Paper Group ANR 290
Image Analysis Enhanced Event Detection from Geo-tagged Tweet Streams. On generalized residue network for deep learning of unknown dynamical systems. Unfair Exposure of Artists in Music Recommendation. Survey of Privacy-Preserving Collaborative Filtering. Autoencoders. Stochastically Differentiable Probabilistic Programs. Cost-Function-Dependent Ba …
Image Analysis Enhanced Event Detection from Geo-tagged Tweet Streams
| Title | Image Analysis Enhanced Event Detection from Geo-tagged Tweet Streams |
| Authors | Yi Han, Shanika Karunasekera, Christopher Leckie |
| Abstract | Events detected from social media streams often include early signs of accidents, crimes or disasters. Therefore, they can be used by related parties for timely and efficient response. Although significant progress has been made on event detection from tweet streams, most existing methods have not considered the posted images in tweets, which provide richer information than the text, and potentially can be a reliable indicator of whether an event occurs or not. In this paper, we design an event detection algorithm that combines textual, statistical and image information, following an unsupervised machine learning approach. Specifically, the algorithm starts with semantic and statistical analyses to obtain a list of tweet clusters, each of which corresponds to an event candidate, and then performs image analysis to separate events from non-events—a convolutional autoencoder is trained for each cluster as an anomaly detector, where a part of the images are used as the training data and the remaining images are used as the test instances. Our experiments on multiple datasets verify that when an event occurs, the mean reconstruction errors of the training and test images are much closer, compared with the case where the candidate is a non-event cluster. Based on this finding, the algorithm rejects a candidate if the difference is larger than a threshold. Experimental results over millions of tweets demonstrate that this image analysis enhanced approach can significantly increase the precision with minimum impact on the recall. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04208v1 |
| https://arxiv.org/pdf/2002.04208v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-analysis-enhanced-event-detection-from |
| Repo | |
| Framework | |
On generalized residue network for deep learning of unknown dynamical systems
| Title | On generalized residue network for deep learning of unknown dynamical systems |
| Authors | Zhen Chen, Dongbin Xiu |
| Abstract | We present a general numerical approach for learning unknown dynamical systems using deep neural networks (DNNs). Our method is built upon recent studies that identified the residue network (ResNet) as an effective neural network structure. In this paper, we present a generalized ResNet framework and broadly define residue as the discrepancy between observation data and prediction made by another model, which can be an existing coarse model or reduced-order model. In this case, the generalized ResNet serves as a model correction to the existing model and recovers the unresolved dynamics. When an existing coarse model is not available, we present numerical strategies for fast creation of coarse models, to be used in conjunction with the generalized ResNet. These coarse models are constructed using the same data set and thus do not require additional resources. The generalized ResNet is capable of learning the underlying unknown equations and producing predictions with accuracy higher than the standard ResNet structure. This is demonstrated via several numerical examples, including long-term prediction of a chaotic system. |
| Tasks | |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2002.02528v1 |
| https://arxiv.org/pdf/2002.02528v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-generalized-residue-network-for-deep |
| Repo | |
| Framework | |
Unfair Exposure of Artists in Music Recommendation
| Title | Unfair Exposure of Artists in Music Recommendation |
| Authors | Himan Abdollahpouri, Robin Burke, Masoud Mansoury |
| Abstract | Fairness in machine learning has been studied by many researchers. In particular, fairness in recommender systems has been investigated to ensure the recommendations meet certain criteria with respect to certain sensitive features such as race, gender etc. However, often recommender systems are multi-stakeholder environments in which the fairness towards all stakeholders should be taken care of. It is well-known that the recommendation algorithms suffer from popularity bias; few popular items are over-recommended which leads to the majority of other items not getting proportionate attention. This bias has been investigated from the perspective of the users and how it makes the final recommendations skewed towards popular items in general. In this paper, however, we investigate the impact of popularity bias in recommendation algorithms on the provider of the items (i.e. the entities who are behind the recommended items). Using a music dataset for our experiments, we show that, due to some biases in the algorithms, different groups of artists with varying degrees of popularity are systematically and consistently treated differently than others. |
| Tasks | Recommendation Systems |
| Published | 2020-03-25 |
| URL | https://arxiv.org/abs/2003.11634v1 |
| https://arxiv.org/pdf/2003.11634v1.pdf | |
| PWC | https://paperswithcode.com/paper/unfair-exposure-of-artists-in-music |
| Repo | |
| Framework | |
Survey of Privacy-Preserving Collaborative Filtering
| Title | Survey of Privacy-Preserving Collaborative Filtering |
| Authors | Islam Elnabarawy, Wei Jiang, Donald C. Wunsch II |
| Abstract | Collaborative filtering recommendation systems provide recommendations to users based on their own past preferences, as well as those of other users who share similar interests. The use of recommendation systems has grown widely in recent years, helping people choose which movies to watch, books to read, and items to buy. However, users are often concerned about their privacy when using such systems, and many users are reluctant to provide accurate information to most online services. Privacy-preserving collaborative filtering recommendation systems aim to provide users with accurate recommendations while maintaining certain guarantees about the privacy of their data. This survey examines the recent literature in privacy-preserving collaborative filtering, providing a broad perspective of the field and classifying the key contributions in the literature using two different criteria: the type of vulnerability they address and the type of approach they use to solve it. |
| Tasks | Recommendation Systems |
| Published | 2020-03-18 |
| URL | https://arxiv.org/abs/2003.08343v1 |
| https://arxiv.org/pdf/2003.08343v1.pdf | |
| PWC | https://paperswithcode.com/paper/survey-of-privacy-preserving-collaborative |
| Repo | |
| Framework | |
Autoencoders
| Title | Autoencoders |
| Authors | Dor Bank, Noam Koenigstein, Raja Giryes |
| Abstract | An autoencoder is a specific type of a neural network, which is mainlydesigned to encode the input into a compressed and meaningful representation, andthen decode it back such that the reconstructed input is similar as possible to theoriginal one. This chapter surveys the different types of autoencoders that are mainlyused today. It also describes various applications and use-cases of autoencoders. |
| Tasks | |
| Published | 2020-03-12 |
| URL | https://arxiv.org/abs/2003.05991v1 |
| https://arxiv.org/pdf/2003.05991v1.pdf | |
| PWC | https://paperswithcode.com/paper/autoencoders |
| Repo | |
| Framework | |
Stochastically Differentiable Probabilistic Programs
| Title | Stochastically Differentiable Probabilistic Programs |
| Authors | David Tolpin, Yuan Zhou, Hongseok Yang |
| Abstract | Probabilistic programs with mixed support (both continuous and discrete latent random variables) commonly appear in many probabilistic programming systems (PPSs). However, the existence of the discrete random variables prohibits many basic gradient-based inference engines, which makes the inference procedure on such models particularly challenging. Existing PPSs either require the user to manually marginalize out the discrete variables or to perform a composing inference by running inference separately on discrete and continuous variables. The former is infeasible in most cases whereas the latter has some fundamental shortcomings. We present a novel approach to run inference efficiently and robustly in such programs using stochastic gradient Markov Chain Monte Carlo family of algorithms. We compare our stochastic gradient-based inference algorithm against conventional baselines in several important cases of probabilistic programs with mixed support, and demonstrate that it outperforms existing composing inference baselines and works almost as well as inference in marginalized versions of the programs, but with less programming effort and at a lower computation cost. |
| Tasks | Probabilistic Programming |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.00704v2 |
| https://arxiv.org/pdf/2003.00704v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastically-differentiable-probabilistic |
| Repo | |
| Framework | |
Cost-Function-Dependent Barren Plateaus in Shallow Quantum Neural Networks
| Title | Cost-Function-Dependent Barren Plateaus in Shallow Quantum Neural Networks |
| Authors | M. Cerezo, Akira Sone, Tyler Volkoff, Lukasz Cincio, Patrick J. Coles |
| Abstract | Variational quantum algorithms (VQAs) optimize the parameters $\boldsymbol{\theta}$ of a quantum neural network $V(\boldsymbol{\theta})$ to minimize a cost function $C$. While VQAs may enable practical applications of noisy quantum computers, they are nevertheless heuristic methods with unproven scaling. Here, we rigorously prove two results, assuming $V(\boldsymbol{\theta})$ is a hardware-efficient ansatz composed of blocks forming local 2-designs. Our first result states that defining $C$ in terms of global observables leads to an exponentially vanishing gradient (i.e., a barren plateau) even when $V(\boldsymbol{\theta})$ is shallow. This implies that several VQAs in the literature must revise their proposed cost functions. On the other hand, our second result states that defining $C$ with local observables leads to at worst a polynomially vanishing gradient, so long as the depth of $V(\boldsymbol{\theta})$ is $\mathcal{O}(\log n)$. Taken together, our results establish a connection between locality and trainability. Finally, we illustrate these ideas with large-scale simulations, up to 100 qubits, of a particular VQA known as quantum autoencoders. |
| Tasks | Visual Question Answering |
| Published | 2020-01-02 |
| URL | https://arxiv.org/abs/2001.00550v2 |
| https://arxiv.org/pdf/2001.00550v2.pdf | |
| PWC | https://paperswithcode.com/paper/cost-function-dependent-barren-plateaus-in |
| Repo | |
| Framework | |
Learning Discrete Distributions by Dequantization
| Title | Learning Discrete Distributions by Dequantization |
| Authors | Emiel Hoogeboom, Taco S. Cohen, Jakub M. Tomczak |
| Abstract | Media is generally stored digitally and is therefore discrete. Many successful deep distribution models in deep learning learn a density, i.e., the distribution of a continuous random variable. Na"ive optimization on discrete data leads to arbitrarily high likelihoods, and instead, it has become standard practice to add noise to datapoints. In this paper, we present a general framework for dequantization that captures existing methods as a special case. We derive two new dequantization objectives: importance-weighted (iw) dequantization and R'enyi dequantization. In addition, we introduce autoregressive dequantization (ARD) for more flexible dequantization distributions. Empirically we find that iw and R'enyi dequantization considerably improve performance for uniform dequantization distributions. ARD achieves a negative log-likelihood of 3.06 bits per dimension on CIFAR10, which to the best of our knowledge is state-of-the-art among distribution models that do not require autoregressive inverses for sampling. |
| Tasks | |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11235v1 |
| https://arxiv.org/pdf/2001.11235v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-discrete-distributions-by |
| Repo | |
| Framework | |
Parasitic Neural Network for Zero-Shot Relation Extraction
| Title | Parasitic Neural Network for Zero-Shot Relation Extraction |
| Authors | Shengbin Jia, Shijia E, Yang Xiang |
| Abstract | Conventional relation extraction methods can only identify limited relation classes and not recognize the unseen relation types that have no pre-labeled training data. In this paper, we explore the zero-shot relation extraction to overcome the challenge. The only requisite information about unseen types is the name of their labels. We propose a Parasitic Neural Network (PNN), and it can learn a mapping between the general feature representations of text samples and the distributions of unseen types in a shared semantic space. Experiment results show that our model significantly outperforms others on the unseen relation extraction task and achieves effect improvement more than 20%, when there are not any manual annotations or additional resources. |
| Tasks | Relation Extraction |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2004.00499v1 |
| https://arxiv.org/pdf/2004.00499v1.pdf | |
| PWC | https://paperswithcode.com/paper/parasitic-neural-network-for-zero-shot |
| Repo | |
| Framework | |
Anonymizing Data for Privacy-Preserving Federated Learning
| Title | Anonymizing Data for Privacy-Preserving Federated Learning |
| Authors | Olivia Choudhury, Aris Gkoulalas-Divanis, Theodoros Salonidis, Issa Sylla, Yoonyoung Park, Grace Hsu, Amar Das |
| Abstract | Federated learning enables training a global machine learning model from data distributed across multiple sites, without having to move the data. This is particularly relevant in healthcare applications, where data is rife with personal, highly-sensitive information, and data analysis methods must provably comply with regulatory guidelines. Although federated learning prevents sharing raw data, it is still possible to launch privacy attacks on the model parameters that are exposed during the training process, or on the generated machine learning model. In this paper, we propose the first syntactic approach for offering privacy in the context of federated learning. Unlike the state-of-the-art differential privacy-based frameworks, our approach aims to maximize utility or model performance, while supporting a defensible level of privacy, as demanded by GDPR and HIPAA. We perform a comprehensive empirical evaluation on two important problems in the healthcare domain, using real-world electronic health data of 1 million patients. The results demonstrate the effectiveness of our approach in achieving high model performance, while offering the desired level of privacy. Through comparative studies, we also show that, for varying datasets, experimental setups, and privacy budgets, our approach offers higher model performance than differential privacy-based techniques in federated learning. |
| Tasks | |
| Published | 2020-02-21 |
| URL | https://arxiv.org/abs/2002.09096v1 |
| https://arxiv.org/pdf/2002.09096v1.pdf | |
| PWC | https://paperswithcode.com/paper/anonymizing-data-for-privacy-preserving |
| Repo | |
| Framework | |
Tackling Air Traffic Conflicts as a Weighted CSP : Experiments with the Lumberjack Method
| Title | Tackling Air Traffic Conflicts as a Weighted CSP : Experiments with the Lumberjack Method |
| Authors | Thomas Chaboud, Cédric Pralet, Nicolas Schmidt |
| Abstract | In this paper, we present an extension to an air traffic conflicts resolution method consisting in generating a large number of trajectories for a set of aircraft, and efficiently selecting the best compatible ones. We propose a multimanoeuvre version which encapsulates different conflict-solving algorithms, in particular an original “smart brute-force” method and the well-known ToulBar2 CSP toolset. Experiments on several benchmarks show that the first one is very efficient on cases involving few aircraft (representative of what actually happens in operations), allowing us to search through a large pool of manoeuvres and trajectories; however, this method is overtaken by its complexity when the number of aircraft increases to 7 and more. Conversely, within acceptable times, the ToulBar2 toolset can handle conflicts involving more aircraft, but with fewer possible trajectories for each. |
| Tasks | |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11390v1 |
| https://arxiv.org/pdf/2001.11390v1.pdf | |
| PWC | https://paperswithcode.com/paper/tackling-air-traffic-conflicts-as-a-weighted |
| Repo | |
| Framework | |
A machine learning based plasticity model using proper orthogonal decomposition
| Title | A machine learning based plasticity model using proper orthogonal decomposition |
| Authors | Dengpeng Huang, Jan Niklas Fuhg, Christian Weißenfels, Peter Wriggers |
| Abstract | Data-driven material models have many advantages over classical numerical approaches, such as the direct utilization of experimental data and the possibility to improve performance of predictions when additional data is available. One approach to develop a data-driven material model is to use machine learning tools. These can be trained offline to fit an observed material behaviour and then be applied in online applications. However, learning and predicting history dependent material models, such as plasticity, is still challenging. In this work, a machine learning based material modelling framework is proposed for both elasticity and plasticity. The machine learning based hyperelasticity model is developed with the Feed forward Neural Network (FNN) directly whereas the machine learning based plasticity model is developed by using of a novel method called Proper Orthogonal Decomposition Feed forward Neural Network (PODFNN). In order to account for the loading history, the accumulated absolute strain is proposed to be the history variable of the plasticity model. Additionally, the strain-stress sequence data for plasticity is collected from different loading-unloading paths based on the concept of sequence for plasticity. By means of the POD, the multi-dimensional stress sequence is decoupled leading to independent one dimensional coefficient sequences. In this case, the neural network with multiple output is replaced by multiple independent neural networks each possessing a one-dimensional output, which leads to less training time and better training performance. To apply the machine learning based material model in finite element analysis, the tangent matrix is derived by the automatic symbolic differentiation tool AceGen. The effectiveness and generalization of the presented models are investigated by a series of numerical examples using both 2D and 3D finite element analysis. |
| Tasks | |
| Published | 2020-01-07 |
| URL | https://arxiv.org/abs/2001.03438v1 |
| https://arxiv.org/pdf/2001.03438v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-based-plasticity-model |
| Repo | |
| Framework | |
Pixel-Semantic Revise of Position Learning A One-Stage Object Detector with A Shared Encoder-Decoder
| Title | Pixel-Semantic Revise of Position Learning A One-Stage Object Detector with A Shared Encoder-Decoder |
| Authors | Qian Li, Nan Guo, Xiaochun Ye, Dongrui Fan, Zhimin Tang, Honggang Chen, Wenming Li |
| Abstract | We analyze that different methods based channel or position attention mechanism give rise to different performance on scale, and some of state-of-the-art detectors applying feature pyramid are integrated with various variants convolutions with many mechanisms to enhance information, resulting in increasing runtime. This work addresses the problem by constructing an anchor-free detector with shared module consisting of encoder and decoder with attention mechanism. First, we consider different level features from backbone (e.g., ResNet-50) as the base features. Second, we feed the feature into a simple block, rather than various complex operations.Then, location and classification tasks are obtained by the detector head and classifier, respectively. At the same time, we use the semantic information to revise geometry locations. Additionally, we show that the detector is a pixel-semantic revise of position, universal, effective and simple to detect, especially, large-scale objects. More importantly, this work compares different feature processing (e.g.,mean, maximum or minimum) performance across channel. Finally,we present that our method improves detection accuracy by 3.8 AP compared to state-of-the-art MNC based ResNet-101 on the standard MSCOCO baseline. |
| Tasks | |
| Published | 2020-01-04 |
| URL | https://arxiv.org/abs/2001.01057v1 |
| https://arxiv.org/pdf/2001.01057v1.pdf | |
| PWC | https://paperswithcode.com/paper/pixel-semantic-revise-of-position-learning-a |
| Repo | |
| Framework | |
An optimal scheduling architecture for accelerating batch algorithms on Neural Network processor architectures
| Title | An optimal scheduling architecture for accelerating batch algorithms on Neural Network processor architectures |
| Authors | Phani Kumar Nyshadham, Mohit Sinha, Biswajit Mishra, H S Vijay |
| Abstract | In neural network topologies, algorithms are running on batches of data tensors. The batches of data are typically scheduled onto the computing cores which execute in parallel. For the algorithms running on batches of data, an optimal batch scheduling architecture is very much needed by suitably utilizing hardware resources - thereby resulting in significant reduction training and inference time. In this paper, we propose to accelerate the batch algorithms for neural networks through a scheduling architecture enabling optimal compute power utilization. The proposed optimal scheduling architecture can be built into HW or can be implemented in SW alone which can be leveraged for accelerating batch algorithms. The results demonstrate that the proposed architecture speeds up the batch algorithms compared to the previous solutions. The proposed idea applies to any HPC architecture meant for neural networks. |
| Tasks | |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.07062v1 |
| https://arxiv.org/pdf/2002.07062v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-optimal-scheduling-architecture-for |
| Repo | |
| Framework | |
SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks
| Title | SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks |
| Authors | Lumin Yang, Jiajie Zhuang, Hongbo Fu, Kun Zhou, Youyi Zheng |
| Abstract | We introduce SketchGCN, a graph convolutional neural network for semantic segmentation and labeling of free-hand sketches. We treat an input sketch as a 2D pointset, and encode the stroke structure information into graph node/edge representations. To predict the per-point labels, our SketchGCN uses graph convolution and a global-local branching network architecture to extract both intra-stroke and inter-stroke features. SketchGCN significantly improves the accuracy of the state-of-the-art methods for semantic sketch segmentation (by 11.4% in the pixel-basedmetric and 18.2% in the component-based metric over a large-scale challenging SPG dataset) and has magnitudes fewer parameters than both image-based and sequence-based methods. |
| Tasks | Semantic Segmentation |
| Published | 2020-03-02 |
| URL | https://arxiv.org/abs/2003.00678v1 |
| https://arxiv.org/pdf/2003.00678v1.pdf | |
| PWC | https://paperswithcode.com/paper/sketchgcn-semantic-sketch-segmentation-with |
| Repo | |
| Framework | |
