Reputation-based trust models using statistical learning have been intensively studied for distributed systems where peers behave maliciously. However practical applications of such models in environments with both malicious and rational behaviors are still very little understood. This paper studies the relation between accuracy of a computational trust model and its ability to effectively enforce cooperation among rational agents. We provide theoretical results showing under which conditions cooperation emerges when using a trust learning algorithms with given accuracy and how cooperation can be still sustained while reducing cost and accuracy of those algorithms. We then verify and extend these theoretical results to a variety of settings involving honest, malicious and strategic players through extensive simulation. These results will enable a much more targeted, cost-effective and realistic design for decentralized trust management systems, such as needed for peer-to-peer systems and electronic commerce.
{"title":"Effective Usage of Computational Trust Models in Rational Environments","authors":"Le-Hung Vu, K. Aberer","doi":"10.1145/2019591.2019593","DOIUrl":"https://doi.org/10.1145/2019591.2019593","url":null,"abstract":"Reputation-based trust models using statistical learning have been intensively studied for distributed systems where peers behave maliciously. However practical applications of such models in environments with both malicious and rational behaviors are still very little understood. This paper studies the relation between accuracy of a computational trust model and its ability to effectively enforce cooperation among rational agents. We provide theoretical results showing under which conditions cooperation emerges when using a trust learning algorithms with given accuracy and how cooperation can be still sustained while reducing cost and accuracy of those algorithms. We then verify and extend these theoretical results to a variety of settings involving honest, malicious and strategic players through extensive simulation. These results will enable a much more targeted, cost-effective and realistic design for decentralized trust management systems, such as needed for peer-to-peer systems and electronic commerce.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2011-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123767817","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}
The ontology alignment has two kinds of major problems. First, the features used for ontology alignment are usually defined by experts, but it is highly possible for some critical features to be excluded from the feature set. Second, the semantic and the structural similarities are usually computed independently, and then they are combined in an ad-hoc way where the weights are determined heuristically. This paper proposes the modified parse tree kernel (MPTK) for ontology alignment. In order to compute the similarity between entities in the ontologies, a tree is adopted as a representation of an ontology. After transforming an ontology into a set of trees, their similarity is computed using MPTK without explicit enumeration of features. In computing the similarity between trees,the approximate string matching is adopted to naturally reflect not only the structural information but also the semantic information. According to a series of experiments with a standard data set, the kernel method outperforms other structural similarities such as GMO. In addition, the proposed method shows the state-of-the-art performance in the ontology alignment.
{"title":"An Ontology Alignment Based on Parse Tree Kernel for Combining Structural and Semantic Information without Explicit Enumeration of Features","authors":"J. Son, Seong-Bae Park, Se-Young Park","doi":"10.1109/WIIAT.2008.239","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.239","url":null,"abstract":"The ontology alignment has two kinds of major problems. First, the features used for ontology alignment are usually defined by experts, but it is highly possible for some critical features to be excluded from the feature set. Second, the semantic and the structural similarities are usually computed independently, and then they are combined in an ad-hoc way where the weights are determined heuristically. This paper proposes the modified parse tree kernel (MPTK) for ontology alignment. In order to compute the similarity between entities in the ontologies, a tree is adopted as a representation of an ontology. After transforming an ontology into a set of trees, their similarity is computed using MPTK without explicit enumeration of features. In computing the similarity between trees,the approximate string matching is adopted to naturally reflect not only the structural information but also the semantic information. According to a series of experiments with a standard data set, the kernel method outperforms other structural similarities such as GMO. In addition, the proposed method shows the state-of-the-art performance in the ontology alignment.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115238364","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}
Interactive environment described in this paper contains several tools and subsystems specialized for diagnostics, therapy and communication between persons interested in evaluating their cognitive capabilities (patients) and field experts (psychologists/therapists). According to functionality, components of the system can be divided into several categories: diagnostic cognitive functions, collecting and storing information about users, data analysis, and communication, interaction and collaboration between users.
{"title":"Interactive Environment Based on Internet Technologies for Psychometric Diagnostics, Psychotherapy and Collaboration","authors":"Velibor Ilic","doi":"10.1109/WIIAT.2008.120","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.120","url":null,"abstract":"Interactive environment described in this paper contains several tools and subsystems specialized for diagnostics, therapy and communication between persons interested in evaluating their cognitive capabilities (patients) and field experts (psychologists/therapists). According to functionality, components of the system can be divided into several categories: diagnostic cognitive functions, collecting and storing information about users, data analysis, and communication, interaction and collaboration between users.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127060287","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}
Resource selection in Grid involves great dynamics and uncertainties inherited from tasks and resources. The optimal selection of a resource against a task requires fast and intelligent services. Intelligent agent with fast learning capability is promising to resource selection problem in Grid. This paper proposes an Extreme Learning Machine (ELM)-based agent, in which an ELM connectionist module is embedded in an extended Belief-Desire-Intention (BDI) architecture. ELM empowers the agent with fast training and learning speed in the Grid environment. To improve generalization performance a cooperative learning among a group of ELM-based agents is proposed, for which the group decision is summarized upon individual decisions. The experiment results show that ELM-based agents are able to provide intelligent resource selection services, and the proposed cooperative learning outperforms the individual one.
{"title":"ELM-Based Agents for Grid Resource Selection","authors":"Guopeng Zhao, Zhiqi Shen, Ailiya, C. Miao","doi":"10.1109/WIIAT.2008.355","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.355","url":null,"abstract":"Resource selection in Grid involves great dynamics and uncertainties inherited from tasks and resources. The optimal selection of a resource against a task requires fast and intelligent services. Intelligent agent with fast learning capability is promising to resource selection problem in Grid. This paper proposes an Extreme Learning Machine (ELM)-based agent, in which an ELM connectionist module is embedded in an extended Belief-Desire-Intention (BDI) architecture. ELM empowers the agent with fast training and learning speed in the Grid environment. To improve generalization performance a cooperative learning among a group of ELM-based agents is proposed, for which the group decision is summarized upon individual decisions. The experiment results show that ELM-based agents are able to provide intelligent resource selection services, and the proposed cooperative learning outperforms the individual one.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126035604","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}
In networks, autonomous nodes have action choices along two dimensions: They can forward/process incoming service requests - or not, and they can establish new links and maintain or terminate existing ones. In other words, a node can choose both an action-selection and a link-selection strategy. Nodes in networks are either humans (as in social networks) or agents controlled by humans, so the question how humans forming networks behave is important. Humans behave boundedly rational at times, e.g., game-theoretic predictions do not always hold. This paper investigates the questions whether individuals being nodes in a network find and actually use strategies leading to efficiency (in the economic sense), how exogenous parameters influence behavior, and what are characteristics of the resulting network. We do so by carrying out laboratory experiments with human subjects (120 altogether) who form a network and have those action choices. Our work is different from previous work on P2P systems which lets nodes choose their actions or their links, but not both. Main findings are that link selection increases cooperation and results in optimal payoffs in relative terms. Thus, link selection fosters efficiency.
{"title":"The Network Game: Analyzing Network-Formation and Interaction Strategies in Tandem","authors":"Björn-Oliver Hartmann, Klemens Böhm, B. Vogt","doi":"10.1109/WIIAT.2008.22","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.22","url":null,"abstract":"In networks, autonomous nodes have action choices along two dimensions: They can forward/process incoming service requests - or not, and they can establish new links and maintain or terminate existing ones. In other words, a node can choose both an action-selection and a link-selection strategy. Nodes in networks are either humans (as in social networks) or agents controlled by humans, so the question how humans forming networks behave is important. Humans behave boundedly rational at times, e.g., game-theoretic predictions do not always hold. This paper investigates the questions whether individuals being nodes in a network find and actually use strategies leading to efficiency (in the economic sense), how exogenous parameters influence behavior, and what are characteristics of the resulting network. We do so by carrying out laboratory experiments with human subjects (120 altogether) who form a network and have those action choices. Our work is different from previous work on P2P systems which lets nodes choose their actions or their links, but not both. Main findings are that link selection increases cooperation and results in optimal payoffs in relative terms. Thus, link selection fosters efficiency.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125359563","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}
To ensure multi-agent based simulation models reproducibility, particular attention must be payed on its possible implementation ambiguities. This concerns every aspect of simulation's architecture, including how the agent selects the actions it performs, and on which agents it is performed. On this point, classical agent-centered design methodologies leave room to implicit design choices. We show in this paper how an interaction-centered design methodology provides guidelines to elicit these choices, and to remove possible implementation ambiguities underlying agent design. To illustrate this issue, we study which ambiguities underly even simple models and how our interaction-based methodology makes them appear.
{"title":"Interaction Selection Ambiguities in Multi-agent Systems","authors":"Yoann Kubera, P. Mathieu, S. Picault","doi":"10.1109/WIIAT.2008.260","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.260","url":null,"abstract":"To ensure multi-agent based simulation models reproducibility, particular attention must be payed on its possible implementation ambiguities. This concerns every aspect of simulation's architecture, including how the agent selects the actions it performs, and on which agents it is performed. On this point, classical agent-centered design methodologies leave room to implicit design choices. We show in this paper how an interaction-centered design methodology provides guidelines to elicit these choices, and to remove possible implementation ambiguities underlying agent design. To illustrate this issue, we study which ambiguities underly even simple models and how our interaction-based methodology makes them appear.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115025343","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}
A trend towards reforming the public sector has emerged in many countries. There are much experience that Chinese government should learn from the development process of e-Government in North America and EU. The structure and core concept of North America and EU in e-Government was introduced briefly in this paper. Though a large amount of money has been invested in the e-Government system construction, it is hard to say the system serves the citizen well. It wonpsilat be simple. E-government, as with all reforms, cannot be achieved simply by drafting a law or issuing an order from political leaders. Electronic government is neither easy nor cheap. At the same time, e-government responds to changes outside of government.
{"title":"E-government for the People: Learn from North America and European Union","authors":"Feng Ding, Yanzhang Wang, Xin Ye","doi":"10.1109/WIIAT.2008.144","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.144","url":null,"abstract":"A trend towards reforming the public sector has emerged in many countries. There are much experience that Chinese government should learn from the development process of e-Government in North America and EU. The structure and core concept of North America and EU in e-Government was introduced briefly in this paper. Though a large amount of money has been invested in the e-Government system construction, it is hard to say the system serves the citizen well. It wonpsilat be simple. E-government, as with all reforms, cannot be achieved simply by drafting a law or issuing an order from political leaders. Electronic government is neither easy nor cheap. At the same time, e-government responds to changes outside of government.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116055269","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}
Paul Doran, V. Tamma, I. Palmisano, T. Payne, L. Iannone
In this paper we therefore propose a reformulation of the entropy metric to evaluate the amount of information carried by both the ontology structure, and also by the language elements (i.e. the semantics associated with the edges in the ontological graph). To evaluate this approach, the reformulated metric is empirically compared to Calemt & Daemi's original entropy metric, for a variety of different sized modules. The results suggest that not only can entropy differentiate between structurally different modules of the same size, but that our improved entropy metric provides a finer grain differentiation than the original entropy metric.
{"title":"Evaluating Ontology Modules Using an Entropy Inspired Metric","authors":"Paul Doran, V. Tamma, I. Palmisano, T. Payne, L. Iannone","doi":"10.1109/WIIAT.2008.256","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.256","url":null,"abstract":"In this paper we therefore propose a reformulation of the entropy metric to evaluate the amount of information carried by both the ontology structure, and also by the language elements (i.e. the semantics associated with the edges in the ontological graph). To evaluate this approach, the reformulated metric is empirically compared to Calemt & Daemi's original entropy metric, for a variety of different sized modules. The results suggest that not only can entropy differentiate between structurally different modules of the same size, but that our improved entropy metric provides a finer grain differentiation than the original entropy metric.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116222502","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}
Scheduling is the allocation of shared resources over time in order to perform a number of tasks. Job Shop Scheduling Problem (JSSP) is the most commonly encountered scheduling problem. A wide range of approaches have been proposed to solve it. In this paper two multi-agent based evolutionary models are proposed to tackle JSSP. The first one is Multi-Agent based Genetic Algorithm (MAGA) and the second model is a Multi-Agent Particle Swarm Optimization (MAPSO). A proposed local search technique as self-learning procedure for agents is hybridized with both of the multi-agent models to enhance their efficiency. The proposed models have been implemented using REPAST toolkit. Encouraging results from both models have been obtained for standard benchmarks from OR library.
{"title":"Improving Multi-agent Evolutionary Techniques with Local Search for Job Shop Scheduling Problem","authors":"Ahmad Balid, S. Minz","doi":"10.1109/WIIAT.2008.191","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.191","url":null,"abstract":"Scheduling is the allocation of shared resources over time in order to perform a number of tasks. Job Shop Scheduling Problem (JSSP) is the most commonly encountered scheduling problem. A wide range of approaches have been proposed to solve it. In this paper two multi-agent based evolutionary models are proposed to tackle JSSP. The first one is Multi-Agent based Genetic Algorithm (MAGA) and the second model is a Multi-Agent Particle Swarm Optimization (MAPSO). A proposed local search technique as self-learning procedure for agents is hybridized with both of the multi-agent models to enhance their efficiency. The proposed models have been implemented using REPAST toolkit. Encouraging results from both models have been obtained for standard benchmarks from OR library.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116558538","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}
Recommender Systems is one of the effective tools to deal with information overload issue. Similar with the explicit rating and other implicit rating behaviors such as purchase behavior, click streams, and browsing history etc., the tagging information implies userpsilas important personal interests and preferences information, which can be used to recommend personalized items to users. This paper is to explore how to utilize tagging information to do personalized recommendations. Based on the distinctive three dimensional relationships among users, tags and items, a new user profiling and similarity measure method is proposed. The experiments suggest that the proposed approach is better than the traditional collaborative filtering recommender systems using only rating data.
{"title":"Collaborative Filtering Recommender Systems Using Tag Information","authors":"Huizhi Liang, Yue Xu, Yuefeng Li, R. Nayak","doi":"10.1109/WIIAT.2008.97","DOIUrl":"https://doi.org/10.1109/WIIAT.2008.97","url":null,"abstract":"Recommender Systems is one of the effective tools to deal with information overload issue. Similar with the explicit rating and other implicit rating behaviors such as purchase behavior, click streams, and browsing history etc., the tagging information implies userpsilas important personal interests and preferences information, which can be used to recommend personalized items to users. This paper is to explore how to utilize tagging information to do personalized recommendations. Based on the distinctive three dimensional relationships among users, tags and items, a new user profiling and similarity measure method is proposed. The experiments suggest that the proposed approach is better than the traditional collaborative filtering recommender systems using only rating data.","PeriodicalId":393772,"journal":{"name":"2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2008-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122515688","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：