Paper Group ANR 781
Bayesian Network Based Label Correlation Analysis For Multi-label Classifier Chain. An Automatic Digital Terrain Generation Technique for Terrestrial Sensing and Virtual Reality Applications. Modelling Dynamic Interactions between Relevance Dimensions. Cognitive Model Priors for Predicting Human Decisions. Unremarkable AI: Fitting Intelligent Decis …
Bayesian Network Based Label Correlation Analysis For Multi-label Classifier Chain
| Title | Bayesian Network Based Label Correlation Analysis For Multi-label Classifier Chain |
| Authors | Ran Wang, Suhe Ye, Ke Li, Sam Kwong |
| Abstract | Classifier chain (CC) is a multi-label learning approach that constructs a sequence of binary classifiers according to a label order. Each classifier in the sequence is responsible for predicting the relevance of one label. When training the classifier for a label, proceeding labels will be taken as extended features. If the extended features are highly correlated to the label, the performance will be improved, otherwise, the performance will not be influenced or even degraded. How to discover label correlation and determine the label order is critical for CC approach. This paper employs Bayesian network (BN) to model the label correlations and proposes a new BN-based CC method (BNCC). First, conditional entropy is used to describe the dependency relations among labels. Then, a BN is built up by taking nodes as labels and weights of edges as their dependency relations. A new scoring function is proposed to evaluate a BN structure, and a heuristic algorithm is introduced to optimize the BN. At last, by applying topological sorting on the nodes of the optimized BN, the label order for constructing CC model is derived. Experimental comparisons demonstrate the feasibility and effectiveness of the proposed method. |
| Tasks | Multi-Label Learning |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.02172v1 |
| https://arxiv.org/pdf/1908.02172v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-network-based-label-correlation |
| Repo | |
| Framework | |
An Automatic Digital Terrain Generation Technique for Terrestrial Sensing and Virtual Reality Applications
| Title | An Automatic Digital Terrain Generation Technique for Terrestrial Sensing and Virtual Reality Applications |
| Authors | Lee Easson, Alireza Tavakkoli, Jonathan Greenberg |
| Abstract | The identification and modeling of the terrain from point cloud data is an important component of Terrestrial Remote Sensing (TRS) applications. The main focus in terrain modeling is capturing details of complex geological features of landforms. Traditional terrain modeling approaches rely on the user to exert control over terrain features. However, relying on the user input to manually develop the digital terrain becomes intractable when considering the amount of data generated by new remote sensing systems capable of producing massive aerial and ground-based point clouds from scanned environments. This article provides a novel terrain modeling technique capable of automatically generating accurate and physically realistic Digital Terrain Models (DTM) from a variety of point cloud data. The proposed method runs efficiently on large-scale point cloud data with real-time performance over large segments of terrestrial landforms. Moreover, generated digital models are designed to effectively render within a Virtual Reality (VR) environment in real time. The paper concludes with an in-depth discussion of possible research directions and outstanding technical and scientific challenges to improve the proposed approach. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04944v1 |
| https://arxiv.org/pdf/1910.04944v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-automatic-digital-terrain-generation |
| Repo | |
| Framework | |
Modelling Dynamic Interactions between Relevance Dimensions
| Title | Modelling Dynamic Interactions between Relevance Dimensions |
| Authors | Sagar Uprety, Shahram Dehdashti, Lauren Fell, Peter Bruza, Dawei Song |
| Abstract | Relevance is an underlying concept in the field of Information Science and Retrieval. It is a cognitive notion consisting of several different criteria or dimensions. Theoretical models of relevance allude to interdependence between these dimensions, where their interaction and fusion leads to the final inference of relevance. We study the interaction between the relevance dimensions using the mathematical framework of Quantum Theory. It is considered a generalised framework to model decision making under uncertainty, involving multiple perspectives and influenced by context. Specifically, we conduct a user study by constructing the cognitive analogue of a famous experiment in Quantum Physics. The data is used to construct a complex-valued vector space model of the user’s cognitive state, which is used to explain incompatibility and interference between relevance dimensions. The implications of our findings to inform the design of Information Retrieval systems are also discussed. |
| Tasks | Decision Making, Decision Making Under Uncertainty, Information Retrieval |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.10943v1 |
| https://arxiv.org/pdf/1907.10943v1.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-dynamic-interactions-between |
| Repo | |
| Framework | |
Cognitive Model Priors for Predicting Human Decisions
| Title | Cognitive Model Priors for Predicting Human Decisions |
| Authors | David D. Bourgin, Joshua C. Peterson, Daniel Reichman, Thomas L. Griffiths, Stuart J. Russell |
| Abstract | Human decision-making underlies all economic behavior. For the past four decades, human decision-making under uncertainty has continued to be explained by theoretical models based on prospect theory, a framework that was awarded the Nobel Prize in Economic Sciences. However, theoretical models of this kind have developed slowly, and robust, high-precision predictive models of human decisions remain a challenge. While machine learning is a natural candidate for solving these problems, it is currently unclear to what extent it can improve predictions obtained by current theories. We argue that this is mainly due to data scarcity, since noisy human behavior requires massive sample sizes to be accurately captured by off-the-shelf machine learning methods. To solve this problem, what is needed are machine learning models with appropriate inductive biases for capturing human behavior, and larger datasets. We offer two contributions towards this end: first, we construct “cognitive model priors” by pretraining neural networks with synthetic data generated by cognitive models (i.e., theoretical models developed by cognitive psychologists). We find that fine-tuning these networks on small datasets of real human decisions results in unprecedented state-of-the-art improvements on two benchmark datasets. Second, we present the first large-scale dataset for human decision-making, containing over 240,000 human judgments across over 13,000 decision problems. This dataset reveals the circumstances where cognitive model priors are useful, and provides a new standard for benchmarking prediction of human decisions under uncertainty. |
| Tasks | Decision Making, Decision Making Under Uncertainty |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09397v1 |
| https://arxiv.org/pdf/1905.09397v1.pdf | |
| PWC | https://paperswithcode.com/paper/cognitive-model-priors-for-predicting-human |
| Repo | |
| Framework | |
Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes
| Title | Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes |
| Authors | Qian Yang, Aaron Steinfeld, John Zimmerman |
| Abstract | Clinical decision support tools (DST) promise improved healthcare outcomes by offering data-driven insights. While effective in lab settings, almost all DSTs have failed in practice. Empirical research diagnosed poor contextual fit as the cause. This paper describes the design and field evaluation of a radically new form of DST. It automatically generates slides for clinicians’ decision meetings with subtly embedded machine prognostics. This design took inspiration from the notion of “Unremarkable Computing”, that by augmenting the users’ routines technology/AI can have significant importance for the users yet remain unobtrusive. Our field evaluation suggests clinicians are more likely to encounter and embrace such a DST. Drawing on their responses, we discuss the importance and intricacies of finding the right level of unremarkableness in DST design, and share lessons learned in prototyping critical AI systems as a situated experience. |
| Tasks | Decision Making |
| Published | 2019-04-21 |
| URL | http://arxiv.org/abs/1904.09612v1 |
| http://arxiv.org/pdf/1904.09612v1.pdf | |
| PWC | https://paperswithcode.com/paper/unremarkable-ai-fitting-intelligent-decision |
| Repo | |
| Framework | |
A Distributionally Robust Boosting Algorithm
| Title | A Distributionally Robust Boosting Algorithm |
| Authors | Jose Blanchet, Yang Kang, Fan Zhang, Zhangyi Hu |
| Abstract | Distributionally Robust Optimization (DRO) has been shown to provide a flexible framework for decision making under uncertainty and statistical estimation. For example, recent works in DRO have shown that popular statistical estimators can be interpreted as the solutions of suitable formulated data-driven DRO problems. In turn, this connection is used to optimally select tuning parameters in terms of a principled approach informed by robustness considerations. This paper contributes to this growing literature, connecting DRO and statistics, by showing how boosting algorithms can be studied via DRO. We propose a boosting type algorithm, named DRO-Boosting, as a procedure to solve our DRO formulation. Our DRO-Boosting algorithm recovers Adaptive Boosting (AdaBoost) in particular, thus showing that AdaBoost is effectively solving a DRO problem. We apply our algorithm to a financial dataset on credit card default payment prediction. We find that our approach compares favorably to alternative boosting methods which are widely used in practice. |
| Tasks | Decision Making, Decision Making Under Uncertainty |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.07845v1 |
| https://arxiv.org/pdf/1905.07845v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-distributionally-robust-boosting-algorithm |
| Repo | |
| Framework | |
A Survey of Methods to Leverage Monolingual Data in Low-resource Neural Machine Translation
| Title | A Survey of Methods to Leverage Monolingual Data in Low-resource Neural Machine Translation |
| Authors | Ilshat Gibadullin, Aidar Valeev, Albina Khusainova, Adil Khan |
| Abstract | Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora. However, the quality of machine translation for low-resource languages leaves much to be desired. There are several approaches to mitigate this problem, such as transfer learning, semi-supervised and unsupervised learning techniques. In this paper, we review the existing methods, where the main idea is to exploit the power of monolingual data, which, compared to parallel, is usually easier to obtain and significantly greater in amount. |
| Tasks | Low-Resource Neural Machine Translation, Machine Translation, Transfer Learning |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00373v1 |
| https://arxiv.org/pdf/1910.00373v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-methods-to-leverage-monolingual |
| Repo | |
| Framework | |
Learning Attribute Patterns in High-Dimensional Structured Latent Attribute Models
| Title | Learning Attribute Patterns in High-Dimensional Structured Latent Attribute Models |
| Authors | Yuqi Gu, Gongjun Xu |
| Abstract | Structured latent attribute models (SLAMs) are a special family of discrete latent variable models widely used in social and biological sciences. This paper considers the problem of learning significant attribute patterns from a SLAM with potentially high-dimensional configurations of the latent attributes. We address the theoretical identifiability issue, propose a penalized likelihood method for the selection of the attribute patterns, and further establish the selection consistency in such an overfitted SLAM with diverging number of latent patterns. The good performance of the proposed methodology is illustrated by simulation studies and two real datasets in educational assessment. |
| Tasks | Latent Variable Models |
| Published | 2019-04-08 |
| URL | https://arxiv.org/abs/1904.04378v2 |
| https://arxiv.org/pdf/1904.04378v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-attribute-patterns-in-high |
| Repo | |
| Framework | |
Efficient Image Splicing Localization via Contrastive Feature Extraction
| Title | Efficient Image Splicing Localization via Contrastive Feature Extraction |
| Authors | Ronald Salloum, C. -C. Jay Kuo |
| Abstract | In this work, we propose a new data visualization and clustering technique for discovering discriminative structures in high-dimensional data. This technique, referred to as cPCA++, utilizes the fact that the interesting features of a “target” dataset may be obscured by high variance components during traditional PCA. By analyzing what is referred to as a “background” dataset (i.e., one that exhibits the high variance principal components but not the interesting structures), our technique is capable of efficiently highlighting the structure that is unique to the “target” dataset. Similar to another recently proposed algorithm called “contrastive PCA” (cPCA), the proposed cPCA++ method identifies important dataset specific patterns that are not detected by traditional PCA in a wide variety of settings. However, the proposed cPCA++ method is significantly more efficient than cPCA, because it does not require the parameter sweep in the latter approach. We applied the cPCA++ method to the problem of image splicing localization. In this application, we utilize authentic edges as the background dataset and the spliced edges as the target dataset. The proposed method is significantly more efficient than state-of-the-art methods, as the former does not require iterative updates of filter weights via stochastic gradient descent and backpropagation, nor the training of a classifier. Furthermore, the cPCA++ method is shown to provide performance scores comparable to the state-of-the-art Multi-task Fully Convolutional Network (MFCN). |
| Tasks | |
| Published | 2019-01-22 |
| URL | http://arxiv.org/abs/1901.07172v1 |
| http://arxiv.org/pdf/1901.07172v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-image-splicing-localization-via |
| Repo | |
| Framework | |
Online Evaluation of Audiences for Targeted Advertising via Bandit Experiments
| Title | Online Evaluation of Audiences for Targeted Advertising via Bandit Experiments |
| Authors | Tong Geng, Xiliang Lin, Harikesh S. Nair |
| Abstract | Firms implementing digital advertising campaigns face a complex problem in determining the right match between their advertising creatives and target audiences. Typical solutions to the problem have leveraged non-experimental methods, or used “split-testing” strategies that have not explicitly addressed the complexities induced by targeted audiences that can potentially overlap with one another. This paper presents an adaptive algorithm that addresses the problem via online experimentation. The algorithm is set up as a contextual bandit and addresses the overlap issue by partitioning the target audiences into disjoint, non-overlapping sub-populations. It learns an optimal creative display policy in the disjoint space, while assessing in parallel which creative has the best match in the space of possibly overlapping target audiences. Experiments show that the proposed method is more efficient compared to naive “split-testing” or non-adaptive “A/B/n” testing based methods. We also describe a testing product we built that uses the algorithm. The product is currently deployed on the advertising platform of JD.com, an eCommerce company and a publisher of digital ads in China. |
| Tasks | |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02178v3 |
| https://arxiv.org/pdf/1907.02178v3.pdf | |
| PWC | https://paperswithcode.com/paper/online-evaluation-of-audiences-for-targeted |
| Repo | |
| Framework | |
Discovering Common Change-Point Patterns in Functional Connectivity Across Subjects
| Title | Discovering Common Change-Point Patterns in Functional Connectivity Across Subjects |
| Authors | Mengyu Dai, Zhengwu Zhang, Anuj Srivastava |
| Abstract | This paper studies change-points in human brain functional connectivity (FC) and seeks patterns that are common across multiple subjects under identical external stimulus. FC relates to the similarity of fMRI responses across different brain regions when the brain is simply resting or performing a task. While the dynamic nature of FC is well accepted, this paper develops a formal statistical test for finding {\it change-points} in times series associated with FC. It represents short-term connectivity by a symmetric positive-definite matrix, and uses a Riemannian metric on this space to develop a graphical method for detecting change-points in a time series of such matrices. It also provides a graphical representation of estimated FC for stationary subintervals in between the detected change-points. Furthermore, it uses a temporal alignment of the test statistic, viewed as a real-valued function over time, to remove inter-subject variability and to discover common change-point patterns across subjects. This method is illustrated using data from Human Connectome Project (HCP) database for multiple subjects and tasks. |
| Tasks | Time Series |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.12023v1 |
| http://arxiv.org/pdf/1904.12023v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-common-change-point-patterns-in |
| Repo | |
| Framework | |
Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation
| Title | Entropy-Enhanced Multimodal Attention Model for Scene-Aware Dialogue Generation |
| Authors | Kuan-Yen Lin, Chao-Chun Hsu, Yun-Nung Chen, Lun-Wei Ku |
| Abstract | With increasing information from social media, there are more and more videos available. Therefore, the ability to reason on a video is important and deserves to be discussed. TheDialog System Technology Challenge (DSTC7) (Yoshino et al. 2018) proposed an Audio Visual Scene-aware Dialog (AVSD) task, which contains five modalities including video, dialogue history, summary, and caption, as a scene-aware environment. In this paper, we propose the entropy-enhanced dynamic memory network (DMN) to effectively model video modality. The attention-based GRU in the proposed model can improve the model’s ability to comprehend and memorize sequential information. The entropy mechanism can control the attention distribution higher, so each to-be-answered question can focus more specifically on a small set of video segments. After the entropy-enhanced DMN secures the video context, we apply an attention model that in-corporates summary and caption to generate an accurate answer given the question about the video. In the official evaluation, our system can achieve improved performance against the released baseline model for both subjective and objective evaluation metrics. |
| Tasks | Dialogue Generation, Scene-Aware Dialogue |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08191v1 |
| https://arxiv.org/pdf/1908.08191v1.pdf | |
| PWC | https://paperswithcode.com/paper/entropy-enhanced-multimodal-attention-model |
| Repo | |
| Framework | |
Comment on “Solving Statistical Mechanics Using VANs”: Introducing saVANt - VANs Enhanced by Importance and MCMC Sampling
| Title | Comment on “Solving Statistical Mechanics Using VANs”: Introducing saVANt - VANs Enhanced by Importance and MCMC Sampling |
| Authors | Kim Nicoli, Pan Kessel, Nils Strodthoff, Wojciech Samek, Klaus-Robert Müller, Shinichi Nakajima |
| Abstract | In this comment on “Solving Statistical Mechanics Using Variational Autoregressive Networks” by Wu et al., we propose a subtle yet powerful modification of their approach. We show that the inherent sampling error of their method can be corrected by using neural network-based MCMC or importance sampling which leads to asymptotically unbiased estimators for physical quantities. This modification is possible due to a singular property of VANs, namely that they provide the exact sample probability. With these modifications, we believe that their method could have a substantially greater impact on various important fields of physics, including strongly-interacting field theories and statistical physics. |
| Tasks | |
| Published | 2019-03-26 |
| URL | http://arxiv.org/abs/1903.11048v1 |
| http://arxiv.org/pdf/1903.11048v1.pdf | |
| PWC | https://paperswithcode.com/paper/comment-on-solving-statistical-mechanics |
| Repo | |
| Framework | |
NEARBY Platform for Detecting Asteroids in Astronomical Images Using Cloud-based Containerized Applications
| Title | NEARBY Platform for Detecting Asteroids in Astronomical Images Using Cloud-based Containerized Applications |
| Authors | V. Bacu, A. Sabou, T. Stefanut, D. Gorgan, O. Vaduvescu |
| Abstract | The continuing monitoring and surveying of the nearby space to detect Near Earth Objects (NEOs) and Near Earth Asteroids (NEAs) are essential because of the threats that this kind of objects impose on the future of our planet. We need more computational resources and advanced algorithms to deal with the exponential growth of the digital cameras’ performances and to be able to process (in near real-time) data coming from large surveys. This paper presents a software platform called NEARBY that supports automated detection of moving sources (asteroids) among stars from astronomical images. The detection procedure is based on the classic “blink” detection and, after that, the system supports visual analysis techniques to validate the moving sources, assisted by static and dynamical presentations. |
| Tasks | |
| Published | 2019-01-14 |
| URL | http://arxiv.org/abs/1901.04248v1 |
| http://arxiv.org/pdf/1901.04248v1.pdf | |
| PWC | https://paperswithcode.com/paper/nearby-platform-for-detecting-asteroids-in |
| Repo | |
| Framework | |
Nonlocal Patches based Gaussian Mixture Model for Image Inpainting
| Title | Nonlocal Patches based Gaussian Mixture Model for Image Inpainting |
| Authors | Wei Wan, Jun Liu |
| Abstract | We consider the inpainting problem for noisy images. It is very challenge to suppress noise when image inpainting is processed. An image patches based nonlocal variational method is proposed to simultaneously inpainting and denoising in this paper. Our approach is developed on an assumption that the small image patches should be obeyed a distribution which can be described by a high dimension Gaussian Mixture Model. By a maximum a posteriori (MAP) estimation, we formulate a new regularization term according to the log-likelihood function of the mixture model. To optimize this regularization term efficiently, we adopt the idea of the Expectation Maximum (EM) algorithm. In which, the expectation step can give an adaptive weighting function which can be regarded as a nonlocal connections among pixels. Using this fact, we built a framework for non-local image inpainting under noise. Moreover, we mathematically prove the existence of minimizer for the proposed inpainting model. By using a spitting algorithm, the proposed model are able to realize image inpainting and denoising simultaneously. Numerical results show that the proposed method can produce impressive reconstructed results when the inpainting region is rather large. |
| Tasks | Denoising, Image Inpainting |
| Published | 2019-09-22 |
| URL | https://arxiv.org/abs/1909.09932v1 |
| https://arxiv.org/pdf/1909.09932v1.pdf | |
| PWC | https://paperswithcode.com/paper/190909932 |
| Repo | |
| Framework | |
