Paper Group ANR 693
Modeling polypharmacy side effects with graph convolutional networks. Role of Awareness and Universal Context in a Spiking Conscious Neural Network (SCNN): A New Perspective and Future Directions. Automatic Catchphrase Extraction from Legal Case Documents via Scoring using Deep Neural Networks. Learning Common Representation from RGB and Depth Imag …
Modeling polypharmacy side effects with graph convolutional networks
| Title | Modeling polypharmacy side effects with graph convolutional networks |
| Authors | Marinka Zitnik, Monica Agrawal, Jure Leskovec |
| Abstract | The use of drug combinations, termed polypharmacy, is common to treat patients with complex diseases and co-existing conditions. However, a major consequence of polypharmacy is a much higher risk of adverse side effects for the patient. Polypharmacy side effects emerge because of drug-drug interactions, in which activity of one drug may change if taken with another drug. The knowledge of drug interactions is limited because these complex relationships are rare, and are usually not observed in relatively small clinical testing. Discovering polypharmacy side effects thus remains an important challenge with significant implications for patient mortality. Here, we present Decagon, an approach for modeling polypharmacy side effects. The approach constructs a multimodal graph of protein-protein interactions, drug-protein target interactions, and the polypharmacy side effects, which are represented as drug-drug interactions, where each side effect is an edge of a different type. Decagon is developed specifically to handle such multimodal graphs with a large number of edge types. Our approach develops a new graph convolutional neural network for multirelational link prediction in multimodal networks. Decagon predicts the exact side effect, if any, through which a given drug combination manifests clinically. Decagon accurately predicts polypharmacy side effects, outperforming baselines by up to 69%. We find that it automatically learns representations of side effects indicative of co-occurrence of polypharmacy in patients. Furthermore, Decagon models particularly well side effects with a strong molecular basis, while on predominantly non-molecular side effects, it achieves good performance because of effective sharing of model parameters across edge types. Decagon creates opportunities to use large pharmacogenomic and patient data to flag and prioritize side effects for follow-up analysis. |
| Tasks | Link Prediction |
| Published | 2018-02-02 |
| URL | http://arxiv.org/abs/1802.00543v2 |
| http://arxiv.org/pdf/1802.00543v2.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-polypharmacy-side-effects-with-graph |
| Repo | |
| Framework | |
Role of Awareness and Universal Context in a Spiking Conscious Neural Network (SCNN): A New Perspective and Future Directions
| Title | Role of Awareness and Universal Context in a Spiking Conscious Neural Network (SCNN): A New Perspective and Future Directions |
| Authors | Ahsan Adeel |
| Abstract | Awareness plays a major role in human cognition and adaptive behaviour, though mechanisms involved remain unknown. Awareness is not an objectively established fact, therefore, despite extensive research, scientists have not been able to fully interpret its contribution in multisensory integration and precise neural firing, hence, questions remain: (1) How the biological neuron integrates the incoming multisensory signals with respect to different situations? (2) How are the roles of incoming multisensory signals defined (selective amplification/attenuation) that help neuron(s) to originate a precise neural firing complying with the anticipated behavioural-constraint of the environment? (3) How are the external environment and anticipated behaviour integrated? Recently, scientists have exploited deep learning to integrate multimodal cues and capture context-dependent meanings. Yet, these methods suffer from imprecise behavioural representation. In this research, we introduce a new theory on the role of awareness and universal context that can help answering the aforementioned crucial neuroscience questions. Specifically, we propose a class of spiking conscious neuron in which the output depends on three functionally distinctive integrated input variables: receptive field (RF), local contextual field (LCF), and universal contextual field (UCF). The RF defines the incoming ambiguous sensory signal, LCF defines the modulatory signal coming from other parts of the brain, and UCF defines the awareness. It is believed that the conscious neuron inherently contains enough knowledge about the situation in which the problem is to be solved based on past learning and reasoning and it defines the precise role of incoming multisensory signals to originate a precise neural firing (exhibiting switch-like behaviour). It is shown that the conscious neuron helps modelling a more precise human behaviour. |
| Tasks | |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01701v1 |
| http://arxiv.org/pdf/1811.01701v1.pdf | |
| PWC | https://paperswithcode.com/paper/role-of-awareness-and-universal-context-in-a |
| Repo | |
| Framework | |
Automatic Catchphrase Extraction from Legal Case Documents via Scoring using Deep Neural Networks
| Title | Automatic Catchphrase Extraction from Legal Case Documents via Scoring using Deep Neural Networks |
| Authors | Vu Tran, Minh Le Nguyen, Ken Satoh |
| Abstract | In this paper, we present a method of automatic catchphrase extracting from legal case documents. We utilize deep neural networks for constructing scoring model of our extraction system. We achieve comparable performance with systems using corpus-wide and citation information which we do not use in our system. |
| Tasks | |
| Published | 2018-09-14 |
| URL | http://arxiv.org/abs/1809.05219v1 |
| http://arxiv.org/pdf/1809.05219v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-catchphrase-extraction-from-legal |
| Repo | |
| Framework | |
Learning Common Representation from RGB and Depth Images
| Title | Learning Common Representation from RGB and Depth Images |
| Authors | Giorgio Giannone, Boris Chidlovskii |
| Abstract | We propose a new deep learning architecture for the tasks of semantic segmentation and depth prediction from RGB-D images. We revise the state of art based on the RGB and depth feature fusion, where both modalities are assumed to be available at train and test time. We propose a new architecture where the feature fusion is replaced with a common deep representation. Combined with an encoder-decoder type of the network, the architecture can jointly learn models for semantic segmentation and depth estimation based on their common representation. This representation, inspired by multi-view learning, offers several important advantages, such as using one modality available at test time to reconstruct the missing modality. In the RGB-D case, this enables the cross-modality scenarios, such as using depth data for semantically segmentation and the RGB images for depth estimation. We demonstrate the effectiveness of the proposed network on two publicly available RGB-D datasets. The experimental results show that the proposed method works well in both semantic segmentation and depth estimation tasks. |
| Tasks | Depth Estimation, MULTI-VIEW LEARNING, Semantic Segmentation |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1812.06873v1 |
| http://arxiv.org/pdf/1812.06873v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-common-representation-from-rgb-and |
| Repo | |
| Framework | |
Zero-Shot Learning with Sparse Attribute Propagation
| Title | Zero-Shot Learning with Sparse Attribute Propagation |
| Authors | Nanyi Fei, Jiechao Guan, Zhiwu Lu, Tao Xiang, Ji-Rong Wen |
| Abstract | Zero-shot learning (ZSL) aims to recognize a set of unseen classes without any training images. The standard approach to ZSL requires a set of training images annotated with seen class labels and a semantic descriptor for seen/unseen classes (attribute vector is the most widely used). Class label/attribute annotation is expensive; it thus severely limits the scalability of ZSL. In this paper, we define a new ZSL setting where only a few annotated images are collected from each seen class. This is clearly more challenging yet more realistic than the conventional ZSL setting. To overcome the resultant image-level attribute sparsity, we propose a novel inductive ZSL model termed sparse attribute propagation (SAP) by propagating attribute annotations to more unannotated images using sparse coding. This is followed by learning bidirectional projections between features and attributes for ZSL. An efficient solver is provided, together with rigorous theoretic algorithm analysis. With our SAP, we show that a ZSL training dataset can now be augmented by the abundant web images returned by image search engine, to further improve the model performance. Moreover, the general applicability of SAP is demonstrated on solving the social image annotation (SIA) problem. Extensive experiments show that our model achieves superior performance on both ZSL and SIA. |
| Tasks | Image Retrieval, Zero-Shot Learning |
| Published | 2018-12-11 |
| URL | http://arxiv.org/abs/1812.04427v2 |
| http://arxiv.org/pdf/1812.04427v2.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-learning-with-sparse-attribute |
| Repo | |
| Framework | |
ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera
| Title | ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera |
| Authors | Chao Li, Zheheng Zhao, Xiaohu Guo |
| Abstract | This paper proposes a real-time dynamic scene reconstruction method capable of reproducing the motion, geometry, and segmentation simultaneously given live depth stream from a single RGB-D camera. Our approach fuses geometry frame by frame and uses a segmentation-enhanced node graph structure to drive the deformation of geometry in registration step. A two-level node motion optimization is proposed. The optimization space of node motions and the range of physically-plausible deformations are largely reduced by taking advantage of the articulated motion prior, which is solved by an efficient node graph segmentation method. Compared to previous fusion-based dynamic scene reconstruction methods, our experiments show robust and improved reconstruction results for tangential and occluded motions. |
| Tasks | |
| Published | 2018-07-19 |
| URL | http://arxiv.org/abs/1807.07243v1 |
| http://arxiv.org/pdf/1807.07243v1.pdf | |
| PWC | https://paperswithcode.com/paper/articulatedfusion-real-time-reconstruction-of |
| Repo | |
| Framework | |
Learning Distributed Representations from Reviews for Collaborative Filtering
| Title | Learning Distributed Representations from Reviews for Collaborative Filtering |
| Authors | Amjad Almahairi, Kyle Kastner, Kyunghyun Cho, Aaron Courville |
| Abstract | Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews, as a way of regularizing the derived product representations. Motivated by the success of this approach, we introduce two different models of reviews and study their effect on collaborative filtering performance. While the previous state-of-the-art approach is based on a latent Dirichlet allocation (LDA) model of reviews, the models we explore are neural network based: a bag-of-words product-of-experts model and a recurrent neural network. We demonstrate that the increased flexibility offered by the product-of-experts model allowed it to achieve state-of-the-art performance on the Amazon review dataset, outperforming the LDA-based approach. However, interestingly, the greater modeling power offered by the recurrent neural network appears to undermine the model’s ability to act as a regularizer of the product representations. |
| Tasks | Recommendation Systems |
| Published | 2018-06-18 |
| URL | http://arxiv.org/abs/1806.06875v1 |
| http://arxiv.org/pdf/1806.06875v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-distributed-representations-from |
| Repo | |
| Framework | |
Multi-step Time Series Forecasting Using Ridge Polynomial Neural Network with Error-Output Feedbacks
| Title | Multi-step Time Series Forecasting Using Ridge Polynomial Neural Network with Error-Output Feedbacks |
| Authors | Waddah Waheeb, Rozaida Ghazali |
| Abstract | Time series forecasting gets much attention due to its impact on many practical applications. Higher-order neural network with recurrent feedback is a powerful technique which used successfully for forecasting. It maintains fast learning and the ability to learn the dynamics of the series over time. For that, in this paper, we propose a novel model which is called Ridge Polynomial Neural Network with Error-Output Feedbacks (RPNN-EOFs) that combines the properties of higher order and error-output feedbacks. The well-known Mackey-Glass time series is used to test the forecasting capability of RPNN-EOFS. Simulation results showed that the proposed RPNN-EOFs provides better understanding for the Mackey-Glass time series with root mean square error equal to 0.00416. This result is smaller than other models in the literature. Therefore, we can conclude that the RPNN-EOFs can be applied successfully for time series forecasting. |
| Tasks | Time Series, Time Series Forecasting |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11620v1 |
| http://arxiv.org/pdf/1811.11620v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-step-time-series-forecasting-using |
| Repo | |
| Framework | |
Consistency for 0-1 Programming
| Title | Consistency for 0-1 Programming |
| Authors | Danial Davarnia, J. N. Hooker |
| Abstract | Concepts of consistency have long played a key role in constraint programming but never developed in integer programming (IP). Consistency nonetheless plays a role in IP as well. For example, cutting planes can reduce backtracking by achieving various forms of consistency as well as by tightening the linear programming (LP) relaxation. We introduce a type of consistency that is particularly suited for 0-1 programming and develop the associated theory. We define a 0-1 constraint set as LP-consistent when any partial assignment that is consistent with its linear programming relaxation is consistent with the original 0-1 constraint set. We prove basic properties of LP-consistency, including its relationship with Chvatal-Gomory cuts and the integer hull. We show that a weak form of LP-consistency can reduce or eliminate backtracking in a way analogous to k-consistency but is easier to achieve. In so doing, we identify a class of valid inequalities that can be more effective than traditional cutting planes at cutting off infeasible 0-1 partial assignments. |
| Tasks | |
| Published | 2018-12-05 |
| URL | http://arxiv.org/abs/1812.02215v1 |
| http://arxiv.org/pdf/1812.02215v1.pdf | |
| PWC | https://paperswithcode.com/paper/consistency-for-0-1-programming |
| Repo | |
| Framework | |
End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification
| Title | End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification |
| Authors | Jindřich Libovický, Jindřich Helcl |
| Abstract | Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in parallel. We present a novel non-autoregressive architecture based on connectionist temporal classification and evaluate it on the task of neural machine translation. Unlike other non-autoregressive methods which operate in several steps, our model can be trained end-to-end. We conduct experiments on the WMT English-Romanian and English-German datasets. Our models achieve a significant speedup over the autoregressive models, keeping the translation quality comparable to other non-autoregressive models. |
| Tasks | Machine Translation |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04719v1 |
| http://arxiv.org/pdf/1811.04719v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-non-autoregressive-neural-machine |
| Repo | |
| Framework | |
Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks
| Title | Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks |
| Authors | Wei Hu, Gusi Te, Ju He, Dong Chen, Zongming Guo |
| Abstract | Face anti-spoofing plays a crucial role in protecting face recognition systems from various attacks. Previous model-based and deep learning approaches achieve satisfactory performance for 2D face spoofs, but remain limited for more advanced 3D attacks such as vivid masks. In this paper, we address 3D face anti-spoofing via the proposed Hypergraph Convolutional Neural Networks (HGCNN). Firstly, we construct a computation-efficient and posture-invariant face representation with only a few key points on hypergraphs. The hypergraph representation is then fed into the designed HGCNN with hypergraph convolution for feature extraction, while the depth auxiliary is also exploited for 3D mask anti-spoofing. Further, we build a 3D face attack database with color, depth and infrared light information to overcome the deficiency of 3D face anti-spoofing data. Experiments show that our method achieves the state-of-the-art performance over widely used 3D and 2D databases as well as the proposed one under various tests. |
| Tasks | Face Anti-Spoofing, Face Recognition |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11594v2 |
| http://arxiv.org/pdf/1811.11594v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-hypergraph-representation-on-face |
| Repo | |
| Framework | |
Distributed Chernoff Test: Optimal decision systems over networks
| Title | Distributed Chernoff Test: Optimal decision systems over networks |
| Authors | Anshuka Rangi, Massimo Franceschetti, Stefano Marano |
| Abstract | In this work, we propose two different sequential and adaptive hypothesis tests, motivated from classic Chernoff’s test, for both decentralized and distributed setup of sensor networks. In the former setup, the sensors can communicate via central entity i.e. fusion center. On the other hand, in the latter setup, sensors are connected via communication link, and no central entity is present to facilitate the communication. We compare the performance of these tests with the optimal consistent sequential test in the sensor network. In decentralized setup, the proposed test achieves the same asymptotic optimality of the classic one, minimizing the expected cost required to reach a decision plus the expected cost of making a wrong decision, when the observation cost per unit time tends to zero. This test is also asymptotic optimal in the higher moments of decision time. The proposed test is parsimonious in terms of communications as the expected number of channel uses required by each sensor, in the regime of vanishing observation cost per unit time, to complete the test converges to four.In distributed setup, the proposed test is evaluated on the same performance measures as the test in decentralized setup. We also provide sufficient conditions for which the proposed test in distributed setup also achieves the same asymptotic optimality as the classic one. Like the proposed test in decentralized setup, under these sufficient conditions, the proposed test in distributed setup is also asymptotic optimal in the higher moments of time required to reach a decision in the sensor network. This test is parsimonious is terms of communications in comparison to the state of art schemes proposed in the literature for distributed hypothesis testing. |
| Tasks | |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04587v1 |
| http://arxiv.org/pdf/1809.04587v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-chernoff-test-optimal-decision |
| Repo | |
| Framework | |
Multimodal Classification with Deep Convolutional-Recurrent Neural Networks for Electroencephalography
| Title | Multimodal Classification with Deep Convolutional-Recurrent Neural Networks for Electroencephalography |
| Authors | Chuanqi Tan, Fuchun Sun, Wenchang Zhang, Jianhua Chen, Chunfang Liu |
| Abstract | Electroencephalography (EEG) has become the most significant input signal for brain computer interface (BCI) based systems. However, it is very difficult to obtain satisfactory classification accuracy due to traditional methods can not fully exploit multimodal information. Herein, we propose a novel approach to modeling cognitive events from EEG data by reducing it to a video classification problem, which is designed to preserve the multimodal information of EEG. In addition, optical flow is introduced to represent the variant information of EEG. We train a deep neural network (DNN) with convolutional neural network (CNN) and recurrent neural network (RNN) for the EEG classification task by using EEG video and optical flow. The experiments demonstrate that our approach has many advantages, such as more robustness and more accuracy in EEG classification tasks. According to our approach, we designed a mixed BCI-based rehabilitation support system to help stroke patients perform some basic operations. |
| Tasks | EEG, Optical Flow Estimation, Video Classification |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.10641v1 |
| http://arxiv.org/pdf/1807.10641v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-classification-with-deep |
| Repo | |
| Framework | |
CAN: Composite Appearance Network for Person Tracking and How to Model Errors in a Tracking System
| Title | CAN: Composite Appearance Network for Person Tracking and How to Model Errors in a Tracking System |
| Authors | Neeti Narayan, Nishant Sankaran, Srirangaraj Setlur, Venu Govindaraju |
| Abstract | Tracking multiple people across multiple cameras is an open problem. It is typically divided into two tasks: (i) single-camera tracking (SCT) - identify trajectories in the same scene, and (ii) inter-camera tracking (ICT) - identify trajectories across cameras for real surveillance scenes. Many methods cater to SCT, while ICT still remains a challenge. In this paper, we propose a tracking method which uses motion cues and a feature aggregation network for template-based person re-identification by incorporating metadata such as person bounding box and camera information. We present a feature aggregation architecture called Composite Appearance Network (CAN) to address the above problem. The key structure of this architecture is called EvalNet that pays attention to each feature vector and learns to weight them based on gradients it receives for the overall template for optimal re-identification performance. We demonstrate the efficiency of our approach with experiments on the challenging multi-camera tracking dataset, DukeMTMC. We also survey existing tracking measures and present an online error metric called “Inference Error” (IE) that provides a better estimate of tracking/re-identification error, by treating SCT and ICT errors uniformly. |
| Tasks | Person Re-Identification |
| Published | 2018-11-15 |
| URL | https://arxiv.org/abs/1811.06582v4 |
| https://arxiv.org/pdf/1811.06582v4.pdf | |
| PWC | https://paperswithcode.com/paper/can-composite-appearance-network-and-a-novel |
| Repo | |
| Framework | |
Tensor Methods for Additive Index Models under Discordance and Heterogeneity
| Title | Tensor Methods for Additive Index Models under Discordance and Heterogeneity |
| Authors | Krishnakumar Balasubramanian, Jianqing Fan, Zhuoran Yang |
| Abstract | Motivated by the sampling problems and heterogeneity issues common in high- dimensional big datasets, we consider a class of discordant additive index models. We propose method of moments based procedures for estimating the indices of such discordant additive index models in both low and high-dimensional settings. Our estimators are based on factorizing certain moment tensors and are also applicable in the overcomplete setting, where the number of indices is more than the dimensionality of the datasets. Furthermore, we provide rates of convergence of our estimator in both high and low-dimensional setting. Establishing such results requires deriving tensor operator norm concentration inequalities that might be of independent interest. Finally, we provide simulation results supporting our theory. Our contributions extend the applicability of tensor methods for novel models in addition to making progress on understanding theoretical properties of such tensor methods. |
| Tasks | |
| Published | 2018-07-17 |
| URL | http://arxiv.org/abs/1807.06693v1 |
| http://arxiv.org/pdf/1807.06693v1.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-methods-for-additive-index-models |
| Repo | |
| Framework | |
