January 31, 2020

3154 words 15 mins read

Paper Group ANR 23

Informing a BDI Player Model for an Interactive Narrative. Bayes Imbalance Impact Index: A Measure of Class Imbalanced Dataset for Classification Problem. Conservative Wasserstein Training for Pose Estimation. Fast and Secure Distributed Learning in High Dimension. Tactile Mapping and Localization from High-Resolution Tactile Imprints. Detecting to …

Informing a BDI Player Model for an Interactive Narrative


Title	Informing a BDI Player Model for an Interactive Narrative
Authors	Jessica Rivera-Villicana, Fabio Zambetta, James Harland, Marsha Berry
Abstract	This work focuses on studying players behaviour in interactive narratives with the aim to simulate their choices. Besides sub-optimal player behaviour due to limited knowledge about the environment, the difference in each player’s style and preferences represents a challenge when trying to make an intelligent system mimic their actions. Based on observations from players interactions with an extract from the interactive fiction Anchorhead, we created a player profile to guide the behaviour of a generic player model based on the BDI (Belief-Desire-Intention) model of agency. We evaluated our approach using qualitative and quantitative methods and found that the player profile can improve the performance of the BDI player model. However, we found that players self-assessment did not yield accurate data to populate their player profile under our current approach.
Tasks
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10414v1
PDF	https://arxiv.org/pdf/1909.10414v1.pdf
PWC	https://paperswithcode.com/paper/190910414
Repo
Framework

Bayes Imbalance Impact Index: A Measure of Class Imbalanced Dataset for Classification Problem


Title	Bayes Imbalance Impact Index: A Measure of Class Imbalanced Dataset for Classification Problem
Authors	Yang Lu, Yiu-ming Cheung, Yuan Yan Tang
Abstract	Recent studies have shown that imbalance ratio is not the only cause of the performance loss of a classifier in imbalanced data classification. In fact, other data factors, such as small disjuncts, noises and overlapping, also play the roles in tandem with imbalance ratio, which makes the problem difficult. Thus far, the empirical studies have demonstrated the relationship between the imbalance ratio and other data factors only. To the best of our knowledge, there is no any measurement about the extent of influence of class imbalance on the classification performance of imbalanced data. Further, it is also unknown for a dataset which data factor is actually the main barrier for classification. In this paper, we focus on Bayes optimal classifier and study the influence of class imbalance from a theoretical perspective. Accordingly, we propose an instance measure called Individual Bayes Imbalance Impact Index ($IBI^3$) and a data measure called Bayes Imbalance Impact Index ($BI^3$). $IBI^3$ and $BI^3$ reflect the extent of influence purely by the factor of imbalance in terms of each minority class sample and the whole dataset, respectively. Therefore, $IBI^3$ can be used as an instance complexity measure of imbalance and $BI^3$ is a criterion to show the degree of how imbalance deteriorates the classification. As a result, we can therefore use $BI^3$ to judge whether it is worth using imbalance recovery methods like sampling or cost-sensitive methods to recover the performance loss of a classifier. The experiments show that $IBI^3$ is highly consistent with the increase of prediction score made by the imbalance recovery methods and $BI^3$ is highly consistent with the improvement of F1 score made by the imbalance recovery methods on both synthetic and real benchmark datasets.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10173v1
PDF	http://arxiv.org/pdf/1901.10173v1.pdf
PWC	https://paperswithcode.com/paper/bayes-imbalance-impact-index-a-measure-of
Repo
Framework

Conservative Wasserstein Training for Pose Estimation


Title	Conservative Wasserstein Training for Pose Estimation
Authors	Xiaofeng Liu, Yang Zou, Tong Che, Peng Ding, Ping Jia, Jane You, Kumar B. V. K
Abstract	This paper targets the task with discrete and periodic class labels ($e.g.,$ pose/orientation estimation) in the context of deep learning. The commonly used cross-entropy or regression loss is not well matched to this problem as they ignore the periodic nature of the labels and the class similarity, or assume labels are continuous value. We propose to incorporate inter-class correlations in a Wasserstein training framework by pre-defining ($i.e.,$ using arc length of a circle) or adaptively learning the ground metric. We extend the ground metric as a linear, convex or concave increasing function $w.r.t.$ arc length from an optimization perspective. We also propose to construct the conservative target labels which model the inlier and outlier noises using a wrapped unimodal-uniform mixture distribution. Unlike the one-hot setting, the conservative label makes the computation of Wasserstein distance more challenging. We systematically conclude the practical closed-form solution of Wasserstein distance for pose data with either one-hot or conservative target label. We evaluate our method on head, body, vehicle and 3D object pose benchmarks with exhaustive ablation studies. The Wasserstein loss obtaining superior performance over the current methods, especially using convex mapping function for ground metric, conservative label, and closed-form solution.
Tasks	Pose Estimation
Published	2019-11-03
URL	https://arxiv.org/abs/1911.00962v1
PDF	https://arxiv.org/pdf/1911.00962v1.pdf
PWC	https://paperswithcode.com/paper/conservative-wasserstein-training-for-pose-1
Repo
Framework

Fast and Secure Distributed Learning in High Dimension


Title	Fast and Secure Distributed Learning in High Dimension
Authors	El-Mahdi El-Mhamdi, Rachid Guerraoui
Abstract	Modern machine learning is distributed and the work of several machines is typically aggregated by \emph{averaging} which is the optimal rule in terms of speed, offering a speedup of $n$ (with respect to using a single machine) when $n$ processes are learning together. Distributing data and models poses however fundamental vulnerabilities, be they to software bugs, asynchrony, or worse, to malicious attackers controlling some machines or injecting misleading data in the network. Such behavior is best modeled as Byzantine failures, and averaging does not tolerate a single one from a worker. Krum, the first provably Byzantine resilient aggregation rule for SGD only uses one worker per step, which hampers its speed of convergence, especially in best case conditions when none of the workers is actually Byzantine. An idea, coined multi-Krum, of using $m$ different workers per step was mentioned, without however any proof neither on its Byzantine resilience nor on its slowdown. More recently, it was shown that in high dimensional machine learning, guaranteeing convergence is not a sufficient condition for \emph{strong} Byzantine resilience. A improvement on Krum, coined Bulyan, was proposed and proved to guarantee stronger resilience. However, Bulyan suffers from the same weakness of Krum: using only one worker per step. This adds up to the aforementioned open problem and leaves the crucial need for both fast and strong Byzantine resilience unfulfilled. The present paper proposes using Bulyan over Multi-Krum (we call it Multi-Bulyan), a combination for which we provide proofs of strong Byzantine resilience, as well as an ${\frac{m}{n}}$ slowdown, compared to averaging, the fastest (but non Byzantine resilient) rule for distributed machine learning, finally we prove that Multi-Bulyan inherits the $O(d)$ merits of both multi-Krum and Bulyan.
Tasks
Published	2019-05-05
URL	https://arxiv.org/abs/1905.04374v1
PDF	https://arxiv.org/pdf/1905.04374v1.pdf
PWC	https://paperswithcode.com/paper/190504374
Repo
Framework

Tactile Mapping and Localization from High-Resolution Tactile Imprints


Title	Tactile Mapping and Localization from High-Resolution Tactile Imprints
Authors	Maria Bauza, Oleguer Canal, Alberto Rodriguez
Abstract	This work studies the problem of shape reconstruction and object localization using a vision-based tactile sensor, GelSlim. The main contributions are the recovery of local shapes from contact, an approach to reconstruct the tactile shape of objects from tactile imprints, and an accurate method for object localization of previously reconstructed objects. The algorithms can be applied to a large variety of 3D objects and provide accurate tactile feedback for in-hand manipulation. Results show that by exploiting the dense tactile information we can reconstruct the shape of objects with high accuracy and do on-line object identification and localization, opening the door to reactive manipulation guided by tactile sensing. We provide videos and supplemental information in the project’s website http://web.mit.edu/mcube/research/tactile_localization.html.
Tasks	Object Localization
Published	2019-04-24
URL	https://arxiv.org/abs/1904.10944v2
PDF	https://arxiv.org/pdf/1904.10944v2.pdf
PWC	https://paperswithcode.com/paper/tactile-mapping-and-localization-from-high
Repo
Framework

Detecting total hip replacement prosthesis design on preoperative radiographs using deep convolutional neural network


Title	Detecting total hip replacement prosthesis design on preoperative radiographs using deep convolutional neural network
Authors	Alireza Borjali, Antonia F. Chen, Orhun K. Muratoglu, Mohammad A. Morid, Kartik M. Varadarajan
Abstract	Identifying the design of a failed implant is a key step in preoperative planning of revision total joint arthroplasty. Manual identification of the implant design from radiographic images is time consuming and prone to error. Failure to identify the implant design preoperatively can lead to increased operating room time, more complex surgery, increased blood loss, increased bone loss, increased recovery time, and overall increased healthcare costs. In this study, we present a novel, fully automatic and interpretable approach to identify the design of total hip replacement (THR) implants from plain radiographs using deep convolutional neural network (CNN). CNN achieved 100% accuracy in identification of three commonly used THR implant designs. Such CNN can be used to automatically identify the design of a failed THR implant preoperatively in just a few seconds, saving time and improving the identification accuracy. This can potentially improve patient outcomes, free practitioners time, and reduce healthcare costs.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.12387v1
PDF	https://arxiv.org/pdf/1911.12387v1.pdf
PWC	https://paperswithcode.com/paper/detecting-total-hip-replacement-prosthesis
Repo
Framework

Grand Challenge of 106-Point Facial Landmark Localization


Title	Grand Challenge of 106-Point Facial Landmark Localization
Authors	Yinglu Liu, Hao Shen, Yue Si, Xiaobo Wang, Xiangyu Zhu, Hailin Shi, Zhibin Hong, Hanqi Guo, Ziyuan Guo, Yanqin Chen, Bi Li, Teng Xi, Jun Yu, Haonian Xie, Guochen Xie, Mengyan Li, Qing Lu, Zengfu Wang, Shenqi Lai, Zhenhua Chai, Xiaoming Wei
Abstract	Facial landmark localization is a very crucial step in numerous face related applications, such as face recognition, facial pose estimation, face image synthesis, etc. However, previous competitions on facial landmark localization (i.e., the 300-W, 300-VW and Menpo challenges) aim to predict 68-point landmarks, which are incompetent to depict the structure of facial components. In order to overcome this problem, we construct a challenging dataset, named JD-landmark. Each image is manually annotated with 106-point landmarks. This dataset covers large variations on pose and expression, which brings a lot of difficulties to predict accurate landmarks. We hold a 106-point facial landmark localization competition1 on this dataset in conjunction with IEEE International Conference on Multimedia and Expo (ICME) 2019. The purpose of this competition is to discover effective and robust facial landmark localization approaches.
Tasks	Face Alignment, Face Recognition, Image Generation, Pose Estimation
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03469v3
PDF	https://arxiv.org/pdf/1905.03469v3.pdf
PWC	https://paperswithcode.com/paper/190503469
Repo
Framework

Mosaic: A Sample-Based Database System for Open World Query Processing


Title	Mosaic: A Sample-Based Database System for Open World Query Processing
Authors	Laurel Orr, Samuel Ainsworth, Walter Cai, Kevin Jamieson, Magda Balazinska, Dan Suciu
Abstract	Data scientists have relied on samples to analyze populations of interest for decades. Recently, with the increase in the number of public data repositories, sample data has become easier to access. It has not, however, become easier to analyze. This sample data is arbitrarily biased with an unknown sampling probability, meaning data scientists must manually debias the sample with custom techniques to avoid inaccurate results. In this vision paper, we propose Mosaic, a database system that treats samples as first-class citizens and allows users to ask questions over populations represented by these samples. Answering queries over biased samples is non-trivial as there is no existing, standard technique to answer population queries when the sampling probability is unknown. In this paper, we show how our envisioned system solves this problem by having a unique sample-based data model with extensions to the SQL language. We propose how to perform population query answering using biased samples and give preliminary results for one of our novel query answering techniques.
Tasks
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07777v3
PDF	https://arxiv.org/pdf/1912.07777v3.pdf
PWC	https://paperswithcode.com/paper/mosaic-a-sample-based-database-system-for
Repo
Framework

Lukthung Classification Using Neural Networks on Lyrics and Audios


Title	Lukthung Classification Using Neural Networks on Lyrics and Audios
Authors	Kawisorn Kamtue, Kasina Euchukanonchai, Dittaya Wanvarie, Naruemon Pratanwanich
Abstract	Music genre classification is a widely researched topic in music information retrieval (MIR). Being able to automatically tag genres will benefit music streaming service providers such as JOOX, Apple Music, and Spotify for their content-based recommendation. However, most studies on music classification have been done on western songs which differ from Thai songs. Lukthung, a distinctive and long-established type of Thai music, is one of the most popular music genres in Thailand and has a specific group of listeners. In this paper, we develop neural networks to classify such Lukthung genre from others using both lyrics and audios. Words used in Lukthung songs are particularly poetical, and their musical styles are uniquely composed of traditional Thai instruments. We leverage these two main characteristics by building a lyrics model based on bag-of-words (BoW), and an audio model using a convolutional neural network (CNN) architecture. We then aggregate the intermediate features learned from both models to build a final classifier. Our results show that the proposed three models outperform all of the standard classifiers where the combined model yields the best $F_1$ score of 0.86, allowing Lukthung classification to be applicable to personalized recommendation for Thai audience.
Tasks	Information Retrieval, Music Classification, Music Information Retrieval
Published	2019-08-23
URL	https://arxiv.org/abs/1908.08769v2
PDF	https://arxiv.org/pdf/1908.08769v2.pdf
PWC	https://paperswithcode.com/paper/lukthung-classification-using-neural-networks
Repo
Framework

Deep Spectral Clustering using Dual Autoencoder Network


Title	Deep Spectral Clustering using Dual Autoencoder Network
Authors	Xu Yang, Cheng Deng, Feng Zheng, Junchi Yan, Wei Liu
Abstract	The clustering methods have recently absorbed even-increasing attention in learning and vision. Deep clustering combines embedding and clustering together to obtain optimal embedding subspace for clustering, which can be more effective compared with conventional clustering methods. In this paper, we propose a joint learning framework for discriminative embedding and spectral clustering. We first devise a dual autoencoder network, which enforces the reconstruction constraint for the latent representations and their noisy versions, to embed the inputs into a latent space for clustering. As such the learned latent representations can be more robust to noise. Then the mutual information estimation is utilized to provide more discriminative information from the inputs. Furthermore, a deep spectral clustering method is applied to embed the latent representations into the eigenspace and subsequently clusters them, which can fully exploit the relationship between inputs to achieve optimal clustering results. Experimental results on benchmark datasets show that our method can significantly outperform state-of-the-art clustering approaches.
Tasks
Published	2019-04-30
URL	http://arxiv.org/abs/1904.13113v1
PDF	http://arxiv.org/pdf/1904.13113v1.pdf
PWC	https://paperswithcode.com/paper/deep-spectral-clustering-using-dual
Repo
Framework

GEVR: An Event Venue Recommendation System for Groups of Mobile Users


Title	GEVR: An Event Venue Recommendation System for Groups of Mobile Users
Authors	Jason Shuo Zhang, Mike Gartrell, Richard Han, Qin Lv, Shivakant Mishra
Abstract	In this paper, we present GEVR, the first Group Event Venue Recommendation system that incorporates mobility via individual location traces and context information into a “social-based” group decision model to provide venue recommendations for groups of mobile users. Our study leverages a real-world dataset collected using the OutWithFriendz mobile app for group event planning, which contains 625 users and over 500 group events. We first develop a novel “social-based” group location prediction model, which adaptively applies different group decision strategies to groups with different social relationship strength to aggregate each group member’s location preference, to predict where groups will meet. Evaluation results show that our prediction model not only outperforms commonly used and state-of-the-art group decision strategies with over 80% accuracy for predicting groups’ final meeting location clusters, but also provides promising qualities in cold-start scenarios. We then integrate our prediction model with the Foursquare Venue Recommendation API to construct an event venue recommendation framework for groups of mobile users. Evaluation results show that GEVR outperforms the comparative models by a significant margin.
Tasks
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10512v1
PDF	http://arxiv.org/pdf/1903.10512v1.pdf
PWC	https://paperswithcode.com/paper/gevr-an-event-venue-recommendation-system-for
Repo
Framework

Online Fair Division: A Survey


Title	Online Fair Division: A Survey
Authors	Martin Aleksandrov, Toby Walsh
Abstract	We survey a burgeoning and promising new research area that considers the online nature of many practical fair division problems. We identify wide variety of such online fair division problems, as well as discuss new mechanisms and normative properties that apply to this online setting. The online nature of such fair division problems provides both opportunities and challenges such as the possibility to develop new online mechanisms as well as the difficulty of dealing with an uncertain future.
Tasks
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09488v1
PDF	https://arxiv.org/pdf/1911.09488v1.pdf
PWC	https://paperswithcode.com/paper/online-fair-division-a-survey
Repo
Framework

Graph Neural Reasoning May Fail in Certifying Boolean Unsatisfiability


Title	Graph Neural Reasoning May Fail in Certifying Boolean Unsatisfiability
Authors	Ziliang Chen, Zhanfu Yang
Abstract	It is feasible and practically-valuable to bridge the characteristics between graph neural networks (GNNs) and logical reasoning. Despite considerable efforts and successes witnessed to solve Boolean satisfiability (SAT), it remains a mystery of GNN-based solvers for more complex predicate logic formulae. In this work, we conjectures with some evidences, that generally-defined GNNs present several limitations to certify the unsatisfiability (UNSAT) in Boolean formulae. It implies that GNNs may probably fail in learning the logical reasoning tasks if they contain proving UNSAT as the sub-problem included by most predicate logic formulae.
Tasks
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11588v2
PDF	https://arxiv.org/pdf/1909.11588v2.pdf
PWC	https://paperswithcode.com/paper/graph-neural-reasoning-may-fail-in-proving
Repo
Framework

Novel quantitative indicators of digital ophthalmoscopy image quality


Title	Novel quantitative indicators of digital ophthalmoscopy image quality
Authors	Chris von Csefalvay
Abstract	With the advent of smartphone indirect ophthalmoscopy, teleophthalmology - the use of specialist ophthalmology assets at a distance from the patient - has experienced a breakthrough, promising enormous benefits especially for healthcare in distant, inaccessible or opthalmologically underserved areas, where specialists are either unavailable or too few in number. However, accurate teleophthalmology requires high-quality ophthalmoscopic imagery. This paper considers three feature families - statistical metrics, gradient-based metrics and wavelet transform coefficient derived indicators - as possible metrics to identify unsharp or blurry images. By using standard machine learning techniques, the suitability of these features for image quality assessment is confirmed, albeit on a rather small data set. With the increased availability and decreasing cost of digital ophthalmoscopy on one hand and the increased prevalence of diabetic retinopathy worldwide on the other, creating tools that can determine whether an image is likely to be diagnostically suitable can play a significant role in accelerating and streamlining the teleophthalmology process. This paper highlights the need for more research in this area, including the compilation of a diverse database of ophthalmoscopic imagery, annotated with quality markers, to train the Point of Acquisition error detection algorithms of the future.
Tasks	Image Quality Assessment
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02695v1
PDF	http://arxiv.org/pdf/1903.02695v1.pdf
PWC	https://paperswithcode.com/paper/novel-quantitative-indicators-of-digital
Repo
Framework

Feature Interaction-aware Graph Neural Networks


Title	Feature Interaction-aware Graph Neural Networks
Authors	Kaize Ding, Yichuan Li, Jundong Li, Chenghao Liu, Huan Liu
Abstract	Inspired by the immense success of deep learning, graph neural networks (GNNs) are widely used to learn powerful node representations and have demonstrated promising performance on different graph learning tasks. However, most real-world graphs often come with high-dimensional and sparse node features, rendering the learned node representations from existing GNN architectures less expressive. In this paper, we propose \textit{Feature Interaction-aware Graph Neural Networks (FI-GNNs)}, a plug-and-play GNN framework for learning node representations encoded with informative feature interactions. Specifically, the proposed framework is able to highlight informative feature interactions in a personalized manner and further learn highly expressive node representations on feature-sparse graphs. Extensive experiments on various datasets demonstrate the superior capability of FI-GNNs for graph learning tasks.
Tasks	Representation Learning
Published	2019-08-19
URL	https://arxiv.org/abs/1908.07110v2
PDF	https://arxiv.org/pdf/1908.07110v2.pdf
PWC	https://paperswithcode.com/paper/graph-neural-networks-with-high-order-feature
Repo
Framework