January 27, 2020

3161 words 15 mins read

Paper Group ANR 1199

SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead. Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience. An Image Based Visual Servo Approach with Deep Learning for Robotic Manipulation. Fingerprints: Fixed Length Representation via Deep Networks and Domain Knowledge. In …

SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead


Title	SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead
Authors	Wentai Wu, Ligang He, Weiwei Lin, RuiMao, Stephen Jarvis
Abstract	Federated learning (FL) has attracted increasing attention as a promising approach to driving a vast number of devices at the edge with artificial intelligence, i.e., Edge Intelligence. However, it is very challenging to guarantee the efficiency of FL considering the unreliable nature of edge devices while the cost of edge-server communication cannot be neglected. In this paper, we propose SAFA, a semi-asynchronous protocol that avoids problems in the pure synchronous/asynchronous approaches such as heavy downlink traffic and poor convergence rate in extreme conditions (e.g., clients dropping offline frequently). Key principles are introduced in model distribution, client selection and global aggregation, which are designed with tolerance to stragglers for efficiency boost and bias reduction. Extensive experiments on typical machine learning tasks show the effectiveness of the proposed protocol in shortening federated round duration, reducing local resource wastage, and improving the global model’s accuracy at a low communication cost.
Tasks
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01355v1
PDF	https://arxiv.org/pdf/1910.01355v1.pdf
PWC	https://paperswithcode.com/paper/safa-a-semi-asynchronous-protocol-for-fast
Repo
Framework

Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience


Title	Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
Authors	Vaishnavh Nagarajan, J. Zico Kolter
Abstract	The ability of overparameterized deep networks to generalize well has been linked to the fact that stochastic gradient descent (SGD) finds solutions that lie in flat, wide minima in the training loss – minima where the output of the network is resilient to small random noise added to its parameters. So far this observation has been used to provide generalization guarantees only for neural networks whose parameters are either \textit{stochastic} or \textit{compressed}. In this work, we present a general PAC-Bayesian framework that leverages this observation to provide a bound on the original network learned – a network that is deterministic and uncompressed. What enables us to do this is a key novelty in our approach: our framework allows us to show that if on training data, the interactions between the weight matrices satisfy certain conditions that imply a wide training loss minimum, these conditions themselves {\em generalize} to the interactions between the matrices on test data, thereby implying a wide test loss minimum. We then apply our general framework in a setup where we assume that the pre-activation values of the network are not too small (although we assume this only on the training data). In this setup, we provide a generalization guarantee for the original (deterministic, uncompressed) network, that does not scale with product of the spectral norms of the weight matrices – a guarantee that would not have been possible with prior approaches.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.13344v1
PDF	https://arxiv.org/pdf/1905.13344v1.pdf
PWC	https://paperswithcode.com/paper/deterministic-pac-bayesian-generalization-1
Repo
Framework

An Image Based Visual Servo Approach with Deep Learning for Robotic Manipulation


Title	An Image Based Visual Servo Approach with Deep Learning for Robotic Manipulation
Authors	Jingshu Liu, Yuan Li
Abstract	Aiming at the difficulty of extracting image features and estimating the Jacobian matrix in image based visual servo, this paper proposes an image based visual servo approach with deep learning. With the powerful learning capabilities of convolutional neural networks(CNN), autonomous learning to extract features from images and fitting the nonlinear relationships from image space to task space is achieved, which can greatly facilitate the image based visual servo procedure. Based on the above ideas a two-stream network based on convolutional neural network is designed and the corresponding control scheme is proposed to realize the four degrees of freedom visual servo of the robot manipulator. Collecting images of observed target under different pose parameters of the manipulator as training samples for CNN, the trained network can be used to estimate the nonlinear relationship from 2D image space to 3D Cartesian space. The two-stream network takes the current image and the desirable image as inputs and makes them equal to guide the manipulator to the desirable pose. The effectiveness of the approach is verified with experimental results.
Tasks
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07727v1
PDF	https://arxiv.org/pdf/1909.07727v1.pdf
PWC	https://paperswithcode.com/paper/an-image-based-visual-servo-approach-with
Repo
Framework

Fingerprints: Fixed Length Representation via Deep Networks and Domain Knowledge


Title	Fingerprints: Fixed Length Representation via Deep Networks and Domain Knowledge
Authors	Joshua J. Engelsma, Kai Cao, Anil K. Jain
Abstract	We learn a discriminative fixed length feature representation of fingerprints which stands in contrast to commonly used unordered, variable length sets of minutiae points. To arrive at this fixed length representation, we embed fingerprint domain knowledge into a multitask deep convolutional neural network architecture. Empirical results, on two public-domain fingerprint databases (NIST SD4 and FVC 2004 DB1) show that compared to minutiae representations, extracted by two state-of-the-art commercial matchers (Verifinger v6.3 and Innovatrics v2.0.3), our fixed-length representations provide (i) higher search accuracy: Rank-1 accuracy of 97.9% vs. 97.3% on NIST SD4 against a gallery size of 2000 and (ii) significantly faster, large scale search: 682,594 matches per second vs. 22 matches per second for commercial matchers on an i5 3.3 GHz processor with 8 GB of RAM.
Tasks
Published	2019-04-01
URL	http://arxiv.org/abs/1904.01099v1
PDF	http://arxiv.org/pdf/1904.01099v1.pdf
PWC	https://paperswithcode.com/paper/fingerprints-fixed-length-representation-via
Repo
Framework

Insertion-based Decoding with automatically Inferred Generation Order


Title	Insertion-based Decoding with automatically Inferred Generation Order
Authors	Jiatao Gu, Qi Liu, Kyunghyun Cho
Abstract	Conventional neural autoregressive decoding commonly assumes a fixed left-to-right generation order, which may be sub-optimal. In this work, we propose a novel decoding algorithm – InDIGO – which supports flexible sequence generation in arbitrary orders through insertion operations. We extend Transformer, a state-of-the-art sequence generation model, to efficiently implement the proposed approach, enabling it to be trained with either a pre-defined generation order or adaptive orders obtained from beam-search. Experiments on four real-world tasks, including word order recovery, machine translation, image caption and code generation, demonstrate that our algorithm can generate sequences following arbitrary orders, while achieving competitive or even better performance compared to the conventional left-to-right generation. The generated sequences show that InDIGO adopts adaptive generation orders based on input information.
Tasks	Code Generation, Machine Translation
Published	2019-02-04
URL	https://arxiv.org/abs/1902.01370v3
PDF	https://arxiv.org/pdf/1902.01370v3.pdf
PWC	https://paperswithcode.com/paper/insertion-based-decoding-with-automatically
Repo
Framework

Generating Data using Monte Carlo Dropout


Title	Generating Data using Monte Carlo Dropout
Authors	Kristian Miok, Dong Nguyen-Doan, Daniela Zaharie, Marko Robnik-Šikonja
Abstract	For many analytical problems the challenge is to handle huge amounts of available data. However, there are data science application areas where collecting information is difficult and costly, e.g., in the study of geological phenomena, rare diseases, faults in complex systems, insurance frauds, etc. In many such cases, generators of synthetic data with the same statistical and predictive properties as the actual data allow efficient simulations and development of tools and applications. In this work, we propose the incorporation of Monte Carlo Dropout method within Autoencoder (MCD-AE) and Variational Autoencoder (MCD-VAE) as efficient generators of synthetic data sets. As the Variational Autoencoder (VAE) is one of the most popular generator techniques, we explore its similarities and differences to the proposed methods. We compare the generated data sets with the original data based on statistical properties, structural similarity, and predictive similarity. The results obtained show a strong similarity between the results of VAE, MCD-VAE and MCD-AE; however, the proposed methods are faster and can generate values similar to specific selected initial instances.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05755v2
PDF	https://arxiv.org/pdf/1909.05755v2.pdf
PWC	https://paperswithcode.com/paper/generating-data-using-monte-carlo-dropout
Repo
Framework

Mining Closed Strict Episodes


Title	Mining Closed Strict Episodes
Authors	Nikolaj Tatti, Boris Cule
Abstract	Discovering patterns in a sequence is an important aspect of data mining. One popular choice of such patterns are episodes, patterns in sequential data describing events that often occur in the vicinity of each other. Episodes also enforce in which order the events are allowed to occur. In this work we introduce a technique for discovering closed episodes. Adopting existing approaches for discovering traditional patterns, such as closed itemsets, to episodes is not straightforward. First of all, we cannot define a unique closure based on frequency because an episode may have several closed superepisodes. Moreover, to define a closedness concept for episodes we need a subset relationship between episodes, which is not trivial to define. We approach these problems by introducing strict episodes. We argue that this class is general enough, and at the same time we are able to define a natural subset relationship within it and use it efficiently. In order to mine closed episodes we define an auxiliary closure operator. We show that this closure satisfies the needed properties so that we can use the existing framework for mining closed patterns. Discovering the true closed episodes can be done as a post-processing step. We combine these observations into an efficient mining algorithm and demonstrate empirically its performance in practice.
Tasks
Published	2019-04-14
URL	http://arxiv.org/abs/1904.09231v2
PDF	http://arxiv.org/pdf/1904.09231v2.pdf
PWC	https://paperswithcode.com/paper/190409231
Repo
Framework

Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study


Title	Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study
Authors	Mohammad Mahdi Bejani, Mehdi Ghatee
Abstract	Intelligent Transportation Systems (ITS) are much correlated with data science mechanisms. Among the different correlation branches, this paper focuses on the neural network learning models. Some of the considered models are shallow and they get some user-defined features and learn the relationship, while deep models extract the necessary features before learning by themselves. Both of these paradigms are utilized in the recent intelligent transportation systems (ITS) to support decision-making by the aid of different operations such as frequent patterns mining, regression, clustering, and classification. When these learners cannot generalize the results and just memorize the training samples, they fail to support the necessities. In these cases, the testing error is bigger than the training error. This phenomenon is addressed as overfitting in the literature. Because, this issue decreases the reliability of learning systems, in ITS applications, we cannot use such over-fitted machine learning models for different tasks such as traffic prediction, the signal controlling, safety applications, emergency responses, mode detection, driving evaluation, etc. Besides, deep learning models use a great number of hyper-parameters, the overfitting in deep models is more attention. To solve this problem, the regularized learning models can be followed. The aim of this paper is to review the approaches presented to regularize the overfitting in different categories of ITS studies. Then, we give a case study on driving safety that uses a regularized version of the convolutional neural network (CNN).
Tasks	Decision Making, Traffic Prediction
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03010v1
PDF	https://arxiv.org/pdf/1911.03010v1.pdf
PWC	https://paperswithcode.com/paper/regularized-deep-networks-in-intelligent
Repo
Framework

Revisiting Flow Information for Traffic Prediction


Title	Revisiting Flow Information for Traffic Prediction
Authors	Xian Zhou, Yanyan Shen, Linpeng Huang
Abstract	Traffic prediction is a fundamental task in many real applications, which aims to predict the future traffic volume in any region of a city. In essence, traffic volume in a region is the aggregation of traffic flows from/to the region. However, existing traffic prediction methods focus on modeling complex spatiotemporal traffic correlations and seldomly study the influence of the original traffic flows among regions. In this paper, we revisit the traffic flow information and exploit the direct flow correlations among regions towards more accurate traffic prediction. We introduce a novel flow-aware graph convolution to model dynamic flow correlations among regions. We further introduce an integrated Gated Recurrent Unit network to incorporate flow correlations with spatiotemporal modeling. The experimental results on real-world traffic datasets validate the effectiveness of the proposed method, especially on the traffic conditions with a great change on flows.
Tasks	Traffic Prediction
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00560v1
PDF	https://arxiv.org/pdf/1906.00560v1.pdf
PWC	https://paperswithcode.com/paper/190600560
Repo
Framework


Title	DeepMNavigate: Deep Reinforced Multi-Robot Navigation Unifying Local & Global Collision Avoidance
Authors	Qingyang Tan, Tingxiang Fan, Jia Pan, Dinesh Manocha
Abstract	We present a novel algorithm (DeepMNavigate) for global multi-agent navigation in dense scenarios using deep reinforcement learning (DRL). Our approach uses local and global information for each robot from motion information maps. We use a three-layer CNN that takes these maps as input to generate a suitable action to drive each robot to its goal position. Our approach is general, learns an optimal policy using a multi-scenario, multi-state training algorithm, and can directly handle raw sensor measurements for local observations. We demonstrate the performance on dense, complex benchmarks with narrow passages and environments with tens of agents. We highlight the algorithm’s benefits over prior learning methods and geometric decentralized algorithms in complex scenarios.
Tasks	Robot Navigation
Published	2019-10-04
URL	https://arxiv.org/abs/1910.09441v3
PDF	https://arxiv.org/pdf/1910.09441v3.pdf
PWC	https://paperswithcode.com/paper/deepmnavigate-deep-reinforced-multi-robot
Repo
Framework

Bayesian Optimization for Iterative Learning


Title	Bayesian Optimization for Iterative Learning
Authors	Vu Nguyen, Sebastian Schulze, Michael A Osborne
Abstract	Deep (reinforcement) learning systems are sensitive to hyperparameters which are notoriously expensive to tune, typically requiring running iterative processes over multiple epochs or episodes. Traditional tuning approaches only consider the final performance of a hyperparameter, ignoring intermediate information from the learning curve. In this paper, we present a Bayesian optimization approach which exploits the iterative structure of learning algorithms for efficient hyperparameter tuning. First, we transform each training curve into numeric scores representing training success as well as stability. Second, we selectively augment the data using the information from the curve. This augmentation step enables modeling efficiency. We demonstrate the efficiency of our algorithm by tuning hyperparameters for the training of deep reinforcement learning agents and convolutional neural networks. Our algorithm outperforms all existing baselines in identifying optimal hyperparameters in minimal time.
Tasks
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09593v3
PDF	https://arxiv.org/pdf/1909.09593v3.pdf
PWC	https://paperswithcode.com/paper/bayesian-optimization-for-iterative-learning
Repo
Framework

Policy Distillation and Value Matching in Multiagent Reinforcement Learning


Title	Policy Distillation and Value Matching in Multiagent Reinforcement Learning
Authors	Samir Wadhwania, Dong-Ki Kim, Shayegan Omidshafiei, Jonathan P. How
Abstract	Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via centralized critics to stabilize learning or through communication to increase performance, but do not generally look at how information can be shared between agents to address the curse of dimensionality in MARL. We posit that a multiagent problem can be decomposed into a multi-task problem where each agent explores a subset of the state space instead of exploring the entire state space. This paper introduces a multiagent actor-critic algorithm and method for combining knowledge from homogeneous agents through distillation and value-matching that outperforms policy distillation alone and allows further learning in both discrete and continuous action spaces.
Tasks
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06592v1
PDF	http://arxiv.org/pdf/1903.06592v1.pdf
PWC	https://paperswithcode.com/paper/policy-distillation-and-value-matching-in
Repo
Framework

Interaction-Aware Multi-Agent Reinforcement Learning for Mobile Agents with Individual Goals


Title	Interaction-Aware Multi-Agent Reinforcement Learning for Mobile Agents with Individual Goals
Authors	Anahita Mohseni-Kabir, David Isele, Kikuo Fujimura
Abstract	In a multi-agent setting, the optimal policy of a single agent is largely dependent on the behavior of other agents. We investigate the problem of multi-agent reinforcement learning, focusing on decentralized learning in non-stationary domains for mobile robot navigation. We identify a cause for the difficulty in training non-stationary policies: mutual adaptation to sub-optimal behaviors, and we use this to motivate a curriculum-based strategy for learning interactive policies. The curriculum has two stages. First, the agent leverages policy gradient algorithms to learn a policy that is capable of achieving multiple goals. Second, the agent learns a modifier policy to learn how to interact with other agents in a multi-agent setting. We evaluated our approach on both an autonomous driving lane-change domain and a robot navigation domain.
Tasks	Autonomous Driving, Multi-agent Reinforcement Learning, Robot Navigation
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12925v1
PDF	https://arxiv.org/pdf/1909.12925v1.pdf
PWC	https://paperswithcode.com/paper/interaction-aware-multi-agent-reinforcement
Repo
Framework

User Traffic Prediction for Proactive Resource Management: Learning-Powered Approaches


Title	User Traffic Prediction for Proactive Resource Management: Learning-Powered Approaches
Authors	Amin Azari, Panagiotis Papapetrou, Stojan Denic, Gunnar Peters
Abstract	Traffic prediction plays a vital role in efficient planning and usage of network resources in wireless networks. While traffic prediction in wired networks is an established field, there is a lack of research on the analysis of traffic in cellular networks, especially in a content-blind manner at the user level. Here, we shed light into this problem by designing traffic prediction tools that employ either statistical, rule-based, or deep machine learning methods. First, we present an extensive experimental evaluation of the designed tools over a real traffic dataset. Within this analysis, the impact of different parameters, such as length of prediction, feature set used in analyses, and granularity of data, on accuracy of prediction are investigated. Second, regarding the coupling observed between behavior of traffic and its generating application, we extend our analysis to the blind classification of applications generating the traffic based on the statistics of traffic arrival/departure. The results demonstrate presence of a threshold number of previous observations, beyond which, deep machine learning can outperform linear statistical learning, and before which, statistical learning outperforms deep learning approaches. Further analysis of this threshold value represents a strong coupling between this threshold, the length of future prediction, and the feature set in use. Finally, through a case study, we present how the experienced delay could be decreased by traffic arrival prediction.
Tasks	Future prediction, Traffic Prediction
Published	2019-05-09
URL	https://arxiv.org/abs/1906.00951v1
PDF	https://arxiv.org/pdf/1906.00951v1.pdf
PWC	https://paperswithcode.com/paper/190600951
Repo
Framework

Scaled Autonomy: Enabling Human Operators to Control Robot Fleets


Title	Scaled Autonomy: Enabling Human Operators to Control Robot Fleets
Authors	Gokul Swamy, Siddharth Reddy, Sergey Levine, Anca D. Dragan
Abstract	Autonomous robots often encounter challenging situations where their control policies fail and an expert human operator must briefly intervene, e.g., through teleoperation. In settings where multiple robots act in separate environments, a single human operator can manage a fleet of robots by identifying and teleoperating one robot at any given time. The key challenge is that users have limited attention: as the number of robots increases, users lose the ability to decide which robot requires teleoperation the most. Our goal is to automate this decision, thereby enabling users to supervise more robots than their attention would normally allow for. Our insight is that we can model the user’s choice of which robot to control as an approximately optimal decision that maximizes the user’s utility function. We learn a model of the user’s preferences from observations of the user’s choices in easy settings with a few robots, and use it in challenging settings with more robots to automatically identify which robot the user would most likely choose to control, if they were able to evaluate the states of all robots at all times. We run simulation experiments and a user study with twelve participants that show our method can be used to assist users in performing a simulated navigation task. We also run a hardware demonstration that illustrates how our method can be applied to a real-world mobile robot navigation task.
Tasks	Robot Navigation
Published	2019-09-22
URL	https://arxiv.org/abs/1910.02910v2
PDF	https://arxiv.org/pdf/1910.02910v2.pdf
PWC	https://paperswithcode.com/paper/scaled-autonomy-enabling-human-operators-to
Repo
Framework