono-modal representations. We demonstrate the practical interest of our fusion model by using BLOCK for two challenging tasks: Visual Question Answering (VQA) and Visual Relationship Detection (VRD), where we design end-to-end learnable architectures for representing relevant interactions between modalities. Through extensive experiments, we show that BLOCK compares favorably with respect to state-of-the-art multimodal fusion models for both VQA and VRD tasks. Our code is available at https://github.com/Cadene/block.bootstrap.pytorch.
Tasks Question Answering, Representation Learning, Visual Question Answering
Published 2019-01-31
URL http://arxiv.org/abs/1902.00038v2
PDF http://arxiv.org/pdf/1902.00038v2.pdf
PWC https://paperswithcode.com/paper/block-bilinear-superdiagonal-fusion-for
Repo https://github.com/Cadene/block.bootstrap.pytorch
Framework pytorch

A Literature Study of Embeddings on Source Code

Title A Literature Study of Embeddings on Source Code
Authors Zimin Chen, Martin Monperrus
Abstract Natural language processing has improved tremendously after the success of word embedding techniques such as word2vec. Recently, the same idea has been applied on source code with encouraging results. In this survey, we aim to collect and discuss the usage of word embedding techniques on programs and source code. The articles in this survey have been collected by asking authors of related work and with an extensive search on Google Scholar. Each article is categorized into five categories: 1. embedding of tokens 2. embedding of functions or methods 3. embedding of sequences or sets of method calls 4. embedding of binary code 5. other embeddings. We also provide links to experimental data and show some remarkable visualization of code embeddings. In summary, word embedding has been successfully applied on different granularities of source code. With access to countless open-source repositories, we see a great potential of applying other data-driven natural language processing techniques on source code in the future.
Tasks
Published 2019-04-05
URL http://arxiv.org/abs/1904.03061v1
PDF http://arxiv.org/pdf/1904.03061v1.pdf
PWC https://paperswithcode.com/paper/a-literature-study-of-embeddings-on-source
Repo https://github.com/boyter/cs
Framework tf

Tropical Cyclone Track Forecasting using Fused Deep Learning from Aligned Reanalysis Data

Title Tropical Cyclone Track Forecasting using Fused Deep Learning from Aligned Reanalysis Data
Authors Sophie Giffard-Roisin, Mo Yang, Guillaume Charpiat, Christina Kumler-Bonfanti, Balázs Kégl, Claire Monteleoni
Abstract The forecast of tropical cyclone trajectories is crucial for the protection of people and property. Although forecast dynamical models can provide high-precision short-term forecasts, they are computationally demanding, and current statistical forecasting models have much room for improvement given that the database of past hurricanes is constantly growing. Machine learning methods, that can capture non-linearities and complex relations, have only been scarcely tested for this application. We propose a neural network model fusing past trajectory data and reanalysis atmospheric images (wind and pressure 3D fields). We use a moving frame of reference that follows the storm center for the 24h tracking forecast. The network is trained to estimate the longitude and latitude displacement of tropical cyclones and depressions from a large database from both hemispheres (more than 3000 storms since 1979, sampled at a 6 hour frequency). The advantage of the fused network is demonstrated and a comparison with current forecast models shows that deep learning methods could provide a valuable and complementary prediction. Moreover, our method can give a forecast for a new storm in a few seconds, which is an important asset for real-time forecasts compared to traditional forecasts.
Tasks
Published 2019-10-23
URL https://arxiv.org/abs/1910.10566v2
PDF https://arxiv.org/pdf/1910.10566v2.pdf
PWC https://paperswithcode.com/paper/tropical-cyclone-track-forecasting-using
Repo https://github.com/sophiegif/FusionCNN_hurricanes
Framework pytorch

BioConceptVec: creating and evaluating literature-based biomedical concept embeddings on a large scale

Title BioConceptVec: creating and evaluating literature-based biomedical concept embeddings on a large scale
Authors Qingyu Chen, Kyubum Lee, Shankai Yan, Sun Kim, Chih-Hsuan Wei, Zhiyong Lu
Abstract Capturing the semantics of related biological concepts, such as genes and mutations, is of significant importance to many research tasks in computational biology such as protein-protein interaction detection, gene-drug association prediction, and biomedical literature-based discovery. Here, we propose to leverage state-of-the-art text mining tools and machine learning models to learn the semantics via vector representations (aka. embeddings) of over 400,000 biological concepts mentioned in the entire PubMed abstracts. Our learned embeddings, namely BioConceptVec, can capture related concepts based on their surrounding contextual information in the literature, which is beyond exact term match or co-occurrence-based methods. BioConceptVec has been thoroughly evaluated in multiple bioinformatics tasks consisting of over 25 million instances from nine different biological datasets. The evaluation results demonstrate that BioConceptVec has better performance than existing methods in all tasks. Finally, BioConceptVec is made freely available to the research community and general public via https://github.com/ncbi-nlp/BioConceptVec.
Tasks
Published 2019-12-23
URL https://arxiv.org/abs/1912.10846v1
PDF https://arxiv.org/pdf/1912.10846v1.pdf
PWC https://paperswithcode.com/paper/bioconceptvec-creating-and-evaluating
Repo https://github.com/ncbi-nlp/BioConceptVec
Framework none

Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning

Title Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
Authors Johann Brehmer, Siddharth Mishra-Sharma, Joeri Hermans, Gilles Louppe, Kyle Cranmer
Abstract The subtle and unique imprint of dark matter substructure on extended arcs in strong lensing systems contains a wealth of information about the properties and distribution of dark matter on small scales and, consequently, about the underlying particle physics. However, teasing out this effect poses a significant challenge since the likelihood function for realistic simulations of population-level parameters is intractable. We apply recently-developed simulation-based inference techniques to the problem of substructure inference in galaxy-galaxy strong lenses. By leveraging additional information extracted from the simulator, neural networks are efficiently trained to estimate likelihood ratios associated with population-level parameters characterizing substructure. Through proof-of-principle application to simulated data, we show that these methods can provide an efficient and principled way to simultaneously analyze an ensemble of strong lenses, and can be used to mine the large sample of lensing images deliverable by near-future surveys for signatures of dark matter substructure.
Tasks
Published 2019-09-04
URL https://arxiv.org/abs/1909.02005v2
PDF https://arxiv.org/pdf/1909.02005v2.pdf
PWC https://paperswithcode.com/paper/mining-for-dark-matter-substructure-inferring
Repo https://github.com/smsharma/mining-for-substructure-lens
Framework none

Class-specific residual constraint non-negative representation for pattern classification

Title Class-specific residual constraint non-negative representation for pattern classification
Authors He-Feng Yin, Xiao-Jun Wu
Abstract Representation based classification method (RBCM) remains one of the hottest topics in the community of pattern recognition, and the recently proposed non-negative representation based classification (NRC) achieved impressive recognition results in various classification tasks. However, NRC ignores the relationship between the coding and classification stages. Moreover, there is no regularization term other than the reconstruction error term in the formulation of NRC, which may result in unstable solution leading to misclassification. To overcome these drawbacks of NRC, in this paper, we propose a class-specific residual constraint non-negative representation (CRNR) for pattern classification. CRNR introduces a class-specific residual constraint into the formulation of NRC, which encourages training samples from different classes to competitively represent the test sample. Based on the proposed CRNR, we develop a CRNR based classifier (CRNRC) for pattern classification. Experimental results on several benchmark datasets demonstrate the superiority of CRNRC over conventional RBCM as well as the recently proposed NRC. Moreover, CRNRC works better or comparable to some state-of-the-art deep approaches on diverse challenging pattern classification tasks. The source code of our proposed CRNRC is accessible at https://github.com/yinhefeng/CRNRC.
Tasks
Published 2019-11-22
URL https://arxiv.org/abs/1911.09953v2
PDF https://arxiv.org/pdf/1911.09953v2.pdf
PWC https://paperswithcode.com/paper/class-specific-residual-constraint-non
Repo https://github.com/yinhefeng/CRNRC
Framework none

Evaluating recommender systems for AI-driven data science

Title Evaluating recommender systems for AI-driven data science
Authors William La Cava, Heather Williams, Weixuan Fu, Jason H. Moore
Abstract We present a free and open-source platform to allow researchers to easily apply supervised machine learning to their data. A key component of this system is a recommendation engine that is bootstrapped with machine learning results generated on a repository of open-source datasets. The recommendation system chooses which analyses to run for the user, and allows the user to view analyses, download reproducible code or fitted models, and visualize results via a web browser. The recommender system learns online as results are generated. In this paper we benchmark several recommendation strategies, including collaborative filtering and metalearning approaches, for their ability to learn to select and run optimal algorithm configurations for various datasets as results are generated. We find that a matrix factorization-based recommendation system learns to choose increasingly accurate models from few initial results.
Tasks Recommendation Systems
Published 2019-05-22
URL https://arxiv.org/abs/1905.09205v2
PDF https://arxiv.org/pdf/1905.09205v2.pdf
PWC https://paperswithcode.com/paper/evaluating-recommender-systems-for-ai-driven
Repo https://github.com/EpistasisLab/pennai
Framework none

Spatial Transformer for 3D Point Clouds

Title Spatial Transformer for 3D Point Clouds
Authors Jiayun Wang, Rudrasis Chakraborty, Stella X. Yu
Abstract Deep neural networks can efficiently process the 3D point cloud data. At each layer, the network needs to partition points into multiple local patches, and then learn features from them, in order to understand the geometric information encoded in the 3D point cloud.Previous networks adopt all the same local patches for different layers, as they utilized the same fixed original 3D point coordinates to define local neighborhoods. It is easy to implement but not necessarily optimal. Ideally local patches should be different at different layers so as to adapt to the specific layer for efficient feature learning. One way to achieve this is to learn different transformations of the original point cloud at each layer, and then learn features from local patches defined on transformed coordinates. In this work, we propose a novel approach to learn different non-rigid transformations of the input point cloud for different local neighborhoods at each layer. We propose both linear (affine) and non-linear (projective and deformable) spatial transformer for 3D points. With spatial transformers on theShapeNet part segmentation dataset, the network achieves higher accuracy for all categories, specifically with 8% gain on earphones and rockets. The proposed methods also outperform the state-of-the-art methods in several other point cloud processing tasks(classification, semantic segmentation and detection). Visualizations show that spatial transformers can learn features more efficiently by altering local neighborhoods according to the semantic information of 3D shapes regardless of variations in a category.
Tasks Semantic Segmentation
Published 2019-06-26
URL https://arxiv.org/abs/1906.10887v3
PDF https://arxiv.org/pdf/1906.10887v3.pdf
PWC https://paperswithcode.com/paper/spatial-transformer-for-3d-points
Repo https://github.com/samaonline/spatial-transformer-for-3d-point-clouds
Framework caffe2

Machine Learning Pipelines with Modern Big Data Tools for High Energy Physics

Title Machine Learning Pipelines with Modern Big Data Tools for High Energy Physics
Authors Matteo Migliorini, Riccardo Castellotti, Luca Canali, Marco Zanetti
Abstract The effective utilization at scale of complex machine learning (ML) techniques for HEP use cases poses several technological challenges, most importantly on the actual implementation of dedicated end-to-end data pipelines. A solution to these challenges is presented, which allows training neural network classifiers using solutions from the Big Data and data science ecosystems, integrated with tools, software, and platforms common in the HEP environment. In particular, Apache Spark is exploited for data preparation and feature engineering, running the corresponding (Python) code interactively on Jupyter notebooks. Key integrations and libraries that make Spark capable of ingesting data stored using ROOT format and accessed via the XRootD protocol, are described and discussed. Training of the neural network models, defined using the Keras API, is performed in a distributed fashion on Spark clusters by using BigDL with Analytics Zoo and also by using TensorFlow, notably for distributed training on CPU and using GPUs. The implementation and the results of the distributed training are described in detail in this work.
Tasks Feature Engineering
Published 2019-09-23
URL https://arxiv.org/abs/1909.10389v4
PDF https://arxiv.org/pdf/1909.10389v4.pdf
PWC https://paperswithcode.com/paper/machine-learning-pipelines-with-modern-big
Repo https://github.com/cerndb/SparkDLTrigger
Framework tf

Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks

Title Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks
Authors Marco Schreyer, Timur Sattarov, Christian Schulze, Bernd Reimer, Damian Borth
Abstract The detection of fraud in accounting data is a long-standing challenge in financial statement audits. Nowadays, the majority of applied techniques refer to handcrafted rules derived from known fraud scenarios. While fairly successful, these rules exhibit the drawback that they often fail to generalize beyond known fraud scenarios and fraudsters gradually find ways to circumvent them. In contrast, more advanced approaches inspired by the recent success of deep learning often lack seamless interpretability of the detected results. To overcome this challenge, we propose the application of adversarial autoencoder networks. We demonstrate that such artificial neural networks are capable of learning a semantic meaningful representation of real-world journal entries. The learned representation provides a holistic view on a given set of journal entries and significantly improves the interpretability of detected accounting anomalies. We show that such a representation combined with the networks reconstruction error can be utilized as an unsupervised and highly adaptive anomaly assessment. Experiments on two datasets and initial feedback received by forensic accountants underpinned the effectiveness of the approach.
Tasks
Published 2019-08-02
URL https://arxiv.org/abs/1908.00734v1
PDF https://arxiv.org/pdf/1908.00734v1.pdf
PWC https://paperswithcode.com/paper/detection-of-accounting-anomalies-in-the
Repo https://github.com/GitiHubi/deepAD
Framework pytorch

IPRE: a Dataset for Inter-Personal Relationship Extraction

Title IPRE: a Dataset for Inter-Personal Relationship Extraction
Authors Haitao Wang, Zhengqiu He, Jin Ma, Wenliang Chen, Min Zhang
Abstract Inter-personal relationship is the basis of human society. In order to automatically identify the relations between persons from texts, we need annotated data for training systems. However, there is a lack of a massive amount of such data so far. To address this situation, we introduce IPRE, a new dataset for inter-personal relationship extraction which aims to facilitate information extraction and knowledge graph construction research. In total, IPRE has over 41,000 labeled sentences for 34 types of relations, including about 9,000 sentences annotated by workers. Our data is the first dataset for inter-personal relationship extraction. Additionally, we define three evaluation tasks based on IPRE and provide the baseline systems for further comparison in future work.
Tasks graph construction
Published 2019-07-30
URL https://arxiv.org/abs/1907.12801v2
PDF https://arxiv.org/pdf/1907.12801v2.pdf
PWC https://paperswithcode.com/paper/ipre-a-dataset-for-inter-personal
Repo https://github.com/SUDA-HLT/IPRE
Framework none

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set

Title Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
Authors Yu Deng, Jiaolong Yang, Sicheng Xu, Dong Chen, Yunde Jia, Xin Tong
Abstract Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce. In this paper, we propose a novel deep 3D face reconstruction approach that 1) leverages a robust, hybrid loss function for weakly-supervised learning which takes into account both low-level and perception-level information for supervision, and 2) performs multi-image face reconstruction by exploiting complementary information from different images for shape aggregation. Our method is fast, accurate, and robust to occlusion and large pose. We provide comprehensive experiments on three datasets, systematically comparing our method with fifteen recent methods and demonstrating its state-of-the-art performance.
Tasks 3D Face Reconstruction, Face Reconstruction
Published 2019-03-20
URL http://arxiv.org/abs/1903.08527v1
PDF http://arxiv.org/pdf/1903.08527v1.pdf
PWC https://paperswithcode.com/paper/accurate-3d-face-reconstruction-with-weakly
Repo https://github.com/Microsoft/Deep3DFaceReconstruction
Framework tf

Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions

Title Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
Authors Hansika Hewamalage, Christoph Bergmeir, Kasun Bandara
Abstract Recurrent Neural Networks (RNN) have become competitive forecasting methods, as most notably shown in the winning method of the recent M4 competition. However, established statistical models such as ETS and ARIMA gain their popularity not only from their high accuracy, but they are also suitable for non-expert users as they are robust, efficient, and automatic. In these areas, RNNs have still a long way to go. We present an extensive empirical study and an open-source software framework of existing RNN architectures for forecasting, that allow us to develop guidelines and best practices for their use. For example, we conclude that RNNs are capable of modelling seasonality directly if the series in the dataset possess homogeneous seasonal patterns, otherwise we recommend a deseasonalization step. Comparisons against ETS and ARIMA demonstrate that the implemented (semi-)automatic RNN models are no silver bullets, but they are competitive alternatives in many situations.
Tasks Time Series, Time Series Forecasting
Published 2019-09-02
URL https://arxiv.org/abs/1909.00590v3
PDF https://arxiv.org/pdf/1909.00590v3.pdf
PWC https://paperswithcode.com/paper/recurrent-neural-networks-for-time-series-1
Repo https://github.com/HansikaPH/time-series-forecasting
Framework tf
comments powered by Disqus