January 26, 2020

3200 words 16 mins read

Paper Group ANR 1359

CrossNorm: Normalization for Off-Policy TD Reinforcement Learning. Convolutional Relational Machine for Group Activity Recognition. Deep Learning for Distributed Optimization: Applications to Wireless Resource Management. FANTrack: 3D Multi-Object Tracking with Feature Association Network. Evaluating Memento Service Optimizations. Differentially Pr …

CrossNorm: Normalization for Off-Policy TD Reinforcement Learning


Title	CrossNorm: Normalization for Off-Policy TD Reinforcement Learning
Authors	Aditya Bhatt, Max Argus, Artemij Amiranashvili, Thomas Brox
Abstract	Off-policy temporal difference (TD) methods are a powerful class of reinforcement learning (RL) algorithms. Intriguingly, deep off-policy TD algorithms are not commonly used in combination with feature normalization techniques, despite positive effects of normalization in other domains. We show that naive application of existing normalization techniques is indeed not effective, but that well-designed normalization improves optimization stability and removes the necessity of target networks. In particular, we introduce a normalization based on a mixture of on- and off-policy transitions, which we call cross-normalization. It can be regarded as an extension of batch normalization that re-centers data for two different distributions, as present in off-policy learning. Applied to DDPG and TD3, cross-normalization improves over the state of the art across a range of MuJoCo benchmark tasks.
Tasks
Published	2019-02-14
URL	https://arxiv.org/abs/1902.05605v2
PDF	https://arxiv.org/pdf/1902.05605v2.pdf
PWC	https://paperswithcode.com/paper/crossnorm-normalization-for-off-policy-td
Repo
Framework

Convolutional Relational Machine for Group Activity Recognition


Title	Convolutional Relational Machine for Group Activity Recognition
Authors	Sina Mokhtarzadeh Azar, Mina Ghadimi Atigh, Ahmad Nickabadi, Alexandre Alahi
Abstract	We present an end-to-end deep Convolutional Neural Network called Convolutional Relational Machine (CRM) for recognizing group activities that utilizes the information in spatial relations between individual persons in image or video. It learns to produce an intermediate spatial representation (activity map) based on individual and group activities. A multi-stage refinement component is responsible for decreasing the incorrect predictions in the activity map. Finally, an aggregation component uses the refined information to recognize group activities. Experimental results demonstrate the constructive contribution of the information extracted and represented in the form of the activity map. CRM shows advantages over state-of-the-art models on Volleyball and Collective Activity datasets.
Tasks	Activity Recognition, Group Activity Recognition
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03308v1
PDF	http://arxiv.org/pdf/1904.03308v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-relational-machine-for-group
Repo
Framework

Deep Learning for Distributed Optimization: Applications to Wireless Resource Management


Title	Deep Learning for Distributed Optimization: Applications to Wireless Resource Management
Authors	Hoon Lee, Sang Hyun Lee, Tony Q. S. Quek
Abstract	This paper studies a deep learning (DL) framework to solve distributed non-convex constrained optimizations in wireless networks where multiple computing nodes, interconnected via backhaul links, desire to determine an efficient assignment of their states based on local observations. Two different configurations are considered: First, an infinite-capacity backhaul enables nodes to communicate in a lossless way, thereby obtaining the solution by centralized computations. Second, a practical finite-capacity backhaul leads to the deployment of distributed solvers equipped along with quantizers for communication through capacity-limited backhaul. The distributed nature and the nonconvexity of the optimizations render the identification of the solution unwieldy. To handle them, deep neural networks (DNNs) are introduced to approximate an unknown computation for the solution accurately. In consequence, the original problems are transformed to training tasks of the DNNs subject to non-convex constraints where existing DL libraries fail to extend straightforwardly. A constrained training strategy is developed based on the primal-dual method. For distributed implementation, a novel binarization technique at the output layer is developed for quantization at each node. Our proposed distributed DL framework is examined in various network configurations of wireless resource management. Numerical results verify the effectiveness of our proposed approach over existing optimization techniques.
Tasks	Distributed Optimization, Quantization
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13378v1
PDF	https://arxiv.org/pdf/1905.13378v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-distributed-optimization
Repo
Framework

FANTrack: 3D Multi-Object Tracking with Feature Association Network


Title	FANTrack: 3D Multi-Object Tracking with Feature Association Network
Authors	Erkan Baser, Venkateshwaran Balasubramanian, Prarthana Bhattacharyya, Krzysztof Czarnecki
Abstract	We propose a data-driven approach to online multi-object tracking (MOT) that uses a convolutional neural network (CNN) for data association in a tracking-by-detection framework. The problem of multi-target tracking aims to assign noisy detections to a-priori unknown and time-varying number of tracked objects across a sequence of frames. A majority of the existing solutions focus on either tediously designing cost functions or formulating the task of data association as a complex optimization problem that can be solved effectively. Instead, we exploit the power of deep learning to formulate the data association problem as inference in a CNN. To this end, we propose to learn a similarity function that combines cues from both image and spatial features of objects. Our solution learns to perform global assignments in 3D purely from data, handles noisy detections and a varying number of targets, and is easy to train. We evaluate our approach on the challenging KITTI dataset and show competitive results. Our code is available at https://git.uwaterloo.ca/wise-lab/fantrack.
Tasks	3D Multi-Object Tracking, Multi-Object Tracking, Object Tracking, Online Multi-Object Tracking
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02843v1
PDF	https://arxiv.org/pdf/1905.02843v1.pdf
PWC	https://paperswithcode.com/paper/fantrack-3d-multi-object-tracking-with
Repo
Framework

Evaluating Memento Service Optimizations


Title	Evaluating Memento Service Optimizations
Authors	Martin Klein, Lyudmila Balakireva, Harihar Shankar
Abstract	Services and applications based on the Memento Aggregator can suffer from slow response times due to the federated search across web archives performed by the Memento infrastructure. In an effort to decrease the response times, we established a cache system and experimented with machine learning models to predict archival holdings. We reported on the experimental results in previous work and can now, after these optimizations have been in production for two years, evaluate their efficiency, based on long-term log data. During our investigation we find that the cache is very effective with a 70-80% cache hit rate for human-driven services. The machine learning prediction operates at an acceptable average recall level of 0.727 but our results also show that a more frequent retraining of the models is needed to further improve prediction accuracy.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1906.00058v1
PDF	https://arxiv.org/pdf/1906.00058v1.pdf
PWC	https://paperswithcode.com/paper/190600058
Repo
Framework

Differentially Private Continual Learning


Title	Differentially Private Continual Learning
Authors	Sebastian Farquhar, Yarin Gal
Abstract	Catastrophic forgetting can be a significant problem for institutions that must delete historic data for privacy reasons. For example, hospitals might not be able to retain patient data permanently. But neural networks trained on recent data alone will tend to forget lessons learned on old data. We present a differentially private continual learning framework based on variational inference. We estimate the likelihood of past data given the current model using differentially private generative models of old datasets.
Tasks	Continual Learning
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06497v1
PDF	http://arxiv.org/pdf/1902.06497v1.pdf
PWC	https://paperswithcode.com/paper/differentially-private-continual-learning
Repo
Framework

Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey


Title	Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey
Authors	Roxana Rădulescu, Patrick Mannion, Diederik M. Roijers, Ann Nowé
Abstract	The majority of multi-agent system (MAS) implementations aim to optimise agents’ policies with respect to a single objective, despite the fact that many real-world problem domains are inherently multi-objective in nature. Multi-objective multi-agent systems (MOMAS) explicitly consider the possible trade-offs between conflicting objective functions. We argue that, in MOMAS, such compromises should be analysed on the basis of the utility that these compromises have for the users of a system. As is standard in multi-objective optimisation, we model the user utility using utility functions that map value or return vectors to scalar values. This approach naturally leads to two different optimisation criteria: expected scalarised returns (ESR) and scalarised expected returns (SER). We develop a new taxonomy which classifies multi-objective multi-agent decision making settings, on the basis of the reward structures, and which and how utility functions are applied. This allows us to offer a structured view of the field, to clearly delineate the current state-of-the-art in multi-objective multi-agent decision making approaches and to identify promising directions for future research. Starting from the execution phase, in which the selected policies are applied and the utility for the users is attained, we analyse which solution concepts apply to the different settings in our taxonomy. Furthermore, we define and discuss these solution concepts under both ESR and SER optimisation criteria. We conclude with a summary of our main findings and a discussion of many promising future research directions in multi-objective multi-agent systems.
Tasks	Decision Making
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02964v1
PDF	https://arxiv.org/pdf/1909.02964v1.pdf
PWC	https://paperswithcode.com/paper/multi-objective-multi-agent-decision-making-a
Repo
Framework

Predicting the Long-Term Outcomes of Biologics in Psoriasis Patients Using Machine Learning


Title	Predicting the Long-Term Outcomes of Biologics in Psoriasis Patients Using Machine Learning
Authors	Sepideh Emam, Amy X. Du, Philip Surmanowicz, Simon F. Thomsen, Russ Greiner, Robert Gniadecki
Abstract	Background. Real-world data show that approximately 50% of psoriasis patients treated with a biologic agent will discontinue the drug because of loss of efficacy. History of previous therapy with another biologic, female sex and obesity were identified as predictors of drug discontinuations, but their individual predictive value is low. Objectives. To determine whether machine learning algorithms can produce models that can accurately predict outcomes of biologic therapy in psoriasis on individual patient level. Results. All tested machine learning algorithms could accurately predict the risk of drug discontinuation and its cause (e.g. lack of efficacy vs adverse event). The learned generalized linear model achieved diagnostic accuracy of 82%, requiring under 2 seconds per patient using the psoriasis patients dataset. Input optimization analysis established a profile of a patient who has best chances of long-term treatment success: biologic-naive patient under 49 years, early-onset plaque psoriasis without psoriatic arthritis, weight < 100 kg, and moderate-to-severe psoriasis activity (DLQI $\geq$ 16; PASI $\geq$ 10). Moreover, a different generalized linear model is used to predict the length of treatment for each patient with mean absolute error (MAE) of 4.5 months. However Pearson Correlation Coefficient indicates 0.935 linear dependencies between the actual treatment lengths and predicted ones. Conclusions. Machine learning algorithms predict the risk of drug discontinuation and treatment duration with accuracy exceeding 80%, based on a small set of predictive variables. This approach can be used as a decision-making tool, communicating expected outcomes to the patient, and development of evidence-based guidelines.
Tasks	Decision Making
Published	2019-08-25
URL	https://arxiv.org/abs/1908.09251v1
PDF	https://arxiv.org/pdf/1908.09251v1.pdf
PWC	https://paperswithcode.com/paper/predicting-the-long-term-outcomes-of
Repo
Framework

DASNet: Dynamic Activation Sparsity for Neural Network Efficiency Improvement


Title	DASNet: Dynamic Activation Sparsity for Neural Network Efficiency Improvement
Authors	Qing Yang, Jiachen Mao, Zuoguan Wang, Hai Li
Abstract	To improve the execution speed and efficiency of neural networks in embedded systems, it is crucial to decrease the model size and computational complexity. In addition to conventional compression techniques, e.g., weight pruning and quantization, removing unimportant activations can reduce the amount of data communication and the computation cost. Unlike weight parameters, the pattern of activations is directly related to input data and thereby changes dynamically. To regulate the dynamic activation sparsity (DAS), in this work, we propose a generic low-cost approach based on winners-take-all (WTA) dropout technique. The network enhanced by the proposed WTA dropout, namely \textit{DASNet}, features structured activation sparsity with an improved sparsity level. Compared to the static feature map pruning methods, DASNets provide better computation cost reduction. The WTA technique can be easily applied in deep neural networks without incurring additional training variables. More importantly, DASNet can be seamlessly integrated with other compression techniques, such as weight pruning and quantization, without compromising on accuracy. Our experiments on various networks and datasets present significant run-time speedups with negligible accuracy loss.
Tasks	Quantization
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06964v1
PDF	https://arxiv.org/pdf/1909.06964v1.pdf
PWC	https://paperswithcode.com/paper/dasnet-dynamic-activation-sparsity-for-neural
Repo
Framework

Fuzzy neural networks to create an expert system for detecting attacks by SQL Injection


Title	Fuzzy neural networks to create an expert system for detecting attacks by SQL Injection
Authors	Lucas Oliveira Batista, Gabriel Adriano de Silva, Vanessa Souza Araújo, Vinícius Jonathan Silva Araújo, Thiago Silva Rezende, Augusto Junio Guimarães, Paulo Vitor de Campos Souza
Abstract	Its constant technological evolution characterizes the contemporary world, and every day the processes, once manual, become computerized. Data are stored in the cyberspace, and as a consequence, one must increase the concern with the security of this environment. Cyber-attacks are represented by a growing worldwide scale and are characterized as one of the significant challenges of the century. This article aims to propose a computational system based on intelligent hybrid models, which through fuzzy rules allows the construction of expert systems in cybernetic data attacks, focusing on the SQL Injection attack. The tests were performed with real bases of SQL Injection attacks on government computers, using fuzzy neural networks. According to the results obtained, the feasibility of constructing a system based on fuzzy rules, with the classification accuracy of cybernetic invasions within the margin of the standard deviation (compared to the state-of-the-art model in solving this type of problem) is real. The model helps countries prepare to protect their data networks and information systems, as well as create opportunities for expert systems to automate the identification of attacks in cyberspace.
Tasks
Published	2019-01-09
URL	http://arxiv.org/abs/1901.02868v1
PDF	http://arxiv.org/pdf/1901.02868v1.pdf
PWC	https://paperswithcode.com/paper/fuzzy-neural-networks-to-create-an-expert
Repo
Framework

A Survey of Tuning Parameter Selection for High-dimensional Regression


Title	A Survey of Tuning Parameter Selection for High-dimensional Regression
Authors	Yunan Wu, Lan Wang
Abstract	Penalized (or regularized) regression, as represented by Lasso and its variants, has become a standard technique for analyzing high-dimensional data when the number of variables substantially exceeds the sample size. The performance of penalized regression relies crucially on the choice of the tuning parameter, which determines the amount of regularization and hence the sparsity level of the fitted model. The optimal choice of tuning parameter depends on both the structure of the design matrix and the unknown random error distribution (variance, tail behavior, etc). This article reviews the current literature of tuning parameter selection for high-dimensional regression from both theoretical and practical perspectives. We discuss various strategies that choose the tuning parameter to achieve prediction accuracy or support recovery. We also review several recently proposed methods for tuning-free high-dimensional regression.
Tasks
Published	2019-08-10
URL	https://arxiv.org/abs/1908.03669v1
PDF	https://arxiv.org/pdf/1908.03669v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-tuning-parameter-selection-for
Repo
Framework

Bayesian Graph Convolutional Neural Networks using Node Copying


Title	Bayesian Graph Convolutional Neural Networks using Node Copying
Authors	Soumyasundar Pal, Florence Regol, Mark Coates
Abstract	Graph convolutional neural networks (GCNN) have numerous applications in different graph based learning tasks. Although the techniques obtain impressive results, they often fall short in accounting for the uncertainty associated with the underlying graph structure. In the recently proposed Bayesian GCNN (BGCN) framework, this issue is tackled by viewing the observed graph as a sample from a parametric random graph model and targeting joint inference of the graph and the GCNN weights. In this paper, we introduce an alternative generative model for graphs based on copying nodes and incorporate it within the BGCN framework. Our approach has the benefit that it uses information provided by the node features and training labels in the graph topology inference. Experiments show that the proposed algorithm compares favorably to the state-of-the-art in benchmark node classification tasks.
Tasks	Node Classification
Published	2019-11-08
URL	https://arxiv.org/abs/1911.04965v1
PDF	https://arxiv.org/pdf/1911.04965v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-graph-convolutional-neural-networks-2
Repo
Framework

Kidney tumor segmentation using an ensembling multi-stage deep learning approach. A contribution to the KiTS19 challenge


Title	Kidney tumor segmentation using an ensembling multi-stage deep learning approach. A contribution to the KiTS19 challenge
Authors	Gianmarco Santini, Noémi Moreau, Mathieu Rubeaux
Abstract	Precise characterization of the kidney and kidney tumor characteristics is of outmost importance in the context of kidney cancer treatment, especially for nephron sparing surgery which requires a precise localization of the tissues to be removed. The need for accurate and automatic delineation tools is at the origin of the KiTS19 challenge. It aims at accelerating the research and development in this field to aid prognosis and treatment planning by providing a characterized dataset of 300 CT scans to be segmented. To address the challenge, we proposed an automatic, multi-stage, 2.5D deep learning-based segmentation approach based on Residual UNet framework. An ensembling operation is added at the end to combine prediction results from previous stages reducing the variance between single models. Our neural network segmentation algorithm reaches a mean Dice score of 0.96 and 0.74 for kidney and kidney tumors, respectively on 90 unseen test cases. The results obtained are promising and could be improved by incorporating prior knowledge about the benign cysts that regularly lower the tumor segmentation results.
Tasks
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00735v1
PDF	https://arxiv.org/pdf/1909.00735v1.pdf
PWC	https://paperswithcode.com/paper/kidney-tumor-segmentation-using-an-ensembling
Repo
Framework

Training Object Detectors on Synthetic Images Containing Reflecting Materials


Title	Training Object Detectors on Synthetic Images Containing Reflecting Materials
Authors	Sebastian Hartwig, Timo Ropinski
Abstract	One of the grand challenges of deep learning is the requirement to obtain large labeled training data sets. While synthesized data sets can be used to overcome this challenge, it is important that these data sets close the reality gap, i.e., a model trained on synthetic image data is able to generalize to real images. Whereas, the reality gap can be considered bridged in several application scenarios, training on synthesized images containing reflecting materials requires further research. Since the appearance of objects with reflecting materials is dominated by the surrounding environment, this interaction needs to be considered during training data generation. Therefore, within this paper we examine the effect of reflecting materials in the context of synthetic image generation for training object detectors. We investigate the influence of rendering approach used for image synthesis, the effect of domain randomization, as well as the amount of used training data. To be able to compare our results to the state-of-the-art, we focus on indoor scenes as they have been investigated extensively. Within this scenario, bathroom furniture is a natural choice for objects with reflecting materials, for which we report our findings on real and synthetic testing data.
Tasks	Image Generation
Published	2019-03-29
URL	http://arxiv.org/abs/1904.00824v1
PDF	http://arxiv.org/pdf/1904.00824v1.pdf
PWC	https://paperswithcode.com/paper/training-object-detectors-on-synthetic-images
Repo
Framework

Artificial Intelligence for Low-Resource Communities: Influence Maximization in an Uncertain World


Title	Artificial Intelligence for Low-Resource Communities: Influence Maximization in an Uncertain World
Authors	Amulya Yadav
Abstract	The potential of Artificial Intelligence (AI) to tackle challenging problems that afflict society is enormous, particularly in the areas of healthcare, conservation and public safety and security. Many problems in these domains involve harnessing social networks of under-served communities to enable positive change, e.g., using social networks of homeless youth to raise awareness about Human Immunodeficiency Virus (HIV) and other STDs. Unfortunately, most of these real-world problems are characterized by uncertainties about social network structure and influence models, and previous research in AI fails to sufficiently address these uncertainties. This thesis addresses these shortcomings by advancing the state-of-the-art to a new generation of algorithms for interventions in social networks. In particular, this thesis describes the design and development of new influence maximization algorithms which can handle various uncertainties that commonly exist in real-world social networks. These algorithms utilize techniques from sequential planning problems and social network theory to develop new kinds of AI algorithms. Further, this thesis also demonstrates the real-world impact of these algorithms by describing their deployment in three pilot studies to spread awareness about HIV among actual homeless youth in Los Angeles. This represents one of the first-ever deployments of computer science based influence maximization algorithms in this domain. Our results show that our AI algorithms improved upon the state-of-the-art by 160% in the real-world. We discuss research and implementation challenges faced in deploying these algorithms, and lessons that can be gleaned for future deployment of such algorithms. The positive results from these deployments illustrate the enormous potential of AI in addressing societally relevant problems.
Tasks
Published	2019-12-03
URL	https://arxiv.org/abs/1912.02102v1
PDF	https://arxiv.org/pdf/1912.02102v1.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-for-low-resource
Repo
Framework