Paper Group ANR 1589
A Probabilistic Approach for Discovering Daily Human Mobility Patterns with Mobile Data. Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias. Achieving Fairness in Determining Medicaid Eligibility through Fairgroup Construction. Indoor image representation by high-level semantic features. Balanced off-policy …
A Probabilistic Approach for Discovering Daily Human Mobility Patterns with Mobile Data
| Title | A Probabilistic Approach for Discovering Daily Human Mobility Patterns with Mobile Data |
| Authors | Weizhu Qian, Fabrice Lauri, Franck Gechter |
| Abstract | Discovering human mobility patterns with geo-location data collected from smartphone users has been a hot research topic in recent years. In this paper, we attempt to discover daily mobile patterns based on GPS data. We view this problem from a probabilistic perspective in order to explore more information from the original GPS data compared to other conventional methods. A non-parameter Bayesian modeling method, Infinite Gaussian Mixture Model, is used to estimate the probability density for the daily mobility. Then, we use Kullback-Leibler divergence as the metrics to measure the similarity of different probability distributions. And combining Infinite Gaussian Mixture Model and Kullback-Leibler divergence, we derived an automatic clustering algorithm to discover mobility patterns for each individual user without setting the number of clusters in advance. In the experiments, the effectiveness of our method is validated on the real user data collected from different users. The results show that the IGMM-based algorithm outperforms the GMM-based algorithm. We also test our methods on the dataset with different lengths to discover the minimum data length for discovering mobility patterns. |
| Tasks | |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09355v1 |
| https://arxiv.org/pdf/1911.09355v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-probabilistic-approach-for-discovering |
| Repo | |
| Framework | |
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias
| Title | Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias |
| Authors | Stéphane d’Ascoli, Levent Sagun, Joan Bruna, Giulio Biroli |
| Abstract | Despite the phenomenal success of deep neural networks in a broad range of learning tasks, there is a lack of theory to understand the way they work. In particular, Convolutional Neural Networks (CNNs) are known to perform much better than Fully-Connected Networks (FCNs) on spatially structured data: the architectural structure of CNNs benefits from prior knowledge on the features of the data, for instance their translation invariance. The aim of this work is to understand this fact through the lens of dynamics in the loss landscape. We introduce a method that maps a CNN to its equivalent FCN (denoted as eFCN). Such an embedding enables the comparison of CNN and FCN training dynamics directly in the FCN space. We use this method to test a new training protocol, which consists in training a CNN, embedding it to FCN space at a certain ``relax time’', then resuming the training in FCN space. We observe that for all relax times, the deviation from the CNN subspace is small, and the final performance reached by the eFCN is higher than that reachable by a standard FCN of same architecture. More surprisingly, for some intermediate relax times, the eFCN outperforms the CNN it stemmed, by combining the prior information of the CNN and the expressivity of the FCN in a complementary way. The practical interest of our protocol is limited by the very large size of the highly sparse eFCN. However, it offers interesting insights into the persistence of architectural bias under stochastic gradient dynamics. It shows the existence of some rare basins in the FCN loss landscape associated with very good generalization. These can only be accessed thanks to the CNN prior, which helps navigate the landscape during the early stages of optimization. | |
| Tasks | |
| Published | 2019-06-16 |
| URL | https://arxiv.org/abs/1906.06766v2 |
| https://arxiv.org/pdf/1906.06766v2.pdf | |
| PWC | https://paperswithcode.com/paper/finding-the-needle-in-the-haystack-with |
| Repo | |
| Framework | |
Achieving Fairness in Determining Medicaid Eligibility through Fairgroup Construction
| Title | Achieving Fairness in Determining Medicaid Eligibility through Fairgroup Construction |
| Authors | Boli Fang, Miao Jiang, Jerry Shen |
| Abstract | Effective complements to human judgment, artificial intelligence techniques have started to aid human decisions in complicated social problems across the world. In the context of United States for instance, automated ML/DL classification models offer complements to human decisions in determining Medicaid eligibility. However, given the limitations in ML/DL model design, these algorithms may fail to leverage various factors for decision making, resulting in improper decisions that allocate resources to individuals who may not be in the most need. In view of such an issue, we propose in this paper the method of \textit{fairgroup construction}, based on the legal doctrine of \textit{disparate impact}, to improve the fairness of regressive classifiers. Experiments on American Community Survey dataset demonstrate that our method could be easily adapted to a variety of regressive classification models to boost their fairness in deciding Medicaid Eligibility, while maintaining high levels of classification accuracy. |
| Tasks | Decision Making |
| Published | 2019-06-01 |
| URL | https://arxiv.org/abs/1906.00128v1 |
| https://arxiv.org/pdf/1906.00128v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600128 |
| Repo | |
| Framework | |
Indoor image representation by high-level semantic features
| Title | Indoor image representation by high-level semantic features |
| Authors | Chiranjibi Sitaula, Yong Xiang, Yushu Zhang, Xuequan Lu, Sunil Aryal |
| Abstract | Indoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on pixels, color, shape/object parts or objects on images, suffer from limited capabilities in describing semantic information (e.g., object association). These techniques, therefore, involve undesired classification performance. To tackle this issue, we propose the notion of high-level semantic features and design four steps to extract them. Specifically, we first construct the objects pattern dictionary through extracting raw objects in the images, and then retrieve and extract semantic objects from the objects pattern dictionary. We finally extract our high-level semantic features based on the calculated probability and delta parameter. Experiments on three publicly available datasets (MIT-67, Scene15 and NYU V1) show that our feature extraction approach outperforms state-of-the-art feature extraction methods for indoor image classification, given a lower dimension of our features than those methods. |
| Tasks | Image Classification |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.04987v3 |
| https://arxiv.org/pdf/1906.04987v3.pdf | |
| PWC | https://paperswithcode.com/paper/indoor-image-representation-by-high-level |
| Repo | |
| Framework | |
Balanced off-policy evaluation in general action spaces
| Title | Balanced off-policy evaluation in general action spaces |
| Authors | Arjun Sondhi, David Arbour, Drew Dimmery |
| Abstract | Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present balanced off-policy evaluation (B-OPE), a generic method for estimating weights which minimize this imbalance. Estimation of these weights reduces to a binary classification problem regardless of action type. We show that minimizing the risk of the classifier implies minimization of imbalance to the desired counterfactual distribution of state-action pairs. The classifier loss is tied to the error of the off-policy estimate, allowing for easy tuning of hyperparameters. We provide experimental evidence that B-OPE improves weighting-based approaches for offline policy evaluation in both discrete and continuous action spaces. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.03694v4 |
| https://arxiv.org/pdf/1906.03694v4.pdf | |
| PWC | https://paperswithcode.com/paper/balanced-off-policy-evaluation-general-action |
| Repo | |
| Framework | |
Does Symbolic Knowledge Prevent Adversarial Fooling?
| Title | Does Symbolic Knowledge Prevent Adversarial Fooling? |
| Authors | Stefano Teso |
| Abstract | Arguments in favor of injecting symbolic knowledge into neural architectures abound. When done right, constraining a sub-symbolic model can substantially improve its performance and sample complexity and prevent it from predicting invalid configurations. Focusing on deep probabilistic (logical) graphical models – i.e., constrained joint distributions whose parameters are determined (in part) by neural nets based on low-level inputs – we draw attention to an elementary but unintended consequence of symbolic knowledge: that the resulting constraints can propagate the negative effects of adversarial examples. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.10834v1 |
| https://arxiv.org/pdf/1912.10834v1.pdf | |
| PWC | https://paperswithcode.com/paper/does-symbolic-knowledge-prevent-adversarial |
| Repo | |
| Framework | |
Unpredictability of AI
| Title | Unpredictability of AI |
| Authors | Roman V. Yampolskiy |
| Abstract | The young field of AI Safety is still in the process of identifying its challenges and limitations. In this paper, we formally describe one such impossibility result, namely Unpredictability of AI. We prove that it is impossible to precisely and consistently predict what specific actions a smarter-than-human intelligent system will take to achieve its objectives, even if we know terminal goals of the system. In conclusion, impact of Unpredictability on AI Safety is discussed. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.13053v1 |
| https://arxiv.org/pdf/1905.13053v1.pdf | |
| PWC | https://paperswithcode.com/paper/unpredictability-of-ai |
| Repo | |
| Framework | |
Auto-GNN: Neural Architecture Search of Graph Neural Networks
| Title | Auto-GNN: Neural Architecture Search of Graph Neural Networks |
| Authors | Kaixiong Zhou, Qingquan Song, Xiao Huang, Xia Hu |
| Abstract | Graph neural networks (GNN) has been successfully applied to operate on the graph-structured data. Given a specific scenario, rich human expertise and tremendous laborious trials are usually required to identify a suitable GNN architecture. It is because the performance of a GNN architecture is significantly affected by the choice of graph convolution components, such as aggregate function and hidden dimension. Neural architecture search (NAS) has shown its potential in discovering effective deep architectures for learning tasks in image and language modeling. However, existing NAS algorithms cannot be directly applied to the GNN search problem. First, the search space of GNN is different from the ones in existing NAS work. Second, the representation learning capacity of GNN architecture changes obviously with slight architecture modifications. It affects the search efficiency of traditional search methods. Third, widely used techniques in NAS such as parameter sharing might become unstable in GNN. To bridge the gap, we propose the automated graph neural networks (AGNN) framework, which aims to find an optimal GNN architecture within a predefined search space. A reinforcement learning based controller is designed to greedily validate architectures via small steps. AGNN has a novel parameter sharing strategy that enables homogeneous architectures to share parameters, based on a carefully-designed homogeneity definition. Experiments on real-world benchmark datasets demonstrate that the GNN architecture identified by AGNN achieves the best performance, comparing with existing handcrafted models and tradistional search methods. |
| Tasks | Language Modelling, Neural Architecture Search, Node Classification, Representation Learning |
| Published | 2019-09-07 |
| URL | https://arxiv.org/abs/1909.03184v2 |
| https://arxiv.org/pdf/1909.03184v2.pdf | |
| PWC | https://paperswithcode.com/paper/auto-gnn-neural-architecture-search-of-graph |
| Repo | |
| Framework | |
Fatigue-Aware Ad Creative Selection
| Title | Fatigue-Aware Ad Creative Selection |
| Authors | Daisuke Moriwaki, Komei Fujita, Shota Yasui, Takahiro Hoshino |
| Abstract | In online display advertising, selecting the most effective ad creative (ad image) for each impression is a crucial task for DSPs (Demand-Side Platforms) to fulfill their goals (click-through rate, number of conversions, revenue, and brand improvement). As widely recognized in the marketing literature, the effect of ad creative changes with the number of repetitive ad exposures. In this study, we propose an efficient and easy-to-implement ad creative selection algorithm that explicitly considers user’s psychological status when selecting ad creatives. The proposed system was deployed in a real-world production environment and tested against the baseline algorithms. The results show superiority of the proposed algorithm. |
| Tasks | |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.08936v2 |
| https://arxiv.org/pdf/1908.08936v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-contextual-bandit-algorithm-for-ad-creative |
| Repo | |
| Framework | |
Decision-Oriented Communications: Application to Energy-Efficient Resource Allocation
| Title | Decision-Oriented Communications: Application to Energy-Efficient Resource Allocation |
| Authors | Hang Zou, Chao Zhang, Samson Lasaulce, Lucas Saludjian, Patrick Panciatici |
| Abstract | In this paper, we introduce the problem of decision-oriented communications, that is, the goal of the source is to send the right amount of information in order for the intended destination to execute a task. More specifically, we restrict our attention to how the source should quantize information so that the destination can maximize a utility function which represents the task to be executed only knowing the quantized information. For example, for utility functions under the form $u\left(\boldsymbol{x};\ \boldsymbol{g}\right)$, $\boldsymbol{x}$ might represent a decision in terms of using some radio resources and $\boldsymbol{g}$ the system state which is only observed through its quantized version $Q(\boldsymbol{g})$. Both in the case where the utility function is known and the case where it is only observed through its realizations, we provide solutions to determine such a quantizer. We show how this approach applies to energy-efficient power allocation. In particular, it is seen that quantizing the state very roughly is perfectly suited to sum-rate-type function maximization, whereas energy-efficiency metrics are more sensitive to imperfections. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07339v1 |
| https://arxiv.org/pdf/1905.07339v1.pdf | |
| PWC | https://paperswithcode.com/paper/decision-oriented-communications-application |
| Repo | |
| Framework | |
SAO WMT19 Test Suite: Machine Translation of Audit Reports
| Title | SAO WMT19 Test Suite: Machine Translation of Audit Reports |
| Authors | Tereza Vojtěchová, Michal Novák, Miloš Klouček, Ondřej Bojar |
| Abstract | This paper describes a machine translation test set of documents from the auditing domain and its use as one of the “test suites” in the WMT19 News Translation Task for translation directions involving Czech, English and German. Our evaluation suggests that current MT systems optimized for the general news domain can perform quite well even in the particular domain of audit reports. The detailed manual evaluation however indicates that deep factual knowledge of the domain is necessary. For the naked eye of a non-expert, translations by many systems seem almost perfect and automatic MT evaluation with one reference is practically useless for considering these details. Furthermore, we show on a sample document from the domain of agreements that even the best systems completely fail in preserving the semantics of the agreement, namely the identity of the parties. |
| Tasks | Machine Translation |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01701v1 |
| https://arxiv.org/pdf/1909.01701v1.pdf | |
| PWC | https://paperswithcode.com/paper/sao-wmt19-test-suite-machine-translation-of-1 |
| Repo | |
| Framework | |
A Decentralized Parallel Algorithm for Training Generative Adversarial Nets
| Title | A Decentralized Parallel Algorithm for Training Generative Adversarial Nets |
| Authors | Mingrui Liu, Wei Zhang, Youssef Mroueh, Xiaodong Cui, Jerret Ross, Tianbao Yang, Payel Das |
| Abstract | Generative Adversarial Networks (GANs) are powerful class of generative models in the deep learning community. Current practice on large-scale GAN training~\citep{brock2018large} utilizes large models and distributed large-batch training strategies, and is implemented on deep learning frameworks (e.g., TensorFlow, PyTorch, etc.) designed in a centralized manner. In the centralized network topology, every worker needs to communicate with the central node. However, when the network bandwidth is low or network latency is high, the performance would be significantly degraded. Despite recent progress on decentralized algorithms for training deep neural networks, it remains unclear whether it is possible to train GANs in a decentralized manner. The main difficulty lies at handling the nonconvex-nonconcave min-max optimization and the decentralized communication simultaneously. In this paper, we address this difficulty by designing the \textbf{first gradient-based decentralized parallel algorithm} which allows workers to have multiple rounds of communications in one iteration and to update the discriminator and generator simultaneously, and this design makes it amenable for the convergence analysis of the proposed decentralized algorithm. Theoretically, our proposed decentralized algorithm is able to solve a class of non-convex non-concave min-max problems with provable non-asymptotic convergence to first-order stationary point. Experimental results on GANs demonstrate the effectiveness of the proposed algorithm. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12999v4 |
| https://arxiv.org/pdf/1910.12999v4.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-parallel-algorithm-for-training |
| Repo | |
| Framework | |
Characterizing Attacks on Deep Reinforcement Learning
| Title | Characterizing Attacks on Deep Reinforcement Learning |
| Authors | Chaowei Xiao, Xinlei Pan, Warren He, Jian Peng, Mingjie Sun, Jinfeng Yi, Mingyan Liu, Bo Li, Dawn Song |
| Abstract | Deep reinforcement learning (DRL) has achieved great success in various applications. However, recent studies show that machine learning models are vulnerable to adversarial attacks. DRL models have been attacked by adding perturbations to observations. While such observation based attack is only one aspect of potential attacks on DRL, other forms of attacks which are more practical require further analysis, such as manipulating environment dynamics. Therefore, we propose to understand the vulnerabilities of DRL from various perspectives and provide a thorough taxonomy of potential attacks. We conduct the first set of experiments on the unexplored parts within the taxonomy. In addition to current observation based attacks against DRL, we propose the first targeted attacks based on action space and environment dynamics. We also introduce the online sequential attacks based on temporal consistency information among frames. To better estimate gradient in black-box setting, we propose a sampling strategy and theoretically prove its efficiency and estimation error bound. We conduct extensive experiments to compare the effectiveness of different attacks with several baselines in various environments, including game playing, robotics control, and autonomous driving. |
| Tasks | Autonomous Driving |
| Published | 2019-07-21 |
| URL | https://arxiv.org/abs/1907.09470v2 |
| https://arxiv.org/pdf/1907.09470v2.pdf | |
| PWC | https://paperswithcode.com/paper/characterizing-attacks-on-deep-reinforcement |
| Repo | |
| Framework | |
Blameworthiness in Multi-Agent Settings
| Title | Blameworthiness in Multi-Agent Settings |
| Authors | Meir Friedenberg, Joseph Y. Halpern |
| Abstract | We provide a formal definition of blameworthiness in settings where multiple agents can collaborate to avoid a negative outcome. We first provide a method for ascribing blameworthiness to groups relative to an epistemic state (a distribution over causal models that describe how the outcome might arise). We then show how we can go from an ascription of blameworthiness for groups to an ascription of blameworthiness for individuals using a standard notion from cooperative game theory, the Shapley value. We believe that getting a good notion of blameworthiness in a group setting will be critical for designing autonomous agents that behave in a moral manner. |
| Tasks | |
| Published | 2019-03-11 |
| URL | http://arxiv.org/abs/1903.04102v1 |
| http://arxiv.org/pdf/1903.04102v1.pdf | |
| PWC | https://paperswithcode.com/paper/blameworthiness-in-multi-agent-settings |
| Repo | |
| Framework | |
Point cloud denoising based on tensor Tucker decomposition
| Title | Point cloud denoising based on tensor Tucker decomposition |
| Authors | Jianze Li, Xiao-Ping Zhang, Tuan Tran |
| Abstract | In this paper, we propose a new algorithm for point cloud denoising based on the tensor Tucker decomposition. We first represent the local surface patches of a noisy point cloud to be matrices by their distances to a reference point, and stack the similar patch matrices to be a 3rd order tensor. Then we use the Tucker decomposition to compress this patch tensor to be a core tensor of smaller size. We consider this core tensor as the frequency domain and remove the noise by manipulating the hard thresholding. Finally, all the fibers of the denoised patch tensor are placed back, and the average is taken if there are more than one estimators overlapped. The experimental evaluation shows that the proposed algorithm outperforms the state-of-the-art graph Laplacian regularized (GLR) algorithm when the Gaussian noise is high ($\sigma=0.1$), and the GLR algorithm is better in lower noise cases ($\sigma=0.04, 0.05, 0.08$). |
| Tasks | Denoising |
| Published | 2019-02-20 |
| URL | https://arxiv.org/abs/1902.07602v2 |
| https://arxiv.org/pdf/1902.07602v2.pdf | |
| PWC | https://paperswithcode.com/paper/point-cloud-denoising-based-on-tensor-tucker |
| Repo | |
| Framework | |
