Paper Group ANR 826
Efficiently Embedding Dynamic Knowledge Graphs. Neural Proximal/Trust Region Policy Optimization Attains Globally Optimal Policy. Machine learning topological phases in real space. Small and Practical BERT Models for Sequence Labeling. Generative Model-Based Ischemic Stroke Lesion Segmentation. MG-VAE: Deep Chinese Folk Songs Generation with Specif …
Efficiently Embedding Dynamic Knowledge Graphs
| Title | Efficiently Embedding Dynamic Knowledge Graphs |
| Authors | Tianxing Wu, Arijit Khan, Huan Gao, Cheng Li |
| Abstract | Knowledge graph (KG) embedding encodes the entities and relations from a KG into low-dimensional vector spaces to support various applications such as KG completion, question answering, and recommender systems. In real world, knowledge graphs (KGs) are dynamic and evolve over time with addition or deletion of triples. However, most existing models focus on embedding static KGs while neglecting dynamics. To adapt to the changes in a KG, these models need to be re-trained on the whole KG with a high time cost. In this paper, to tackle the aforementioned problem, we propose a new context-aware Dynamic Knowledge Graph Embedding (DKGE) method which supports the embedding learning in an online fashion. DKGE introduces two different representations (i.e., knowledge embedding and contextual element embedding) for each entity and each relation, in the joint modeling of entities and relations as well as their contexts, by employing two attentive graph convolutional networks, a gate strategy, and translation operations. This effectively helps limit the impacts of a KG update in certain regions, not in the entire graph, so that DKGE can rapidly acquire the updated KG embedding by a proposed online learning algorithm. Furthermore, DKGE can also learn KG embedding from scratch. Experiments on the tasks of link prediction and question answering in a dynamic environment demonstrate the effectiveness and efficiency of DKGE. |
| Tasks | Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs, Link Prediction, Question Answering, Recommendation Systems |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06708v1 |
| https://arxiv.org/pdf/1910.06708v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficiently-embedding-dynamic-knowledge |
| Repo | |
| Framework | |
Neural Proximal/Trust Region Policy Optimization Attains Globally Optimal Policy
| Title | Neural Proximal/Trust Region Policy Optimization Attains Globally Optimal Policy |
| Authors | Boyi Liu, Qi Cai, Zhuoran Yang, Zhaoran Wang |
| Abstract | Proximal policy optimization and trust region policy optimization (PPO and TRPO) with actor and critic parametrized by neural networks achieve significant empirical success in deep reinforcement learning. However, due to nonconvexity, the global convergence of PPO and TRPO remains less understood, which separates theory from practice. In this paper, we prove that a variant of PPO and TRPO equipped with overparametrized neural networks converges to the globally optimal policy at a sublinear rate. The key to our analysis is the global convergence of infinite-dimensional mirror descent under a notion of one-point monotonicity, where the gradient and iterate are instantiated by neural networks. In particular, the desirable representation power and optimization geometry induced by the overparametrization of such neural networks allow them to accurately approximate the infinite-dimensional gradient and iterate. |
| Tasks | |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10306v2 |
| https://arxiv.org/pdf/1906.10306v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-proximaltrust-region-policy |
| Repo | |
| Framework | |
Machine learning topological phases in real space
| Title | Machine learning topological phases in real space |
| Authors | N. L. Holanda, M. A. R. Griffith |
| Abstract | We develop a supervised machine learning algorithm that is able to learn topological phases for finite condensed matter systems in real lattice space. The algorithm employs diagonalization in real space together with any supervised learning algorithm to learn topological phases through an eigenvector-ensembling procedure. We combine our algorithm with decision trees to successfully recover topological phase diagrams of Su-Schrieffer-Heeger (SSH) models from lattice data in real space and show how the Gini impurity of ensembles of lattice eigenvectors can be used to retrieve a topological signal detailing how topological information is distributed along the lattice. The discovery of local Gini topological signals from the analysis of data from several thousand SSH systems illustrates how machine learning can advance the research and discovery of new quantum materials with exotic properties that may power future technological applications such as quantum computing. |
| Tasks | |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.01963v3 |
| http://arxiv.org/pdf/1901.01963v3.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-topological-phases-in-real |
| Repo | |
| Framework | |
Small and Practical BERT Models for Sequence Labeling
| Title | Small and Practical BERT Models for Sequence Labeling |
| Authors | Henry Tsai, Jason Riesa, Melvin Johnson, Naveen Arivazhagan, Xin Li, Amelia Archer |
| Abstract | We propose a practical scheme to train a single multilingual sequence labeling model that yields state of the art results and is small and fast enough to run on a single CPU. Starting from a public multilingual BERT checkpoint, our final model is 6x smaller and 27x faster, and has higher accuracy than a state-of-the-art multilingual baseline. We show that our model especially outperforms on low-resource languages, and works on codemixed input text without being explicitly trained on codemixed examples. We showcase the effectiveness of our method by reporting on part-of-speech tagging and morphological prediction on 70 treebanks and 48 languages. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2019-08-31 |
| URL | https://arxiv.org/abs/1909.00100v1 |
| https://arxiv.org/pdf/1909.00100v1.pdf | |
| PWC | https://paperswithcode.com/paper/small-and-practical-bert-models-for-sequence |
| Repo | |
| Framework | |
Generative Model-Based Ischemic Stroke Lesion Segmentation
| Title | Generative Model-Based Ischemic Stroke Lesion Segmentation |
| Authors | Tao Song |
| Abstract | CT perfusion (CTP) has been used to triage ischemic stroke patients in the early stage, because of its speed, availability, and lack of contraindications. Perfusion parameters including cerebral blood volume (CBV), cerebral blood flow (CBF), mean transit time (MTT) and time of peak (Tmax) could also be computed from CTP data. However, CTP data or the perfusion parameters, are ambiguous to locate the infarct core or tissue at risk (penumbra), which is normally confirmed by the follow-up Diffusion Weighted Imaging (DWI) or perfusion diffusion mismatch. In this paper, we propose a novel generative modelbased segmentation framework composed of an extractor, a generator and a segmentor for ischemic stroke lesion segmentation. First, an extractor is used to directly extract the representative feature images from the CTP feature images. Second, a generator is used to generate the clinical relevant DWI images using the output from the extractor and perfusion parameters. Finally, the segmentor is used to precisely segment the ischemic stroke lesion using the generated DWI from the generator. Meanwhile, a novel pixel-region loss function, generalized dice combined with weighted cross entropy, is used to handle data unbalance problem which is commonly encountered in medical image segmentation. All networks are trained end-to-end from scratch using the 2018 Ischemic Stroke Lesion Segmentation Challenge (ISLES) dataset and our method won the first place in the 2018 ischemic stroke lesions segmentation challenge in the test stage. |
| Tasks | Ischemic Stroke Lesion Segmentation, Lesion Segmentation, Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02392v1 |
| https://arxiv.org/pdf/1906.02392v1.pdf | |
| PWC | https://paperswithcode.com/paper/190602392 |
| Repo | |
| Framework | |
MG-VAE: Deep Chinese Folk Songs Generation with Specific Regional Style
| Title | MG-VAE: Deep Chinese Folk Songs Generation with Specific Regional Style |
| Authors | Jing Luo, Xinyu Yang, Shulei Ji, Juan Li |
| Abstract | Regional style in Chinese folk songs is a rich treasure that can be used for ethnic music creation and folk culture research. In this paper, we propose MG-VAE, a music generative model based on VAE (Variational Auto-Encoder) that is capable of capturing specific music style and generating novel tunes for Chinese folk songs (Min Ge) in a manipulatable way. Specifically, we disentangle the latent space of VAE into four parts in an adversarial training way to control the information of pitch and rhythm sequence, as well as of music style and content. In detail, two classifiers are used to separate style and content latent space, and temporal supervision is utilized to disentangle the pitch and rhythm sequence. The experimental results show that the disentanglement is successful and our model is able to create novel folk songs with controllable regional styles. To our best knowledge, this is the first study on applying deep generative model and adversarial training for Chinese music generation. |
| Tasks | Music Generation |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13287v1 |
| https://arxiv.org/pdf/1909.13287v1.pdf | |
| PWC | https://paperswithcode.com/paper/mg-vae-deep-chinese-folk-songs-generation |
| Repo | |
| Framework | |
An Unsupervised Feature Learning Approach to Reduce False Alarm Rate in ICUs
| Title | An Unsupervised Feature Learning Approach to Reduce False Alarm Rate in ICUs |
| Authors | Behzad Ghazanfari, Fatemeh Afghah, Kayvan Najarian, Sajad Mousavi, Jonathan Gryak, James Todd |
| Abstract | The high rate of false alarms in intensive care units (ICUs) is one of the top challenges of using medical technology in hospitals. These false alarms are often caused by patients’ movements, detachment of monitoring sensors, or different sources of noise and interference that impact the collected signals from different monitoring devices. In this paper, we propose a novel set of high-level features based on unsupervised feature learning technique in order to effectively capture the characteristics of different arrhythmia in electrocardiogram (ECG) signal and differentiate them from irregularity in signals due to different sources of signal disturbances. This unsupervised feature learning technique, first extracts a set of low-level features from all existing heart cycles of a patient, and then clusters these segments for each individual patient to provide a set of prominent high-level features. The objective of the clustering phase is to enable the classification method to differentiate between the high-level features extracted from normal and abnormal cycles (i.e., either due to arrhythmia or different sources of distortions in signal) in order to put more attention to the features extracted from abnormal portion of the signal that contribute to the alarm. The performance of this method is evaluated using the 2015 PhysioNet/Computing in Cardiology Challenge dataset for reducing false arrhythmia alarms in the ICUs. As confirmed by the experimental results, the proposed method offers a considerable performance in terms of accuracy, sensitivity and specificity of alarm detection only using a few high-level features that are extracted from one single lead ECG signal. |
| Tasks | |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08495v1 |
| http://arxiv.org/pdf/1904.08495v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-unsupervised-feature-learning-approach-to-1 |
| Repo | |
| Framework | |
Competitive Algorithms for Online Budget-Constrained Continuous DR-Submodular Problems
| Title | Competitive Algorithms for Online Budget-Constrained Continuous DR-Submodular Problems |
| Authors | Omid Sadeghi, Reza Eghbali, Maryam Fazel |
| Abstract | In this paper, we study a certain class of online optimization problems, where the goal is to maximize a function that is not necessarily concave and satisfies the Diminishing Returns (DR) property under budget constraints. We analyze a primal-dual algorithm, called the Generalized Sequential algorithm, and we obtain the first bound on the competitive ratio of online monotone DR-submodular function maximization subject to linear packing constraints which matches the known tight bound in the special case of linear objective function. |
| Tasks | |
| Published | 2019-06-30 |
| URL | https://arxiv.org/abs/1907.00312v1 |
| https://arxiv.org/pdf/1907.00312v1.pdf | |
| PWC | https://paperswithcode.com/paper/competitive-algorithms-for-online-budget |
| Repo | |
| Framework | |
CT-To-MR Conditional Generative Adversarial Networks for Ischemic Stroke Lesion Segmentation
| Title | CT-To-MR Conditional Generative Adversarial Networks for Ischemic Stroke Lesion Segmentation |
| Authors | Jonathan Rubin, S. Mazdak Abulnaga |
| Abstract | Infarcted brain tissue resulting from acute stroke readily shows up as hyperintense regions within diffusion-weighted magnetic resonance imaging (DWI). It has also been proposed that computed tomography perfusion (CTP) could alternatively be used to triage stroke patients, given improvements in speed and availability, as well as reduced cost. However, CTP has a lower signal to noise ratio compared to MR. In this work, we investigate whether a conditional mapping can be learned by a generative adversarial network to map CTP inputs to generated MR DWI that more clearly delineates hyperintense regions due to ischemic stroke. We detail the architectures of the generator and discriminator and describe the training process used to perform image-to-image translation from multi-modal CT perfusion maps to diffusion weighted MR outputs. We evaluate the results both qualitatively by visual comparison of generated MR to ground truth, as well as quantitatively by training fully convolutional neural networks that make use of generated MR data inputs to perform ischemic stroke lesion segmentation. Segmentation networks trained using generated CT-to-MR inputs result in at least some improvement on all metrics used for evaluation, compared with networks that only use CT perfusion input. |
| Tasks | Image-to-Image Translation, Ischemic Stroke Lesion Segmentation, Lesion Segmentation |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1904.13281v1 |
| http://arxiv.org/pdf/1904.13281v1.pdf | |
| PWC | https://paperswithcode.com/paper/ct-to-mr-conditional-generative-adversarial |
| Repo | |
| Framework | |
Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint
| Title | Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint |
| Authors | Kaixu Huang, Fanman Meng, Hongliang Li, Shuai Chen, Qingbo Wu, King N. Ngan |
| Abstract | Class activation map (CAM) highlights regions of classes based on classification network, which is widely used in weakly supervised tasks. However, it faces the problem that the class activation regions are usually small and local. Although several efforts paid to the second step (the CAM generation step) have partially enhanced the generation, we believe such problem is also caused by the first step (training step), because single classification model trained on the entire classes contains finite discriminate information that limits the object region extraction. To this end, this paper solves CAM generation by using multiple classification models. To form multiple classification networks that carry different discriminative information, we try to capture the semantic relationships between classes to form different semantic levels of classification models. Specifically, hierarchical clustering based on class relationships is used to form hierarchical clustering results, where the clustering levels are treated as semantic levels to form the classification models. Moreover, a new orthogonal module and a two-branch based CAM generation method are proposed to generate class regions that are orthogonal and complementary. We use the PASCAL VOC 2012 dataset to verify the proposed method. Experimental results show that our approach improves the CAM generation. |
| Tasks | |
| Published | 2019-09-21 |
| URL | https://arxiv.org/abs/1909.09839v1 |
| https://arxiv.org/pdf/1909.09839v1.pdf | |
| PWC | https://paperswithcode.com/paper/190909839 |
| Repo | |
| Framework | |
A Geometric Approach to Obtain a Bird’s Eye View from an Image
| Title | A Geometric Approach to Obtain a Bird’s Eye View from an Image |
| Authors | Ammar Abbas, Andrew Zisserman |
| Abstract | The objective of this paper is to rectify any monocular image by computing a homography matrix that transforms it to a bird’s eye (overhead) view. We make the following contributions: (i) we show that the homography matrix can be parameterised with only four parameters that specify the horizon line and the vertical vanishing point, or only two if the field of view or focal length is known; (ii) We introduce a novel representation for the geometry of a line or point (which can be at infinity) that is suitable for regression with a convolutional neural network (CNN); (iii) We introduce a large synthetic image dataset with ground truth for the orthogonal vanishing points, that can be used for training a CNN to predict these geometric entities; and finally (iv) We achieve state-of-the-art results on horizon detection, with 74.52% AUC on the Horizon Lines in the Wild dataset. Our method is fast and robust, and can be used to remove perspective distortion from videos in real time. |
| Tasks | |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02231v1 |
| https://arxiv.org/pdf/1905.02231v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-geometric-approach-to-obtain-a-birds-eye |
| Repo | |
| Framework | |
DiamondGAN: Unified Multi-Modal Generative Adversarial Networks for MRI Sequences Synthesis
| Title | DiamondGAN: Unified Multi-Modal Generative Adversarial Networks for MRI Sequences Synthesis |
| Authors | Hongwei Li, Johannes C. Paetzold, Anjany Sekuboyina, Florian Kofler, Jianguo Zhang, Jan S. Kirschke, Benedikt Wiestler, Bjoern Menze |
| Abstract | Synthesizing MR imaging sequences is highly relevant in clinical practice, as single sequences are often missing or are of poor quality (e.g. due to motion). Naturally, the idea arises that a target modality would benefit from multi-modal input, as proprietary information of individual modalities can be synergistic. However, existing methods fail to scale up to multiple non-aligned imaging modalities, facing common drawbacks of complex imaging sequences. We propose a novel, scalable and multi-modal approach called DiamondGAN. Our model is capable of performing exible non-aligned cross-modality synthesis and data infill, when given multiple modalities or any of their arbitrary subsets, learning structured information in an end-to-end fashion. We synthesize two MRI sequences with clinical relevance (i.e., double inversion recovery (DIR) and contrast-enhanced T1 (T1-c)), reconstructed from three common sequences. In addition, we perform a multi-rater visual evaluation experiment and find that trained radiologists are unable to distinguish synthetic DIR images from real ones. |
| Tasks | Image Generation |
| Published | 2019-04-29 |
| URL | https://arxiv.org/abs/1904.12894v4 |
| https://arxiv.org/pdf/1904.12894v4.pdf | |
| PWC | https://paperswithcode.com/paper/diamondgan-unified-multi-modal-generative |
| Repo | |
| Framework | |
A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks
| Title | A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks |
| Authors | Dong Wang, Lei Zhou, Xiao Bai, Jun Zhou |
| Abstract | Acceleration of convolutional neural network has received increasing attention during the past several years. Among various acceleration techniques, filter pruning has its inherent merit by effectively reducing the number of convolution filters. However, most filter pruning methods resort to tedious and time-consuming layer-by-layer pruning-recovery strategy to avoid a significant drop of accuracy. In this paper, we present an efficient filter pruning framework to solve this problem. Our method accelerates the network in one-step pruning-recovery manner with a novel optimization objective function, which achieves higher accuracy with much less cost compared with existing pruning methods. Furthermore, our method allows network compression with global filter pruning. Given a global pruning rate, it can adaptively determine the pruning rate for each single convolutional layer, while these rates are often set as hyper-parameters in previous approaches. Evaluated on VGG-16 and ResNet-50 using ImageNet, our approach outperforms several state-of-the-art methods with less accuracy drop under the same and even much fewer floating-point operations (FLOPs). |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07488v1 |
| https://arxiv.org/pdf/1906.07488v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-one-step-pruning-recovery-framework-for |
| Repo | |
| Framework | |
Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks
| Title | Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks |
| Authors | Tieyun Qian, Yile Liang, Qing Li |
| Abstract | Matrix completion is a classic problem underlying recommender systems. It is traditionally tackled with matrix factorization. Recently, deep learning based methods, especially graph neural networks, have made impressive progress on this problem. Despite their effectiveness, existing methods focus on modeling the user-item interaction graph. The inherent drawback of such methods is that their performance is bound to the density of the interactions, which is however usually of high sparsity. More importantly, for a cold start user/item that does not have any interactions, such methods are unable to learn the preference embedding of the user/item since there is no link to this user/item in the graph. In this work, we develop a novel framework Attribute Graph Neural Networks (AGNN) by exploiting the attribute graph rather than the commonly used interaction graph. This leads to the capability of learning embeddings for cold start users/items. Our AGNN can produce the preference embedding for a cold user/item by learning on the distribution of attributes with an extended variational auto-encoder structure. Moreover, we propose a new graph neural network variant, i.e., gated-GNN, to effectively aggregate various attributes of different modalities in a neighborhood. Empirical results on two real-world datasets demonstrate that our model yields significant improvements for cold start recommendations and outperforms or matches state-of-the-arts performance in the warm start scenario. |
| Tasks | Matrix Completion, Recommendation Systems |
| Published | 2019-12-28 |
| URL | https://arxiv.org/abs/1912.12398v2 |
| https://arxiv.org/pdf/1912.12398v2.pdf | |
| PWC | https://paperswithcode.com/paper/solving-cold-start-problem-in-recommendation |
| Repo | |
| Framework | |
Edge Contraction Pooling for Graph Neural Networks
| Title | Edge Contraction Pooling for Graph Neural Networks |
| Authors | Frederik Diehl |
| Abstract | Graph Neural Network (GNN) research has concentrated on improving convolutional layers, with little attention paid to developing graph pooling layers. Yet pooling layers can enable GNNs to reason over abstracted groups of nodes instead of single nodes. To close this gap, we propose a graph pooling layer relying on the notion of edge contraction: EdgePool learns a localized and sparse hard pooling transform. We show that EdgePool outperforms alternative pooling methods, can be easily integrated into most GNN models, and improves performance on both node and graph classification. |
| Tasks | Graph Classification |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.10990v1 |
| https://arxiv.org/pdf/1905.10990v1.pdf | |
| PWC | https://paperswithcode.com/paper/edge-contraction-pooling-for-graph-neural |
| Repo | |
| Framework | |
