Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00138
G. Drakopoulos, Xenophon Liapakis, Giannis Tzimas, Phivos Mylonas
Structural resilience is an inherent, paramount property of real world, massive, scale free graphs such as those typically encountered in brain networks, protein-to-protein interaction diagrams, logistics and supply chains, as well as social media among others. This means that in case a small fraction of edges or even vertices with their incident edges are deleted, then alternative, although possibly longer, paths can be found such that the overall graph connectivity remains intact. This durability, which is constantly exhibited in nature, can be attributed to three main reasons. First, almost by construction, scale free graphs have a relatively high density. Moreover, they have a short diameter or at least an effective diameter. Finally, scale free graphs are recursively built on communities. As a consequence, the effect of a few edge or even vertex deletions inside a community remains isolated there as a rule and the effects of deletion are thus negated. Ultimately these properties stem from the degree distribution. In this conference paper is proposed a new, generic, and scalable graph resilience metric which relies on the weighted sum of the number of paths crossing certain vertices of great communication and structural value. Finally, the CUDA implementation is discussed and compared to a serial one in mex. The metric performance is assessed in terms of total computational time and parallelism.
{"title":"A Graph Resilience Metric Based On Paths: Higher Order Analytics With GPU","authors":"G. Drakopoulos, Xenophon Liapakis, Giannis Tzimas, Phivos Mylonas","doi":"10.1109/ICTAI.2018.00138","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00138","url":null,"abstract":"Structural resilience is an inherent, paramount property of real world, massive, scale free graphs such as those typically encountered in brain networks, protein-to-protein interaction diagrams, logistics and supply chains, as well as social media among others. This means that in case a small fraction of edges or even vertices with their incident edges are deleted, then alternative, although possibly longer, paths can be found such that the overall graph connectivity remains intact. This durability, which is constantly exhibited in nature, can be attributed to three main reasons. First, almost by construction, scale free graphs have a relatively high density. Moreover, they have a short diameter or at least an effective diameter. Finally, scale free graphs are recursively built on communities. As a consequence, the effect of a few edge or even vertex deletions inside a community remains isolated there as a rule and the effects of deletion are thus negated. Ultimately these properties stem from the degree distribution. In this conference paper is proposed a new, generic, and scalable graph resilience metric which relies on the weighted sum of the number of paths crossing certain vertices of great communication and structural value. Finally, the CUDA implementation is discussed and compared to a serial one in mex. The metric performance is assessed in terms of total computational time and parallelism.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130693545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00100
Tao Ding, Fatema Hasan, W. Bickel, Shimei Pan
People nowadays spend a significant amount of time on social media such as Twitter, Facebook, and Instagram. As a result, social media data capture rich human behavioral evidence that can be used to help us understand their thoughts, behavior and decision making process. Social media data, however, are mostly unstructured (e.g., text and images) and may involve a large number of raw features (e.g., millions of raw text and image features). Moreover, the ground truth data about human behavior and decision making could be difficult to obtain at a large scale. As a result, most state-of-the-art social media-based human behavior models employ sophisticated unsupervised feature learning to leverage a large amount of unsupervised data. Unfortunately, these advanced models often rely on latent features that are hard to explain. Since understanding the knowledge captured in these models is important for behavior scientists, public health providers as well as policymakers, in this research, we focus on employing a knowledge distillation framework to build machine learning models with not only state-of-the-art predictive performance but also interpretable results. We evaluate the effectiveness of the proposed framework in explaining Substance Use Disorder (SUD) prediction models. Our best models achieved 87% ROC AUC for predicting tobacco use, 84% for alcohol use and 93% for drug use, which are comparable to existing state-of-the-art SUD prediction models. Since these models are also interpretable (e.g., a logistics regression model and a gradient boosting tree model), we combine the results from these models to gain insight into the relationship between a user's social media behavior (e.g., social media likes and word usage) and substance use.
{"title":"Interpreting Social Media-Based Substance Use Prediction Models with Knowledge Distillation","authors":"Tao Ding, Fatema Hasan, W. Bickel, Shimei Pan","doi":"10.1109/ICTAI.2018.00100","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00100","url":null,"abstract":"People nowadays spend a significant amount of time on social media such as Twitter, Facebook, and Instagram. As a result, social media data capture rich human behavioral evidence that can be used to help us understand their thoughts, behavior and decision making process. Social media data, however, are mostly unstructured (e.g., text and images) and may involve a large number of raw features (e.g., millions of raw text and image features). Moreover, the ground truth data about human behavior and decision making could be difficult to obtain at a large scale. As a result, most state-of-the-art social media-based human behavior models employ sophisticated unsupervised feature learning to leverage a large amount of unsupervised data. Unfortunately, these advanced models often rely on latent features that are hard to explain. Since understanding the knowledge captured in these models is important for behavior scientists, public health providers as well as policymakers, in this research, we focus on employing a knowledge distillation framework to build machine learning models with not only state-of-the-art predictive performance but also interpretable results. We evaluate the effectiveness of the proposed framework in explaining Substance Use Disorder (SUD) prediction models. Our best models achieved 87% ROC AUC for predicting tobacco use, 84% for alcohol use and 93% for drug use, which are comparable to existing state-of-the-art SUD prediction models. Since these models are also interpretable (e.g., a logistics regression model and a gradient boosting tree model), we combine the results from these models to gain insight into the relationship between a user's social media behavior (e.g., social media likes and word usage) and substance use.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133939890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00035
B. Díaz-Agudo, Guillermo Jiménez-Díaz, J. A. Recio-García
Social systems by their definition encourage interaction between users and both on-line content and other users thus generating new sources of knowledge that is valuable for recommender systems. In this paper we deal with the situation of having a recommender system where, even if a social structure implicitly exist, its users are not explicitly connected through a social network. We describe SocialFan, a domain independent tool that allows defining and integrating the social network infrastructure to capture and use the social knowledge into an existing recommender system.
{"title":"SocialFan: Integrating Social Networks Into Recommender Systems","authors":"B. Díaz-Agudo, Guillermo Jiménez-Díaz, J. A. Recio-García","doi":"10.1109/ICTAI.2018.00035","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00035","url":null,"abstract":"Social systems by their definition encourage interaction between users and both on-line content and other users thus generating new sources of knowledge that is valuable for recommender systems. In this paper we deal with the situation of having a recommender system where, even if a social structure implicitly exist, its users are not explicitly connected through a social network. We describe SocialFan, a domain independent tool that allows defining and integrating the social network infrastructure to capture and use the social knowledge into an existing recommender system.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134395508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00020
N. Dervenis, Georgios Alexandridis, A. Stafylopatis
Integrated spiral inductors are a fundamental part of Radio-Frequency (RF) circuits. In certain scenarios, a solution to the inverse spiral inductor design problem is required; given the desired properties of an inductor, locate the most suitable geometric characteristics. This problem does not have a unique solution and current approaches approximate it through a number of differential equations and the subsequent application of optimization techniques that narrow down the set of feasible solutions. In this work, the Neural Network Specialists model is outlined; a preliminary approach to solving the aforementioned problem using fully connected neural network models. The obtained results on a first round of experiments are encouraging, especially in terms of the reduction in time complexity.
{"title":"Neural Network Specialists for Inverse Spiral Inductor Design","authors":"N. Dervenis, Georgios Alexandridis, A. Stafylopatis","doi":"10.1109/ICTAI.2018.00020","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00020","url":null,"abstract":"Integrated spiral inductors are a fundamental part of Radio-Frequency (RF) circuits. In certain scenarios, a solution to the inverse spiral inductor design problem is required; given the desired properties of an inductor, locate the most suitable geometric characteristics. This problem does not have a unique solution and current approaches approximate it through a number of differential equations and the subsequent application of optimization techniques that narrow down the set of feasible solutions. In this work, the Neural Network Specialists model is outlined; a preliminary approach to solving the aforementioned problem using fully connected neural network models. The obtained results on a first round of experiments are encouraging, especially in terms of the reduction in time complexity.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129316231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00101
T. M. G. Tennakoon, R. Nayak
In this paper we introduce the flow hierarchy derived from frequent interactions to represent complex social networks in a concise way. Frequent interactions extract the impactful users while the flow hierarchy visualizes the dependencies and identifies different roles such as leaders, topic experts, information disseminators, emerging leaders and active followers. It is highly applicable in intelligent systems which involve user ranking, expert searching, recommendation, viral marketing, political campaigning, disaster management and many more. We present novel methods of deriving flow hierarchy considering the temporal dimension of interactions among users, flow directions and structural dependencies. We empirically evaluate proposed methods using real-world social network interaction datasets related to citation and retweet networks. Empirical analysis reveals that a hierarchy derived from frequent social interactions is effective in extracting the impactful users and their position in the network. Baseline results with user-centric measures show the efficacy of the proposed methods in finding a concise network representation.
{"title":"A Concise Social Network Representation with Flow Hierarchy Using Frequent Interactions","authors":"T. M. G. Tennakoon, R. Nayak","doi":"10.1109/ICTAI.2018.00101","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00101","url":null,"abstract":"In this paper we introduce the flow hierarchy derived from frequent interactions to represent complex social networks in a concise way. Frequent interactions extract the impactful users while the flow hierarchy visualizes the dependencies and identifies different roles such as leaders, topic experts, information disseminators, emerging leaders and active followers. It is highly applicable in intelligent systems which involve user ranking, expert searching, recommendation, viral marketing, political campaigning, disaster management and many more. We present novel methods of deriving flow hierarchy considering the temporal dimension of interactions among users, flow directions and structural dependencies. We empirically evaluate proposed methods using real-world social network interaction datasets related to citation and retweet networks. Empirical analysis reveals that a hierarchy derived from frequent social interactions is effective in extracting the impactful users and their position in the network. Baseline results with user-centric measures show the efficacy of the proposed methods in finding a concise network representation.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115163876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00034
Yi He, Di Wu, Ege Beyazit, Xiaoduan Sun, Xindong Wu
Traffic crashes have threatened properties and lives for more than thirty years. Thanks to the recent proliferation of traffic data, the machine learning techniques have been broadly expected to make contributions in the traffic safety community due to their triumphs in many other domains. Among these contributions, the most cited method is to classify traffic crashes in different severities since they have significantly unequal occurrences and costs. However, considering the complexity of transportation system, the traffic data are usually highly imbalanced and lowly separable (HILS), so that few proposed works report satisfactory results. In this paper, we propose a novel framework to deal with the HILS traffic crash data. The framework comprises two parts. In part I, a novel Supervised Data Synthesizing and Evolving algorithm is proposed, which can properly represent the HILS data into a more balanced and separable form without altering the original data distribution. In part II, the details of a customized Multi-Layer Perceptron (MLP) are presented, serving the purpose of learning from the represented data with fast convergence and high accuracy. A real-world traffic crash dataset, as a benchmark, is employed to evaluate the classification performances of our framework and three state-of-the-art imbalanced learning algorithms. The experimental results validate that our framework significantly outperforms the other algorithms. Moreover, the impacts of various parameter settings are studied and discussed
{"title":"Supervised Data Synthesizing and Evolving – A Framework for Real-World Traffic Crash Severity Classification","authors":"Yi He, Di Wu, Ege Beyazit, Xiaoduan Sun, Xindong Wu","doi":"10.1109/ICTAI.2018.00034","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00034","url":null,"abstract":"Traffic crashes have threatened properties and lives for more than thirty years. Thanks to the recent proliferation of traffic data, the machine learning techniques have been broadly expected to make contributions in the traffic safety community due to their triumphs in many other domains. Among these contributions, the most cited method is to classify traffic crashes in different severities since they have significantly unequal occurrences and costs. However, considering the complexity of transportation system, the traffic data are usually highly imbalanced and lowly separable (HILS), so that few proposed works report satisfactory results. In this paper, we propose a novel framework to deal with the HILS traffic crash data. The framework comprises two parts. In part I, a novel Supervised Data Synthesizing and Evolving algorithm is proposed, which can properly represent the HILS data into a more balanced and separable form without altering the original data distribution. In part II, the details of a customized Multi-Layer Perceptron (MLP) are presented, serving the purpose of learning from the represented data with fast convergence and high accuracy. A real-world traffic crash dataset, as a benchmark, is employed to evaluate the classification performances of our framework and three state-of-the-art imbalanced learning algorithms. The experimental results validate that our framework significantly outperforms the other algorithms. Moreover, the impacts of various parameter settings are studied and discussed","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115673599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00127
Gregory Moro Puppi Wanderley, Marie-Hélène Abel, E. Paraiso, J. Barthès
Despite the great number of Systems of Systems (SoS) being developed, building them still remains hard and difficult. Currently, there is a lack of methods capable of supporting architects for building an actual SoS. In this paper we introduce an original method called GAMBAD for developing an SoS from a practical point of view. Our method guides the development of SoS on top of a multi-agent layer supported by ontologies. We tested GAMBAD by building an SoS in the domain of Health Care. Early results show that by using our method, architects can develop an SoS faster and more accurately.
{"title":"GAMBAD: A Method for Developing Systems of Systems","authors":"Gregory Moro Puppi Wanderley, Marie-Hélène Abel, E. Paraiso, J. Barthès","doi":"10.1109/ICTAI.2018.00127","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00127","url":null,"abstract":"Despite the great number of Systems of Systems (SoS) being developed, building them still remains hard and difficult. Currently, there is a lack of methods capable of supporting architects for building an actual SoS. In this paper we introduce an original method called GAMBAD for developing an SoS from a practical point of view. Our method guides the development of SoS on top of a multi-agent layer supported by ontologies. We tested GAMBAD by building an SoS in the domain of Health Care. Early results show that by using our method, architects can develop an SoS faster and more accurately.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124330114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00108
Kuruge Darshana Abeyrathna, Ole-Christoffer Granmo, M. G. Olsen
Being capable of online learning in unknown stochastic environments, Tsetlin Automata (TA) have gained considerable interest. As a model of biological systems, teams of TA have been used for solving complex problems in a decentralized manner, with low computational complexity. For many domains, decentralized problem solving is an advantage, however, also may lead to coordination difficulties and unstable learning. To combat this negative effect, this paper proposes a novel TA coordination scheme designed for learning problems with continuous input and output. By saving and updating the best solution that has been chosen so far, we can avoid having the overall system being led astray by spurious erroneous actions. We organize this process hierarchically by a principal-teacherclass structure. We further propose a binary representation of continuous actions (coefficients). Each coefficient in the cost function is represented by 8 TA. TA teams at different classes produce different solutions. They are trained to find the global optimum with the help of their own best and the overall best solutions. The proposed algorithm is tested first with an artificial dataset and later used to forecast dengue haemorrhagic fever in the Philippines. Results of the novel procedure are compared with results from two traditional TA approaches. The training error of the novel TA scheme is lower approx. 50 and 62 times compared to the considered two traditional Tsetlin Automata approaches and testing error is approx. 31 and 21 times lower for the new scheme. These improvements not only highlight the effectiveness of the proposed scheme, but also the importance of old, simple, yet powerful concepts in the Artificial Intelligence techniques.
{"title":"A Novel Tsetlin Automata Scheme to Forecast Dengue Outbreaks in the Philippines","authors":"Kuruge Darshana Abeyrathna, Ole-Christoffer Granmo, M. G. Olsen","doi":"10.1109/ICTAI.2018.00108","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00108","url":null,"abstract":"Being capable of online learning in unknown stochastic environments, Tsetlin Automata (TA) have gained considerable interest. As a model of biological systems, teams of TA have been used for solving complex problems in a decentralized manner, with low computational complexity. For many domains, decentralized problem solving is an advantage, however, also may lead to coordination difficulties and unstable learning. To combat this negative effect, this paper proposes a novel TA coordination scheme designed for learning problems with continuous input and output. By saving and updating the best solution that has been chosen so far, we can avoid having the overall system being led astray by spurious erroneous actions. We organize this process hierarchically by a principal-teacherclass structure. We further propose a binary representation of continuous actions (coefficients). Each coefficient in the cost function is represented by 8 TA. TA teams at different classes produce different solutions. They are trained to find the global optimum with the help of their own best and the overall best solutions. The proposed algorithm is tested first with an artificial dataset and later used to forecast dengue haemorrhagic fever in the Philippines. Results of the novel procedure are compared with results from two traditional TA approaches. The training error of the novel TA scheme is lower approx. 50 and 62 times compared to the considered two traditional Tsetlin Automata approaches and testing error is approx. 31 and 21 times lower for the new scheme. These improvements not only highlight the effectiveness of the proposed scheme, but also the importance of old, simple, yet powerful concepts in the Artificial Intelligence techniques.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116328942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00077
Jonathan Cohen, A. Mouaddib
Teamwork in decentralized systems plays a central role in recent artificial intelligence advances, such as in applications to disaster response. Decentralized partially observable Markov decision processes (Dec-POMDPs) have emerged as the de facto standard mathematical framework to study and optimally plan in sequentially decentralized multiagent systems under uncertainty. In this work, we focus our analysis on team formation and reformation in Decentralized POMDPs with a new model coined Team-POMDPs. We present some interesting structural properties of this model inherited from the field of cooperative game theory. We introduce a Monte Carlo-based planning algorithm to learn locally optimal team-reformation policies that tell our agents how to dynamically rearrange in order to better deal with the evolution of the task at hand. By reforming the team during execution, our experiments show that we are able to achieve higher expected long-term rewards than with stationary teams.
{"title":"Monte-Carlo Planning for Team Re-Formation Under Uncertainty: Model and Properties","authors":"Jonathan Cohen, A. Mouaddib","doi":"10.1109/ICTAI.2018.00077","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00077","url":null,"abstract":"Teamwork in decentralized systems plays a central role in recent artificial intelligence advances, such as in applications to disaster response. Decentralized partially observable Markov decision processes (Dec-POMDPs) have emerged as the de facto standard mathematical framework to study and optimally plan in sequentially decentralized multiagent systems under uncertainty. In this work, we focus our analysis on team formation and reformation in Decentralized POMDPs with a new model coined Team-POMDPs. We present some interesting structural properties of this model inherited from the field of cooperative game theory. We introduce a Monte Carlo-based planning algorithm to learn locally optimal team-reformation policies that tell our agents how to dynamically rearrange in order to better deal with the evolution of the task at hand. By reforming the team during execution, our experiments show that we are able to achieve higher expected long-term rewards than with stationary teams.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116491003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTAI.2018.00102
Fan Yang, Min Gao, Junliang Yu, Yuqi Song, Xinyi Wang
The recommendation systems have been widely employed due to the effectiveness on mitigating the information overload issue. At present, the recommendation systems have made great progress, but they are under the threat of shilling attack because of their open nature. Shilling attack is the way by which the attackers can manipulate the recommendation results and cause great harm to recommendation systems. Existing shilling attack detection models are mainly based on statistical measures to extract features like the rating deviation, which are generally susceptible to attack strategies. Once the attacker changes attack strategy, the detection model which is based on the statistical method may fail. Some researchers have identified that implicit features hidden in user-user interactions and user-item interactions can be utilized to solve the problem. Their research aims to learn potential relationship between users to update features. However, the research ignores the significance of learning features by employing label information. To solve this problem, in this paper, we propose a novel detection model, named BayesDetector, which takes not only the user-user and user-item interactions but also the label information into consideration in the process of learning user implicit features. Furthermore, to take full advantage of user labels, the Bayesian model is added to the feature learning. Experiments on two datasets, Amazon and Movielens, show that BayesDetector significantly outperforms the state-of-the-art methods.
{"title":"Detection of Shilling Attack Based on Bayesian Model and User Embedding","authors":"Fan Yang, Min Gao, Junliang Yu, Yuqi Song, Xinyi Wang","doi":"10.1109/ICTAI.2018.00102","DOIUrl":"https://doi.org/10.1109/ICTAI.2018.00102","url":null,"abstract":"The recommendation systems have been widely employed due to the effectiveness on mitigating the information overload issue. At present, the recommendation systems have made great progress, but they are under the threat of shilling attack because of their open nature. Shilling attack is the way by which the attackers can manipulate the recommendation results and cause great harm to recommendation systems. Existing shilling attack detection models are mainly based on statistical measures to extract features like the rating deviation, which are generally susceptible to attack strategies. Once the attacker changes attack strategy, the detection model which is based on the statistical method may fail. Some researchers have identified that implicit features hidden in user-user interactions and user-item interactions can be utilized to solve the problem. Their research aims to learn potential relationship between users to update features. However, the research ignores the significance of learning features by employing label information. To solve this problem, in this paper, we propose a novel detection model, named BayesDetector, which takes not only the user-user and user-item interactions but also the label information into consideration in the process of learning user implicit features. Furthermore, to take full advantage of user labels, the Bayesian model is added to the feature learning. Experiments on two datasets, Amazon and Movielens, show that BayesDetector significantly outperforms the state-of-the-art methods.","PeriodicalId":254686,"journal":{"name":"2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123277440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：