January 25, 2020

3448 words 17 mins read

Paper Group ANR 1766

Context based Analysis of Lexical Semantics for Hindi Language. Hyperbolic Node Embedding for Signed Networks. Customized Graph Embedding: Tailoring Embedding Vectors to different Applications. MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit. Mobile Edge Computing, Blockchain and Reputation-based Crowdsourcing IoT Federa …

Context based Analysis of Lexical Semantics for Hindi Language


Title	Context based Analysis of Lexical Semantics for Hindi Language
Authors	Mohd Zeeshan Ansari, Lubna Khan
Abstract	A word having multiple senses in a text introduces the lexical semantic task to find out which particular sense is appropriate for the given context. One such task is Word sense disambiguation which refers to the identification of the most appropriate meaning of the polysemous word in a given context using computational algorithms. The language processing research in Hindi, the official language of India, and other Indian languages is restricted by unavailability of the standard corpus. For Hindi word sense disambiguation also, the large corpus is not available. In this work, we prepared the text containing new senses of certain words leading to the enrichment of the sense-tagged Hindi corpus of sixty polysemous words. Furthermore, we analyzed two novel lexical associations for Hindi word sense disambiguation based on the contextual features of the polysemous word. The evaluation of these methods is carried out over learning algorithms and favorable results are achieved.
Tasks	Word Sense Disambiguation
Published	2019-01-23
URL	http://arxiv.org/abs/1901.07867v1
PDF	http://arxiv.org/pdf/1901.07867v1.pdf
PWC	https://paperswithcode.com/paper/context-based-analysis-of-lexical-semantics
Repo
Framework

Hyperbolic Node Embedding for Signed Networks


Title	Hyperbolic Node Embedding for Signed Networks
Authors	Wenzhuo Song, Shengsheng Wang
Abstract	The rapid evolving World Wide Web has produced a large amount of complex and heterogeneous network data. To facilitate network analysis algorithms, signed network embedding methods automatically learn feature vectors of nodes in signed networks. However, existing algorithms only managed to embed the networks into Euclidean spaces, although many features of signed networks reported are more suitable for non-Euclidean space. Besides, previous works also do not consider the hierarchical organization of networks, which is widely existed in real-world networks. In this work, we investigate the problem of whether the hyperbolic space is a better choice to represent signed networks. We develop a non-Euclidean signed network embedding method based on structural balance theory and Riemannian optimization. Our method embeds signed networks into a Poincar'e ball, which is a hyperbolic space can be seen as a continuous tree. This feature enables our approach to capture underlying hierarchical structure in signed networks. We empirically compare our method with three Euclidean-based baselines in visualization, sign prediction, and reconstruction tasks on six real-world datasets. The results show that our hyperbolic embedding performs better than Euclidean counterparts and can extract a meaningful latent hierarchical structure from signed networks.
Tasks	Network Embedding
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13090v1
PDF	https://arxiv.org/pdf/1910.13090v1.pdf
PWC	https://paperswithcode.com/paper/hyperbolic-node-embedding-for-signed-networks
Repo
Framework

Customized Graph Embedding: Tailoring Embedding Vectors to different Applications


Title	Customized Graph Embedding: Tailoring Embedding Vectors to different Applications
Authors	Bitan Hou, Yujing Wang, Ming Zeng, Shan Jiang, Ole J. Mengshoel, Yunhai Tong, Jing Bai
Abstract	Graph is a natural representation of data for a variety of real-word applications, such as knowledge graph mining, social network analysis and biological network comparison. For these applications, graph embedding is crucial as it provides vector representations of the graph. One limitation of existing graph embedding methods is that their embedding optimization procedures are disconnected from the target application. In this paper, we propose a novel approach, namely Customized Graph Embedding (CGE) to tackle this problem. The CGE algorithm learns customized vector representations of graph nodes by differentiating the importance of distinct graph paths automatically for a specific application. Extensive experiments were carried out on a diverse set of node classification datasets, which demonstrate strong performances of CGE and provide deep insights into the model.
Tasks	Graph Embedding, Node Classification
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09454v3
PDF	https://arxiv.org/pdf/1911.09454v3.pdf
PWC	https://paperswithcode.com/paper/customized-graph-embedding-tailoring-the
Repo
Framework

MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit


Title	MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit
Authors	John Palowitch, Bryan Perozzi
Abstract	Are Graph Neural Networks (GNNs) fair? In many real world graphs, the formation of edges is related to certain node attributes (e.g. gender, community, reputation). In this case, standard GNNs using these edges will be biased by this information, as it is encoded in the structure of the adjacency matrix itself. In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata. This bias implies an inability to control for important covariates in real-world applications, such as recommendation systems. To solve these issues, we introduce the Metadata-Orthogonal Node Embedding Training (MONET) unit, a general model for debiasing embeddings of nodes in a graph. MONET achieves this by ensuring that the node embeddings are trained on a hyperplane orthogonal to that of the node metadata. This effectively organizes unstructured embedding dimensions into an interpretable topology-only, metadata-only division with no linear interactions. We illustrate the effectiveness of MONET though our experiments on a variety of real world graphs, which shows that our method can learn and remove the effect of arbitrary covariates in tasks such as preventing the leakage of political party affiliation in a blog network, and thwarting the gaming of embedding-based recommendation systems.
Tasks	Recommendation Systems
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11793v2
PDF	https://arxiv.org/pdf/1909.11793v2.pdf
PWC	https://paperswithcode.com/paper/monet-debiasing-graph-embeddings-via-the
Repo
Framework

Mobile Edge Computing, Blockchain and Reputation-based Crowdsourcing IoT Federated Learning: A Secure, Decentralized and Privacy-preserving System


Title	Mobile Edge Computing, Blockchain and Reputation-based Crowdsourcing IoT Federated Learning: A Secure, Decentralized and Privacy-preserving System
Authors	Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato
Abstract	Internet-of-Things (IoT) companies strive to get feedback from users to improve their products and services. However, traditional surveys cannot reflect the actual conditions of customers’ due to the limited questions. Besides, survey results are affected by various subjective factors. In contrast, the recorded usages of IoT devices reflect customers’ behaviours more comprehensively and accurately. We design an intelligent system to help IoT device manufacturers to take advantage of customers’ data and build a machine learning model to predict customers’ requirements and possible consumption behaviours with federated learning (FL) technology. The FL consists of two stages: in the first stage, customers train the initial model using the phone and the edge computing server collaboratively. The mobile edge computing server’s high computation power can assist customers’ training locally. Customers first collect data from various IoT devices using phones, and then download and train the initial model with their data. During the training, customers first extract features using their mobiles, and then add the Laplacian noise to the extracted features based on differential privacy, a formal and popular notion to quantify privacy. After achieving the local model, customers sign on their models respectively and send them to the blockchain. We use the blockchain to replace the centralized aggregator which belongs to the third party in FL. In the second stage, miners calculate the averaged model using the collected models sent from customers. By the end of the crowdsourcing job, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. Besides, to attract more customers to participate in the crowdsourcing FL, we design an incentive mechanism, which awards participants with coins that can be used to purchase other services provided by the company.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.10893v1
PDF	https://arxiv.org/pdf/1906.10893v1.pdf
PWC	https://paperswithcode.com/paper/mobile-edge-computing-blockchain-and
Repo
Framework

Signal retrieval with measurement system knowledge using variational generative model


Title	Signal retrieval with measurement system knowledge using variational generative model
Authors	Zheyuan Zhu, Yangyang Sun, Johnathon White, Zenghu Chang, Shuo Pang
Abstract	Signal retrieval from a series of indirect measurements is a common task in many imaging, metrology and characterization platforms in science and engineering. Because most of the indirect measurement processes are well-described by physical models, signal retrieval can be solved with an iterative optimization that enforces measurement consistency and prior knowledge on the signal. These iterative processes are time-consuming and only accommodate a linear measurement process and convex signal constraints. Recently, neural networks have been widely adopted to supersede iterative signal retrieval methods by approximating the inverse mapping of the measurement model. However, networks with deterministic processes have failed to distinguish signal ambiguities in an ill-posed measurement system, and retrieved signals often lack consistency with the measurement. In this work we introduce a variational generative model to capture the distribution of all possible signals, given a particular measurement. By exploiting the known measurement model in the variational generative framework, our signal retrieval process resolves the ambiguity in the forward process, and learns to retrieve signals that satisfy the measurement with high fidelity in a variety of linear and nonlinear ill-posed systems, including ultrafast pulse retrieval, coded aperture compressive video sensing and image retrieval from Fresnel hologram.
Tasks	Image Retrieval
Published	2019-09-09
URL	https://arxiv.org/abs/1909.04188v1
PDF	https://arxiv.org/pdf/1909.04188v1.pdf
PWC	https://paperswithcode.com/paper/signal-retrieval-with-measurement-system
Repo
Framework

A neural document language modeling framework for spoken document retrieval


Title	A neural document language modeling framework for spoken document retrieval
Authors	Li-Phen Yen, Zhen-Yu Wu, Kuan-Yu Chen
Abstract	Recent developments in deep learning have led to a significant innovation in various classic and practical subjects, including speech recognition, computer vision, question answering, information retrieval and so on. In the context of natural language processing (NLP), language representations have shown giant successes in many downstream tasks, so the school of studies have become a major stream of research recently. Because the immenseness of multimedia data along with speech have spread around the world in our daily life, spoken document retrieval (SDR) has become an important research subject in the past decades. Targeting on enhancing the SDR performance, the paper concentrates on proposing a neural retrieval framework, which assembles the merits of using language modeling (LM) mechanism in SDR and leveraging the abstractive information learned by the language representation models. Consequently, to our knowledge, this is a pioneer study on supervised training of a neural LM-based SDR framework, especially combined with the pretrained language representation methods.
Tasks	Information Retrieval, Language Modelling, Question Answering, Speech Recognition
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14286v1
PDF	https://arxiv.org/pdf/1910.14286v1.pdf
PWC	https://paperswithcode.com/paper/a-neural-document-language-modeling-framework
Repo
Framework

USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets


Title	USE-Net: incorporating Squeeze-and-Excitation blocks into U-Net for prostate zonal segmentation of multi-institutional MRI datasets
Authors	Leonardo Rundo, Changhee Han, Yudai Nagano, Jin Zhang, Ryuichiro Hataya, Carmelo Militello, Andrea Tangherloni, Marco S. Nobile, Claudio Ferretti, Daniela Besozzi, Maria Carla Gilardi, Salvatore Vitabile, Giancarlo Mauri, Hideki Nakayama, Paolo Cazzaniga
Abstract	Prostate cancer is the most common malignant tumors in men but prostate Magnetic Resonance Imaging (MRI) analysis remains challenging. Besides whole prostate gland segmentation, the capability to differentiate between the blurry boundary of the Central Gland (CG) and Peripheral Zone (PZ) can lead to differential diagnosis, since tumor’s frequency and severity differ in these regions. To tackle the prostate zonal segmentation task, we propose a novel Convolutional Neural Network (CNN), called USE-Net, which incorporates Squeeze-and-Excitation (SE) blocks into U-Net. Especially, the SE blocks are added after every Encoder (Enc USE-Net) or Encoder-Decoder block (Enc-Dec USE-Net). This study evaluates the generalization ability of CNN-based architectures on three T2-weighted MRI datasets, each one consisting of a different number of patients and heterogeneous image characteristics, collected by different institutions. The following mixed scheme is used for training/testing: (i) training on either each individual dataset or multiple prostate MRI datasets and (ii) testing on all three datasets with all possible training/testing combinations. USE-Net is compared against three state-of-the-art CNN-based architectures (i.e., U-Net, pix2pix, and Mixed-Scale Dense Network), along with a semi-automatic continuous max-flow model. The results show that training on the union of the datasets generally outperforms training on each dataset separately, allowing for both intra-/cross-dataset generalization. Enc USE-Net shows good overall generalization under any training condition, while Enc-Dec USE-Net remarkably outperforms the other methods when trained on all datasets. These findings reveal that the SE blocks’ adaptive feature recalibration provides excellent cross-dataset generalization when testing is performed on samples of the datasets used during training.
Tasks
Published	2019-04-17
URL	https://arxiv.org/abs/1904.08254v2
PDF	https://arxiv.org/pdf/1904.08254v2.pdf
PWC	https://paperswithcode.com/paper/use-net-incorporating-squeeze-and-excitation
Repo
Framework

FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods


Title	FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods
Authors	Nur Sila Gulgec, Zheng Shi, Neil Deshmukh, Shamim Pakzad, Martin Takáč
Abstract	Discovering the underlying physical behavior of complex systems is a crucial, but less well-understood topic in many engineering disciplines. This study proposes a finite-difference inspired convolutional neural network framework to learn hidden partial differential equations from given data and iteratively estimate future dynamical behavior. The methodology designs the filter sizes such that they mimic the finite difference between the neighboring points. By learning the governing equation, the network predicts the future evolution of the solution by using only a few trainable parameters. In this paper, we provide numerical results to compare the efficiency of the second-order Trust-Region Conjugate Gradient (TRCG) method with the first-order ADAM optimizer.
Tasks
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12680v2
PDF	https://arxiv.org/pdf/1910.12680v2.pdf
PWC	https://paperswithcode.com/paper/fd-net-with-auxiliary-time-steps-fast
Repo
Framework

Power Allocation in Cache-Aided NOMA Systems: Optimization and Deep Reinforcement Learning Approaches


Title	Power Allocation in Cache-Aided NOMA Systems: Optimization and Deep Reinforcement Learning Approaches
Authors	Khai Nguyen Doan, Mojtaba Vaezi, Wonjae Shin, H. Vincent Poor, Hyundong Shin, Tony Q. S. Quek
Abstract	This work exploits the advantages of two prominent techniques in future communication networks, namely caching and non-orthogonal multiple access (NOMA). Particularly, a system with Rayleigh fading channels and cache-enabled users is analyzed. It is shown that the caching-NOMA combination provides a new opportunity of cache hit which enhances the cache utility as well as the effectiveness of NOMA. Importantly, this comes without requiring users’ collaboration, and thus, avoids many complicated issues such as users’ privacy and security, selfishness, etc. In order to optimize users’ quality of service and, concurrently, ensure the fairness among users, the probability that all users can decode the desired signals is maximized. In NOMA, a combination of multiple messages are sent to users, and the defined objective is approached by finding an appropriate power allocation for message signals. To address the power allocation problem, two novel methods are proposed. The first one is a divide-and-conquer-based method for which closed-form expressions for the optimal resource allocation policy are derived, making this method simple and flexible to the system context. The second one is based on the deep reinforcement learning method that allows all users to share the full bandwidth. Finally, simulation results are provided to demonstrate the effectiveness of the proposed methods and to compare their performance.
Tasks
Published	2019-09-24
URL	https://arxiv.org/abs/1909.11074v1
PDF	https://arxiv.org/pdf/1909.11074v1.pdf
PWC	https://paperswithcode.com/paper/power-allocation-in-cache-aided-noma-systems
Repo
Framework

Controllable Attention for Structured Layered Video Decomposition


Title	Controllable Attention for Structured Layered Video Decomposition
Authors	Jean-Baptiste Alayrac, João Carreira, Relja Arandjelović, Andrew Zisserman
Abstract	The objective of this paper is to be able to separate a video into its natural layers, and to control which of the separated layers to attend to. For example, to be able to separate reflections, transparency or object motion. We make the following three contributions: (i) we introduce a new structured neural network architecture that explicitly incorporates layers (as spatial masks) into its design. This improves separation performance over previous general purpose networks for this task; (ii) we demonstrate that we can augment the architecture to leverage external cues such as audio for controllability and to help disambiguation; and (iii) we experimentally demonstrate the effectiveness of our approach and training procedure with controlled experiments while also showing that the proposed model can be successfully applied to real-word applications such as reflection removal and action recognition in cluttered scenes.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11306v1
PDF	https://arxiv.org/pdf/1910.11306v1.pdf
PWC	https://paperswithcode.com/paper/controllable-attention-for-structured-layered-1
Repo
Framework

Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification


Title	Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification
Authors	Lingxiao He, Yinggang Wang, Wu Liu, Xingyu Liao, He Zhao, Zhenan Sun, Jiashi Feng
Abstract	Re-identifying a person across multiple disjoint camera views is important for intelligent video surveillance, smart retailing and many other applications. However, existing person re-identification (ReID) methods are challenged by the ubiquitous occlusion over persons and suffer from performance degradation. This paper proposes a novel occlusion-robust and alignment-free model for occluded person ReID and extends its application to realistic and crowded scenarios. The proposed model first leverages the full convolution network (FCN) and pyramid pooling to extract spatial pyramid features. Then an alignment-free matching approach, namely Foreground-aware Pyramid Reconstruction (FPR), is developed to accurately compute matching scores between occluded persons, despite their different scales and sizes. FPR uses the error from robust reconstruction over spatial pyramid features to measure similarities between two persons. More importantly, we design an occlusion-sensitive foreground probability generator that focuses more on clean human body parts to refine the similarity computation with less contamination from occlusion. The FPR is easily embedded into any end-to-end person ReID models. The effectiveness of the proposed method is clearly demonstrated by the experimental results (Rank-1 accuracy) on three occluded person datasets: Partial REID (78.30%), Partial iLIDS (68.08%) and Occluded REID (81.00%); and three benchmark person datasets: Market1501 (95.42%), DukeMTMC (88.64%) and CUHK03 (76.08%)
Tasks	Person Re-Identification
Published	2019-04-10
URL	http://arxiv.org/abs/1904.04975v2
PDF	http://arxiv.org/pdf/1904.04975v2.pdf
PWC	https://paperswithcode.com/paper/foreground-aware-pyramid-reconstruction-for
Repo
Framework


Title	On the Unintended Social Bias of Training Language Generation Models with Data from Local Media
Authors	Omar U. Florez
Abstract	There are concerns that neural language models may preserve some of the stereotypes of the underlying societies that generate the large corpora needed to train these models. For example, gender bias is a significant problem when generating text, and its unintended memorization could impact the user experience of many applications (e.g., the smart-compose feature in Gmail). In this paper, we introduce a novel architecture that decouples the representation learning of a neural model from its memory management role. This architecture allows us to update a memory module with an equal ratio across gender types addressing biased correlations directly in the latent space. We experimentally show that our approach can mitigate the gender bias amplification in the automatic generation of articles news while providing similar perplexity values when extending the Sequence2Sequence architecture.
Tasks	Representation Learning, Text Generation
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00461v1
PDF	https://arxiv.org/pdf/1911.00461v1.pdf
PWC	https://paperswithcode.com/paper/on-the-unintended-social-bias-of-training
Repo
Framework

Looking at the right stuff: Guided semantic-gaze for autonomous driving


Title	Looking at the right stuff: Guided semantic-gaze for autonomous driving
Authors	Anwesan Pal, Sayan Mondal, Henrik I. Christensen
Abstract	In recent years, predicting driver’s focus of attention has been a very active area of research in the autonomous driving community. Unfortunately, existing state-of-the-art techniques achieve this by relying only on human gaze information, thereby ignoring scene semantics. We propose a novel Semantics Augmented GazE (SAGE) detection approach that captures driving specific contextual information, in addition to the raw gaze. Such a combined attention mechanism serves as a powerful tool to focus on the relevant regions in an image frame in order to make driving both safe and efficient. Using this, we design a complete saliency prediction framework - SAGE-Net, which modifies the initial prediction from SAGE by taking into account vital aspects such as distance to objects (depth), ego vehicle speed, and pedestrian crossing intent. Exhaustive experiments conducted through four popular saliency algorithms show that on $\mathbf{49/56\text{ }(87.5%)}$ cases - considering both the overall dataset and crucial driving scenarios, SAGE outperforms existing techniques without any additional computational overhead during the training process. The augmented dataset along with the relevant code are available as part of the supplementary material.
Tasks	Autonomous Driving, Saliency Prediction
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10455v2
PDF	https://arxiv.org/pdf/1911.10455v2.pdf
PWC	https://paperswithcode.com/paper/looking-at-the-right-stuff-guided-semantic
Repo
Framework

An Induced Multi-Relational Framework for Answer Selection in Community Question Answer Platforms


Title	An Induced Multi-Relational Framework for Answer Selection in Community Question Answer Platforms
Authors	Kanika Narang, Chaoqi Yang, Adit Krishnan, Junting Wang, Hari Sundaram, Carolyn Sutter
Abstract	This paper addresses the question of identifying the best candidate answer to a question on Community Question Answer (CQA) forums. The problem is important because Individuals often visit CQA forums to seek answers to nuanced questions. We develop a novel induced relational graph convolutional network (IR-GCN) framework to address the question. We make three contributions. First, we introduce a modular framework that separates the construction of the graph with the label selection mechanism. We use equivalence relations to induce a graph comprising cliques and identify two label assignment mechanisms—label contrast, label sharing. Then, we show how to encode these assignment mechanisms in GCNs. Second, we show that encoding contrast creates discriminative magnification—enhancing the separation between nodes in the embedding space. Third, we show a surprising result—boosting techniques improve learning over familiar stacking, fusion, or aggregation approaches for neural architectures. We show strong results over the state-of-the-art neural baselines in extensive experiments on 50 StackExchange communities.
Tasks	Answer Selection
Published	2019-11-16
URL	https://arxiv.org/abs/1911.06957v1
PDF	https://arxiv.org/pdf/1911.06957v1.pdf
PWC	https://paperswithcode.com/paper/an-induced-multi-relational-framework-for
Repo
Framework