January 28, 2020

3188 words 15 mins read

Paper Group ANR 927

Attention-based Deep Reinforcement Learning for Multi-view Environments. Machine Learning on EPEX Order Books: Insights and Forecasts. Rethinking the Artificial Neural Networks: A Mesh of Subnets with a Central Mechanism for Storing and Predicting the Data. Analyzing Privacy Loss in Updates of Natural Language Models. Interactive Differentiable Sim …

Attention-based Deep Reinforcement Learning for Multi-view Environments


Title	Attention-based Deep Reinforcement Learning for Multi-view Environments
Authors	Elaheh Barati, Xuewen Chen, Zichun Zhong
Abstract	In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of complicated policies. Since the views may frequently suffer from partial observability, their provided observation can have different levels of importance. In this paper, we present a novel attention-based deep reinforcement learning method in a multi-view environment in which each view can provide various representative information about the environment. Specifically, our method learns a policy to dynamically attend to views of the environment based on their importance in the decision-making process. We evaluate the performance of our method on TORCS racing car simulator and three other complex 3D environments with obstacles.
Tasks	Decision Making
Published	2019-05-10
URL	https://arxiv.org/abs/1905.03985v1
PDF	https://arxiv.org/pdf/1905.03985v1.pdf
PWC	https://paperswithcode.com/paper/attention-based-deep-reinforcement-learning
Repo
Framework

Machine Learning on EPEX Order Books: Insights and Forecasts


Title	Machine Learning on EPEX Order Books: Insights and Forecasts
Authors	Simon Schnürch, Andreas Wagner
Abstract	This paper employs machine learning algorithms to forecast German electricity spot market prices. The forecasts utilize in particular bid and ask order book data from the spot market but also fundamental market data like renewable infeed and expected demand. Appropriate feature extraction for the order book data is developed. Using cross-validation to optimise hyperparameters, neural networks and random forests are proposed and compared to statistical reference models. The machine learning models outperform traditional approaches.
Tasks
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06248v3
PDF	https://arxiv.org/pdf/1906.06248v3.pdf
PWC	https://paperswithcode.com/paper/machine-learning-on-epex-order-books-insights
Repo
Framework

Rethinking the Artificial Neural Networks: A Mesh of Subnets with a Central Mechanism for Storing and Predicting the Data


Title	Rethinking the Artificial Neural Networks: A Mesh of Subnets with a Central Mechanism for Storing and Predicting the Data
Authors	Usman Ahmad, Hong Song, Awais Bilal, Shahid Mahmood, Asad Ullah, Uzair Saeed
Abstract	The Artificial Neural Networks (ANNs) have been originally designed to function like a biological neural network, but does an ANN really work in the same way as a biological neural network? As we know, the human brain holds information in its memory cells, so if the ANNs use the same model as our brains, they should store datasets in a similar manner. The most popular type of ANN architecture is based on a layered structure of neurons, whereas a human brain has trillions of complex interconnections of neurons continuously establishing new connections, updating existing ones, and removing the irrelevant connections across different parts of the brain. In this paper, we propose a novel approach to building ANNs which are truly inspired by the biological network containing a mesh of subnets controlled by a central mechanism. A subnet is a network of neurons that hold the dataset values. We attempt to address the following fundamental questions: (1) What is the architecture of the ANN model? Whether the layered architecture is the most appropriate choice? (2) Whether a neuron is a process or a memory cell? (3) What is the best way of interconnecting neurons and what weight-assignment mechanism should be used? (4) How to incorporate prior knowledge, bias, and generalizations for features extraction and prediction? Our proposed ANN architecture leverages the accuracy on textual data and our experimental findings confirm the effectiveness of our model. We also collaborate with the construction of the ANN model for storing and processing the images.
Tasks
Published	2019-01-05
URL	http://arxiv.org/abs/1901.01462v1
PDF	http://arxiv.org/pdf/1901.01462v1.pdf
PWC	https://paperswithcode.com/paper/rethinking-the-artificial-neural-networks-a
Repo
Framework

Analyzing Privacy Loss in Updates of Natural Language Models


Title	Analyzing Privacy Loss in Updates of Natural Language Models
Authors	Shruti Tople, Marc Brockschmidt, Boris Köpf, Olga Ohrimenko, Santiago Zanella-Béguelin
Abstract	To continuously improve quality and reflect changes in data, machine learning-based services have to regularly re-train and update their core models. In the setting of language models, we show that a comparative analysis of model snapshots before and after an update can reveal a surprising amount of detailed information about the changes in the data used for training before and after the update. We discuss the privacy implications of our findings, propose mitigation strategies and evaluate their effect.
Tasks
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07942v2
PDF	https://arxiv.org/pdf/1912.07942v2.pdf
PWC	https://paperswithcode.com/paper/analyzing-privacy-loss-in-updates-of-natural-1
Repo
Framework

Interactive Differentiable Simulation


Title	Interactive Differentiable Simulation
Authors	Eric Heiden, David Millard, Hejia Zhang, Gaurav S. Sukhatme
Abstract	Intelligent agents need a physical understanding of the world to predict the impact of their actions in the future. While learning-based models of the environment dynamics have contributed to significant improvements in sample efficiency compared to model-free reinforcement learning algorithms, they typically fail to generalize to system states beyond the training data, while often grounding their predictions on non-interpretable latent variables. We introduce Interactive Differentiable Simulation (IDS), a differentiable physics engine, that allows for efficient, accurate inference of physical properties of rigid-body systems. Integrated into deep learning architectures, our model is able to accomplish system identification using visual input, leading to an interpretable model of the world whose parameters have physical meaning. We present experiments showing automatic task-based robot design and parameter estimation for nonlinear dynamical systems by automatically calculating gradients in IDS. When integrated into an adaptive model-predictive control algorithm, our approach exhibits orders of magnitude improvements in sample efficiency over model-free reinforcement learning algorithms on challenging nonlinear control domains.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10706v2
PDF	https://arxiv.org/pdf/1905.10706v2.pdf
PWC	https://paperswithcode.com/paper/interactive-differentiable-simulation
Repo
Framework

Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning


Title	Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning
Authors	Michael Everett, Yu Fan Chen, Jonathan P. How
Abstract	Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to model the complex interactions and cooperation with nearby, decision-making agents (e.g., pedestrians, other robots). Existing RL-based works assume homogeneity of agent policies, use specific motion models over short timescales, or lack a mechanism to consider measurements taken with a large number (possibly varying) of nearby agents. Therefore, this work develops an algorithm that learns collision avoidance among a variety of types of non-communicating, dynamic agents without assuming they follow any particular behavior rules. It extends our previous work by introducing a strategy using Long Short-Term Memory (LSTM) that enables the algorithm to use observations of an arbitrary number of other agents, instead of a small, fixed number of neighbors. The proposed algorithm is shown to outperform a classical collision avoidance algorithm, another deep RL-based algorithm, and scales with the number of agents better (fewer collisions, shorter time to goal) than our previously published learning-based approach. Analysis of the LSTM provides insights into how observations of nearby agents affect the hidden state and quantifies the performance impact of various agent ordering heuristics. The learned policy generalizes to several applications beyond the training scenarios: formation control (arrangement into letters), an implementation on a fleet of four multirotors, and an implementation on a fully autonomous robotic vehicle capable of traveling at human walking speed among pedestrians.
Tasks	Decision Making
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11689v2
PDF	https://arxiv.org/pdf/1910.11689v2.pdf
PWC	https://paperswithcode.com/paper/collision-avoidance-in-pedestrian-rich
Repo
Framework


Title	Investigating the Relationship between Multi-Party Linguistic Entrainment, Team Characteristics, and the Perception of Team Social Outcomes
Authors	Mingzhi Yu, Diane Litman, Susannah Paletz
Abstract	Multi-party linguistic entrainment refers to the phenomenon that speakers tend to speak more similarly during conversation. We first developed new measures of multi-party entrainment on features describing linguistic style, and then examined the relationship between entrainment and team characteristics in terms of gender composition, team size, and diversity. Next, we predicted the perception of team social outcomes using multi-party linguistic entrainment and team characteristics with a hierarchical regression model. We found that teams with greater gender diversity had higher minimum convergence than teams with less gender diversity. Entrainment contributed significantly to predicting perceived team social outcomes both alone and controlling for team characteristics.
Tasks
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00867v1
PDF	https://arxiv.org/pdf/1909.00867v1.pdf
PWC	https://paperswithcode.com/paper/investigating-the-relationship-between-multi
Repo
Framework

Equalizing Recourse across Groups


Title	Equalizing Recourse across Groups
Authors	Vivek Gupta, Pegah Nokhiz, Chitradeep Dutta Roy, Suresh Venkatasubramanian
Abstract	The rise in machine learning-assisted decision-making has led to concerns about the fairness of the decisions and techniques to mitigate problems of discrimination. If a negative decision is made about an individual (denying a loan, rejecting an application for housing, and so on) justice dictates that we be able to ask how we might change circumstances to get a favorable decision the next time. Moreover, the ability to change circumstances (a better education, improved credentials) should not be limited to only those with access to expensive resources. In other words, \emph{recourse} for negative decisions should be considered a desirable value that can be equalized across (demographically defined) groups. This paper describes how to build models that make accurate predictions while still ensuring that the penalties for a negative outcome do not disadvantage different groups disproportionately. We measure recourse as the distance of an individual from the decision boundary of a classifier. We then introduce a regularized objective to minimize the difference in recourse across groups. We explore linear settings and further extend recourse to non-linear settings as well as model-agnostic settings where the exact distance from boundary cannot be calculated. Our results show that we can successfully decrease the unfairness in recourse while maintaining classifier performance.
Tasks	Decision Making
Published	2019-09-07
URL	https://arxiv.org/abs/1909.03166v1
PDF	https://arxiv.org/pdf/1909.03166v1.pdf
PWC	https://paperswithcode.com/paper/equalizing-recourse-across-groups
Repo
Framework

To What Extent are Name Variants Used as Named Entities in Turkish Tweets?


Title	To What Extent are Name Variants Used as Named Entities in Turkish Tweets?
Authors	Dilek Küçük
Abstract	Social media texts differ from regular texts in various aspects. One of the main differences is the common use of informal name variants instead of well-formed named entities in social media compared to regular texts. These name variants may come in the form of abbreviations, nicknames, contractions, and hypocoristic uses, in addition to names distorted due to capitalization and writing errors. In this paper, we present an analysis of the named entities in a publicly-available tweet dataset in Turkish with respect to their being name variants belonging to different categories. We also provide finer-grained annotations of the named entities as well-formed names and different categories of name variants, where these annotations are made publicly-available. The analysis presented and the accompanying annotations will contribute to related research on the treatment of named entities in social media.
Tasks
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07940v1
PDF	https://arxiv.org/pdf/1912.07940v1.pdf
PWC	https://paperswithcode.com/paper/to-what-extent-are-name-variants-used-as
Repo
Framework

Small Obstacle Avoidance Based on RGB-D Semantic Segmentation


Title	Small Obstacle Avoidance Based on RGB-D Semantic Segmentation
Authors	Minjie Hua, Yibing Nan, Shiguo Lian
Abstract	This paper presents a novel obstacle avoidance system for road robots equipped with RGB-D sensor that captures scenes of its way forward. The purpose of the system is to have road robots move around autonomously and constantly without any collision even with small obstacles, which are often missed by existing solutions. For each input RGB-D image, the system uses a new two-stage semantic segmentation network followed by the morphological processing to generate the accurate semantic map containing road and obstacles. Based on the map, the local path planning is applied to avoid possible collision. Additionally, optical flow supervision and motion blurring augmented training scheme is applied to improve temporal consistency between adjacent frames and overcome the disturbance caused by camera shake. Various experiments are conducted to show that the proposed architecture obtains high performance both in indoor and outdoor scenarios.
Tasks	Optical Flow Estimation, Semantic Segmentation
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11675v1
PDF	https://arxiv.org/pdf/1908.11675v1.pdf
PWC	https://paperswithcode.com/paper/small-obstacle-avoidance-based-on-rgb-d
Repo
Framework

Tactical Reward Shaping: Bypassing Reinforcement Learning with Strategy-Based Goals


Title	Tactical Reward Shaping: Bypassing Reinforcement Learning with Strategy-Based Goals
Authors	Yizheng Zhang, Andre Rosendo
Abstract	Deep Reinforcement Learning (DRL) has shown its promising capabilities to learn optimal policies directly from trial and error. However, learning can be hindered if the goal of the learning, defined by the reward function, is “not optimal”. We demonstrate that by setting the goal/target of competition in a counter-intuitive but intelligent way, instead of heuristically trying solutions through many hours the DRL simulation can quickly converge into a winning strategy. The ICRA-DJI RoboMaster AI Challenge is a game of cooperation and competition between robots in a partially observable environment, quite similar to the Counter-Strike game. Unlike the traditional approach to games, where the reward is given at winning the match or hitting the enemy, our DRL algorithm rewards our robots when in a geometric-strategic advantage, which implicitly increases the winning chances. Furthermore, we use Deep Q Learning (DQL) to generate multi-agent paths for moving, which improves the cooperation between two robots by avoiding the collision. Finally, we implement a variant A* algorithm with the same implicit geometric goal as DQL and compare results. We conclude that a well-set goal can put in question the need for learning algorithms, with geometric-based searches outperforming DQL in many orders of magnitude.
Tasks	Q-Learning
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03144v1
PDF	https://arxiv.org/pdf/1910.03144v1.pdf
PWC	https://paperswithcode.com/paper/tactical-reward-shaping-bypassing
Repo
Framework

Automatic Malware Description via Attribute Tagging and Similarity Embedding


Title	Automatic Malware Description via Attribute Tagging and Similarity Embedding
Authors	Felipe N. Ducau, Ethan M. Rudd, Tad M. Heppner, Alex Long, Konstantin Berlin
Abstract	With the rapid proliferation and increased sophistication of malicious software (malware), detection methods no longer rely only on manually generated signatures but have also incorporated more general approaches like machine learning detection. Although powerful for conviction of malicious artifacts, these methods do not produce any further information about the type of threat that has been detected neither allows for identifying relationships between malware samples. In this work, we address the information gap between machine learning and signature-based detection methods by learning a representation space for malware samples in which files with similar malicious behaviors appear close to each other. We do so by introducing a deep learning based tagging model trained to generate human-interpretable semantic descriptions of malicious software, which, at the same time provides potentially more useful and flexible information than malware family names. We show that the malware descriptions generated with the proposed approach correctly identify more than 95% of eleven possible tag descriptions for a given sample, at a deployable false positive rate of 1% per tag. Furthermore, we use the learned representation space to introduce a similarity index between malware files, and empirically demonstrate using dynamic traces from files’ execution, that is not only more effective at identifying samples from the same families, but also 32 times smaller than those based on raw feature vectors.
Tasks	Malware Detection
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06262v3
PDF	https://arxiv.org/pdf/1905.06262v3.pdf
PWC	https://paperswithcode.com/paper/smart-semantic-malware-attribute-relevance
Repo
Framework

DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks


Title	DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks
Authors	Feihong Liu, Jun Feng, Geng Chen, Ye Wu, Yoonmi Hong, Pew-Thian Yap, Dinggang Shen
Abstract	Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure. Existing fiber parcellation approaches rely on accurate registration between an atlas and the tractograms of an individual, however, due to large individual differences, accurate registration is hard to guarantee in practice. To resolve this issue, we propose a novel deep learning method, called DeepBundle, for registration-free fiber parcellation. Our method utilizes graph convolution neural networks (GCNNs) to predict the parcellation label of each fiber tract. GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately avoiding the use of atlases and any registration method. We evaluate DeepBundle using data from the Human Connectome Project. Experimental results demonstrate the advantages of DeepBundle and suggest that the geometric features extracted from each fiber tract can be used to effectively parcellate the fiber tracts.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03051v2
PDF	https://arxiv.org/pdf/1906.03051v2.pdf
PWC	https://paperswithcode.com/paper/deepbundle-fiber-bundle-parcellation-with
Repo
Framework

Efficient Contraction of Large Tensor Networks for Weighted Model Counting through Graph Decompositions


Title	Efficient Contraction of Large Tensor Networks for Weighted Model Counting through Graph Decompositions
Authors	Jeffrey M. Dudek, Leonardo Dueñas-Osorio, Moshe Y. Vardi
Abstract	Constrained counting is a fundamental problem in artificial intelligence. A promising new algebraic approach to constrained counting makes use of tensor networks, following a reduction from constrained counting to the problem of tensor-network contraction. Contracting a tensor network efficiently requires determining an efficient order to contract the tensors inside the network, which is itself a difficult problem. In this work, we apply graph decompositions to find contraction orders for tensor networks. We prove that finding an efficient contraction order for a tensor network is equivalent to the well-known problem of finding an optimal carving decomposition. Thus memory-optimal contraction orders for planar tensor networks can be found in cubic time. We show that tree decompositions can be used both to find carving decompositions and to factor tensor networks with high-rank, structured tensors. We implement these algorithms on top of state-of-the-art solvers for tree decompositions and show empirically that the resulting weighted model counter is quite effective and useful as part of a portfolio of counters.
Tasks	Tensor Networks
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04381v1
PDF	https://arxiv.org/pdf/1908.04381v1.pdf
PWC	https://paperswithcode.com/paper/efficient-contraction-of-large-tensor
Repo
Framework

The TCGA Meta-Dataset Clinical Benchmark


Title	The TCGA Meta-Dataset Clinical Benchmark
Authors	Mandana Samiei, Tobias Würfl, Tristan Deleu, Martin Weiss, Francis Dutil, Thomas Fevens, Geneviève Boucher, Sebastien Lemieux, Joseph Paul Cohen
Abstract	Machine learning is bringing a paradigm shift to healthcare by changing the process of disease diagnosis and prognosis in clinics and hospitals. This development equips doctors and medical staff with tools to evaluate their hypotheses and hence make more precise decisions. Although most current research in the literature seeks to develop techniques and methods for predicting one particular clinical outcome, this approach is far from the reality of clinical decision making in which you have to consider several factors simultaneously. In addition, it is difficult to follow the recent progress concretely as there is a lack of consistency in benchmark datasets and task definitions in the field of Genomics. To address the aforementioned issues, we provide a clinical Meta-Dataset derived from the publicly available data hub called The Cancer Genome Atlas Program (TCGA) that contains 174 tasks. We believe those tasks could be good proxy tasks to develop methods which can work on a few samples of gene expression data. Also, learning to predict multiple clinical variables using gene-expression data is an important task due to the variety of phenotypes in clinical problems and lack of samples for some of the rare variables. The defined tasks cover a wide range of clinical problems including predicting tumor tissue site, white cell count, histological type, family history of cancer, gender, and many others which we explain later in the paper. Each task represents an independent dataset. We use regression and neural network baselines for all the tasks using only 150 samples and compare their performance.
Tasks	Decision Making
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08636v1
PDF	https://arxiv.org/pdf/1910.08636v1.pdf
PWC	https://paperswithcode.com/paper/the-tcga-meta-dataset-clinical-benchmark
Repo
Framework