October 18, 2019

3132 words 15 mins read

Paper Group ANR 666

Learning Supervised Topic Models for Classification and Regression from Crowds. Scene Recomposition by Learning-based ICP. A Clonal Selection Algorithm with Levenshtein Distance based Image Similarity in Multidimensional Subjective Tourist Information and Discovery of Cryptic Spots by Interactive GHSOM. Analysis of Risk Factor Domains in Psychosis …

Learning Supervised Topic Models for Classification and Regression from Crowds


Title	Learning Supervised Topic Models for Classification and Regression from Crowds
Authors	Filipe Rodrigues, Mariana Lourenço, Bernardete Ribeiro, Francisco Pereira
Abstract	The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on supervised topic models. However, the nature of most annotation tasks, prone to ambiguity and noise, often with high volumes of documents, deem learning under a single-annotator assumption unrealistic or unpractical for most real-world applications. In this article, we propose two supervised topic models, one for classification and another for regression problems, which account for the heterogeneity and biases among different annotators that are encountered in practice when learning from crowds. We develop an efficient stochastic variational inference algorithm that is able to scale to very large datasets, and we empirically demonstrate the advantages of the proposed model over state-of-the-art approaches.
Tasks	Topic Models
Published	2018-08-17
URL	http://arxiv.org/abs/1808.05902v1
PDF	http://arxiv.org/pdf/1808.05902v1.pdf
PWC	https://paperswithcode.com/paper/learning-supervised-topic-models-for
Repo
Framework

Scene Recomposition by Learning-based ICP


Title	Scene Recomposition by Learning-based ICP
Authors	Hamid Izadinia, Steven M. Seitz
Abstract	By moving a depth sensor around a room, we compute a 3D CAD model of the environment, capturing the room shape and contents such as chairs, desks, sofas, and tables. Rather than reconstructing geometry, we match, place, and align each object in the scene to thousands of CAD models of objects. In addition to the end-to-end system, the key technical contribution is a novel approach for aligning CAD models to 3D scans, based on deep reinforcement learning. This approach, which we call Learning-based ICP, outperforms prior ICP methods in the literature, by learning the best points to match and conditioning on object viewpoint. LICP learns to align using only synthetic data and does not require ground-truth annotation of object pose or keypoint pair matching in real scene scans. While LICP is trained on synthetic data and without 3D real scene annotations, it outperforms both learned local deep feature matching and geometric based alignment methods in real scenes. Proposed method is evaluated on publicly available real scenes datasets of SceneNN and ScanNet as well as synthetic scenes of SUNCG. High quality results are demonstrated on a range of real world scenes, with robustness to clutter, viewpoint, and occlusion.
Tasks
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05583v1
PDF	http://arxiv.org/pdf/1812.05583v1.pdf
PWC	https://paperswithcode.com/paper/scene-recomposition-by-learning-based-icp
Repo
Framework

A Clonal Selection Algorithm with Levenshtein Distance based Image Similarity in Multidimensional Subjective Tourist Information and Discovery of Cryptic Spots by Interactive GHSOM


Title	A Clonal Selection Algorithm with Levenshtein Distance based Image Similarity in Multidimensional Subjective Tourist Information and Discovery of Cryptic Spots by Interactive GHSOM
Authors	Takumi Ichimura, Shin Kamada
Abstract	Mobile Phone based Participatory Sensing (MPPS) system involves a community of users sending personal information and participating in autonomous sensing through their mobile phones. Sensed data can also be obtained from external sensing devices that can communicate wirelessly to the phone. Our developed tourist subjective data collection system with Android smartphone can determine the filtering rules to provide the important information of sightseeing spot. The rules are automatically generated by Interactive Growing Hierarchical SOM. However, the filtering rules related to photograph were not generated, because the extraction of the specified characteristics from images cannot be realized. We propose the effective method of the Levenshtein distance to deduce the spatial proximity of image viewpoints and thus determine the specified pattern in which images should be processed. To verify the proposed method, some experiments to classify the subjective data with images are executed by Interactive GHSOM and Clonal Selection Algorithm with Immunological Memory Cells in this paper.
Tasks
Published	2018-04-08
URL	http://arxiv.org/abs/1804.05669v1
PDF	http://arxiv.org/pdf/1804.05669v1.pdf
PWC	https://paperswithcode.com/paper/a-clonal-selection-algorithm-with-levenshtein
Repo
Framework

Analysis of Risk Factor Domains in Psychosis Patient Health Records


Title	Analysis of Risk Factor Domains in Psychosis Patient Health Records
Authors	Eben Holderness, Nicholas Miller, Philip Cawkwell, Kirsten Bolton, James Pustejovsky, Marie Meteer, Mei-Hua Hall
Abstract	Readmission after discharge from a hospital is disruptive and costly, regardless of the reason. However, it can be particularly problematic for psychiatric patients, so predicting which patients may be readmitted is critically important but also very difficult. Clinical narratives in psychiatric electronic health records (EHRs) span a wide range of topics and vocabulary; therefore, a psychiatric readmission prediction model must begin with a robust and interpretable topic extraction component. We created a data pipeline for using document vector similarity metrics to perform topic extraction on psychiatric EHR data in service of our long-term goal of creating a readmission risk classifier. We show initial results for our topic extraction model and identify additional features we will be incorporating in the future.
Tasks	Readmission Prediction
Published	2018-09-15
URL	http://arxiv.org/abs/1809.05752v1
PDF	http://arxiv.org/pdf/1809.05752v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-risk-factor-domains-in-psychosis
Repo
Framework

A likelihood-ratio type test for stochastic block models with bounded degrees


Title	A likelihood-ratio type test for stochastic block models with bounded degrees
Authors	Mingao Yuan, Yang Feng, Zuofeng Shang
Abstract	A fundamental problem in network data analysis is to test Erd"{o}s-R'{e}nyi model $\mathcal{G}\left(n,\frac{a+b}{2n}\right)$ versus a bisection stochastic block model $\mathcal{G}\left(n,\frac{a}{n},\frac{b}{n}\right)$, where $a,b>0$ are constants that represent the expected degrees of the graphs and $n$ denotes the number of nodes. This problem serves as the foundation of many other problems such as testing-based methods for determining the number of communities (\cite{BS16,L16}) and community detection (\cite{MS16}). Existing work has been focusing on growing-degree regime $a,b\to\infty$ (\cite{BS16,L16,MS16,BM17,B18,GL17a,GL17b}) while leaving the bounded-degree regime untreated. In this paper, we propose a likelihood-ratio (LR) type procedure based on regularization to test stochastic block models with bounded degrees. We derive the limit distributions as power Poisson laws under both null and alternative hypotheses, based on which the limit power of the test is carefully analyzed. We also examine a Monte-Carlo method that partly resolves the computational cost issue. The proposed procedures are examined by both simulated and real-world data. The proof depends on a contiguity theory developed by Janson \cite{J95}.
Tasks	Community Detection
Published	2018-07-12
URL	http://arxiv.org/abs/1807.04426v2
PDF	http://arxiv.org/pdf/1807.04426v2.pdf
PWC	https://paperswithcode.com/paper/a-likelihood-ratio-type-test-for-stochastic
Repo
Framework

Stochastic subgradient method converges on tame functions


Title	Stochastic subgradient method converges on tame functions
Authors	Damek Davis, Dmitriy Drusvyatskiy, Sham Kakade, Jason D. Lee
Abstract	This work considers the question: what convergence guarantees does the stochastic subgradient method have in the absence of smoothness and convexity? We prove that the stochastic subgradient method, on any semialgebraic locally Lipschitz function, produces limit points that are all first-order stationary. More generally, our result applies to any function with a Whitney stratifiable graph. In particular, this work endows the stochastic subgradient method, and its proximal extension, with rigorous convergence guarantees for a wide class of problems arising in data science—including all popular deep learning architectures.
Tasks
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07795v3
PDF	http://arxiv.org/pdf/1804.07795v3.pdf
PWC	https://paperswithcode.com/paper/stochastic-subgradient-method-converges-on
Repo
Framework

Promising Accurate Prefix Boosting for sequence-to-sequence ASR


Title	Promising Accurate Prefix Boosting for sequence-to-sequence ASR
Authors	Murali Karthick Baskar, Lukáš Burget, Shinji Watanabe, Martin Karafiát, Takaaki Hori, Jan Honza Černocký
Abstract	In this paper, we present promising accurate prefix boosting (PAPB), a discriminative training technique for attention based sequence-to-sequence (seq2seq) ASR. PAPB is devised to unify the training and testing scheme in an effective manner. The training procedure involves maximizing the score of each partial correct sequence obtained during beam search compared to other hypotheses. The training objective also includes minimization of token (character) error rate. PAPB shows its efficacy by achieving 10.8% and 3.8% WER with and without RNNLM respectively on Wall Street Journal dataset.
Tasks
Published	2018-11-07
URL	http://arxiv.org/abs/1811.02770v1
PDF	http://arxiv.org/pdf/1811.02770v1.pdf
PWC	https://paperswithcode.com/paper/promising-accurate-prefix-boosting-for
Repo
Framework

Clear the Fog: Combat Value Assessment in Incomplete Information Games with Convolutional Encoder-Decoders


Title	Clear the Fog: Combat Value Assessment in Incomplete Information Games with Convolutional Encoder-Decoders
Authors	Hyungu Kahng, Yonghyun Jeong, Yoon Sang Cho, Gonie Ahn, Young Joon Park, Uk Jo, Hankyu Lee, Hyungrok Do, Junseung Lee, Hyunjin Choi, Iljoo Yoon, Hyunjae Lee, Daehun Jun, Changhyeon Bae, Seoung Bum Kim
Abstract	StarCraft, one of the most popular real-time strategy games, is a compelling environment for artificial intelligence research for both micro-level unit control and macro-level strategic decision making. In this study, we address an eminent problem concerning macro-level decision making, known as the ‘fog-of-war’, which rises naturally from the fact that information regarding the opponent’s state is always provided in the incomplete form. For intelligent agents to play like human players, it is obvious that making accurate predictions of the opponent’s status under incomplete information will increase its chance of winning. To reflect this fact, we propose a convolutional encoder-decoder architecture that predicts potential counts and locations of the opponent’s units based on only partially visible and noisy information. To evaluate the performance of our proposed method, we train an additional classifier on the encoder-decoder output to predict the game outcome (win or lose). Finally, we designed an agent incorporating the proposed method and conducted simulation games against rule-based agents to demonstrate both effectiveness and practicality. All experiments were conducted on actual game replay data acquired from professional players.
Tasks	Decision Making, Real-Time Strategy Games, Starcraft
Published	2018-11-30
URL	http://arxiv.org/abs/1811.12627v2
PDF	http://arxiv.org/pdf/1811.12627v2.pdf
PWC	https://paperswithcode.com/paper/clear-the-fog-combat-value-assessment-in
Repo
Framework

High-Level Strategy Selection under Partial Observability in StarCraft: Brood War


Title	High-Level Strategy Selection under Partial Observability in StarCraft: Brood War
Authors	Jonas Gehring, Da Ju, Vegard Mella, Daniel Gant, Nicolas Usunier, Gabriel Synnaeve
Abstract	We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action corresponds to switching to the respective strategy. Here, a good strategy successfully counters the opponent’s current and possible future strategies which can only be estimated using partial observations. We investigate whether we can utilize the full game state information during training time (in the form of an auxiliary prediction task) to increase performance. Experiments carried out within a StarCraft: Brood War bot against strong community bots show substantial win rate improvements over a fixed-strategy baseline and encouraging results when learning with the auxiliary task.
Tasks	Real-Time Strategy Games, Starcraft
Published	2018-11-21
URL	http://arxiv.org/abs/1811.08568v1
PDF	http://arxiv.org/pdf/1811.08568v1.pdf
PWC	https://paperswithcode.com/paper/high-level-strategy-selection-under-partial
Repo
Framework

Evolutionary Multi-objective Optimization of Real-Time Strategy Micro


Title	Evolutionary Multi-objective Optimization of Real-Time Strategy Micro
Authors	Rahul Dubey, Joseph Ghantous, Sushil Louis, Siming Liu
Abstract	We investigate an evolutionary multi-objective approach to good micro for real-time strategy games. Good micro helps a player win skirmishes and is one of the keys to developing better real-time strategy game play. In prior work, the same multi-objective approach of maximizing damage done while minimizing damage received was used to evolve micro for a group of ranged units versus a group of melee units. We extend this work to consider groups composed from two types of units. Specifically, this paper uses evolutionary multi-objective optimization to generate micro for one group composed from both ranged and melee units versus another group of ranged and melee units. Our micro behavior representation uses influence maps to represent enemy spatial information and potential fields generated from distance, health, and weapons cool down to guide unit movement. Experimental results indicate that our multi-objective approach leads to a Pareto front of diverse high-quality micro encapsulating multiple possible tactics. This range of micro provided by the Pareto front enables a human or AI player to trade-off among short term tactics that better suit the player’s longer term strategy - for example, choosing to minimize friendly unit damage at the cost of only lightly damaging the enemy versus maximizing damage to the enemy units at the cost of increased damage to friendly units. We believe that our results indicate the usefulness of potential fields as a representation, and of evolutionary multi-objective optimization as an approach, for generating good micro.
Tasks	Real-Time Strategy Games
Published	2018-03-27
URL	http://arxiv.org/abs/1803.10316v1
PDF	http://arxiv.org/pdf/1803.10316v1.pdf
PWC	https://paperswithcode.com/paper/evolutionary-multi-objective-optimization-of
Repo
Framework

Neuroevolution for RTS Micro


Title	Neuroevolution for RTS Micro
Authors	Aavaas Gajurel, Sushil J Louis, Daniel J Mendez, Siming Liu
Abstract	This paper uses neuroevolution of augmenting topologies to evolve control tactics for groups of units in real-time strategy games. In such games, players build economies to generate armies composed of multiple types of units with different attack and movement characteristics to combat each other. This paper evolves neural networks to control movement and attack commands, also called micro, for a group of ranged units skirmishing with a group of melee units. Our results show that neuroevolution of augmenting topologies can effectively generate neural networks capable of good micro for our ranged units against a group of hand-coded melee units. The evolved neural networks lead to kiting behavior for the ranged units which is a common tactic used by professional players in ranged versus melee skirmishes in popular real-time strategy games like Starcraft. The evolved neural networks also generalized well to other starting positions and numbers of units. We believe these results indicate the potential of neuroevolution for generating effective micro in real-time strategy games.
Tasks	Real-Time Strategy Games, Starcraft
Published	2018-03-27
URL	http://arxiv.org/abs/1803.10288v1
PDF	http://arxiv.org/pdf/1803.10288v1.pdf
PWC	https://paperswithcode.com/paper/neuroevolution-for-rts-micro
Repo
Framework

Network-based Biased Tree Ensembles (NetBiTE) for Drug Sensitivity Prediction and Drug Sensitivity Biomarker Identification in Cancer


Title	Network-based Biased Tree Ensembles (NetBiTE) for Drug Sensitivity Prediction and Drug Sensitivity Biomarker Identification in Cancer
Authors	Ali Oskooei, Matteo Manica, Roland Mathis, Maria Rodriguez Martinez
Abstract	We present the Network-based Biased Tree Ensembles (NetBiTE) method for drug sensitivity prediction and drug sensitivity biomarker identification in cancer using a combination of prior knowledge and gene expression data. Our devised method consists of a biased tree ensemble that is built according to a probabilistic bias weight distribution. The bias weight distribution is obtained from the assignment of high weights to the drug targets and propagating the assigned weights over a protein-protein interaction network such as STRING. The propagation of weights, defines neighborhoods of influence around the drug targets and as such simulates the spread of perturbations within the cell, following drug administration. Using a synthetic dataset, we showcase how application of biased tree ensembles (BiTE) results in significant accuracy gains at a much lower computational cost compared to the unbiased random forests (RF) algorithm. We then apply NetBiTE to the Genomics of Drug Sensitivity in Cancer (GDSC) dataset and demonstrate that NetBiTE outperforms RF in predicting IC50 drug sensitivity, only for drugs that target membrane receptor pathways (MRPs): RTK, EGFR and IGFR signaling pathways. We propose based on the NetBiTE results, that for drugs that inhibit MRPs, the expression of target genes prior to drug administration is a biomarker for IC50 drug sensitivity following drug administration. We further verify and reinforce this proposition through control studies on, PI3K/MTOR signaling pathway inhibitors, a drug category that does not target MRPs, and through assignment of dummy targets to MRP inhibiting drugs and investigating the variation in NetBiTE accuracy.
Tasks
Published	2018-08-18
URL	http://arxiv.org/abs/1808.06603v2
PDF	http://arxiv.org/pdf/1808.06603v2.pdf
PWC	https://paperswithcode.com/paper/network-based-biased-tree-ensembles-netbite
Repo
Framework

How to Make a BLT Sandwich? Learning to Reason towards Understanding Web Instructional Videos


Title	How to Make a BLT Sandwich? Learning to Reason towards Understanding Web Instructional Videos
Authors	Shaojie Wang, Wentian Zhao, Ziyi Kou, Chenliang Xu
Abstract	Understanding web instructional videos is an essential branch of video understanding in two aspects. First, most existing video methods focus on short-term actions for a-few-second-long video clips; these methods are not directly applicable to long videos. Second, unlike unconstrained long videos, e.g., movies, instructional videos are more structured in that they have step-by-step procedure constraining the understanding task. In this paper, we study reasoning on instructional videos via question-answering (QA). Surprisingly, it has not been an emphasis in the video community despite its rich applications. We thereby introduce YouQuek, an annotated QA dataset for instructional videos based on the recent YouCook2. The questions in YouQuek are not limited to cues on one frame but related to logical reasoning in the temporal dimension. Observing the lack of effective representations for modeling long videos, we propose a set of carefully designed models including a novel Recurrent Graph Convolutional Network (RGCN) that captures both temporal order and relation information. Furthermore, we study multiple modalities including description and transcripts for the purpose of boosting video understanding. Extensive experiments on YouQuek suggest that RGCN performs the best in terms of QA accuracy and a better performance is gained by introducing human annotated description.
Tasks	Question Answering, Video Understanding
Published	2018-12-02
URL	http://arxiv.org/abs/1812.00344v2
PDF	http://arxiv.org/pdf/1812.00344v2.pdf
PWC	https://paperswithcode.com/paper/how-to-make-a-blt-sandwich-learning-to-reason
Repo
Framework

LIUM-CVC Submissions for WMT18 Multimodal Translation Task


Title	LIUM-CVC Submissions for WMT18 Multimodal Translation Task
Authors	Ozan Caglayan, Adrien Bardet, Fethi Bougares, Loïc Barrault, Kai Wang, Marc Masana, Luis Herranz, Joost van de Weijer
Abstract	This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation. This year we propose several modifications to our previous multimodal attention architecture in order to better integrate convolutional features and refine them using encoder-side information. Our final constrained submissions ranked first for English-French and second for English-German language pairs among the constrained submissions according to the automatic evaluation metric METEOR.
Tasks	Machine Translation
Published	2018-09-01
URL	http://arxiv.org/abs/1809.00151v1
PDF	http://arxiv.org/pdf/1809.00151v1.pdf
PWC	https://paperswithcode.com/paper/lium-cvc-submissions-for-wmt18-multimodal
Repo
Framework

Resilient Active Information Gathering with Mobile Robots


Title	Resilient Active Information Gathering with Mobile Robots
Authors	Brent Schlotfeldt, Vasileios Tzoumas, Dinesh Thakur, George J. Pappas
Abstract	Applications of safety, security, and rescue in robotics, such as multi-robot target tracking, involve the execution of information acquisition tasks by teams of mobile robots. However, in failure-prone or adversarial environments, robots get attacked, their communication channels get jammed, and their sensors may fail, resulting in the withdrawal of robots from the collective task, and consequently the inability of the remaining active robots to coordinate with each other. As a result, traditional design paradigms become insufficient and, in contrast, resilient designs against system-wide failures and attacks become important. In general, resilient design problems are hard, and even though they often involve objective functions that are monotone or submodular, scalable approximation algorithms for their solution have been hitherto unknown. In this paper, we provide the first algorithm, enabling the following capabilities: minimal communication, i.e., the algorithm is executed by the robots based only on minimal communication between them; system-wide resiliency, i.e., the algorithm is valid for any number of denial-of-service attacks and failures; and provable approximation performance, i.e., the algorithm ensures for all monotone (and not necessarily submodular) objective functions a solution that is finitely close to the optimal. We quantify our algorithm’s approximation performance using a notion of curvature for monotone set functions. We support our theoretical analyses with simulated and real-world experiments, by considering an active information gathering scenario, namely, multi-robot target tracking.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09730v3
PDF	http://arxiv.org/pdf/1803.09730v3.pdf
PWC	https://paperswithcode.com/paper/resilient-active-information-gathering-with
Repo
Framework