Jianshu Weng

An Entropy-Based Approach to Protecting Rating Systems from Unfair Testimonies

How to mitigate the influence of unfair testimonies remains an open issue in the research of rating systems. Methods have been proposed to filter the unfair testimonies in order to mitigate the influence of unfair testimonies. However, existing methods depend on assumptions that ratings follow a particular distribution to carry out the testimony filtering. This constrains them in specific rating systems and hinders their applications in other reputation systems. Moreover, existing methods do not scale well with the increase of testimony number due to their iterative nature. In this paper, a novel entropy-based method is proposed to measure the testimony quality, based on which unfair testimonies are further filtered. The proposed method does not require the assumption regarding the rating distribution. Moreover, it scales linearly with the increase of the testimony number. Experimental results show that the proposed method is effective in mitigating the influence of various types of unfair testimonies.

Improving collaborative filtering with trust-based metrics

Despite its success, similarity-based collaborative filtering suffers from some significant limitations, such as scalability and sparsity. This paper introduces trust to the domain of collaborative filtering to overcome these limitations. Compared with the similarity-based CF, introduction of trust does improve the performance of CF in terms of coverage, prediction accuracy, and robustness in the presence of attacks. Experimental results based on a real dataset are illustrated as evidences to support our claim.

Trust-based web service selection in virtual communities

In the present web service architecture, selecting which web service to use is still a task which requires a high level of human intervention. In this paper, we propose a trust-based web service selection process which aspires to automate part of the web service selection task to decrease the workload of human designers in the process. Most of the existing web service selection mechanisms are capability oriented or function oriented. We propose a trust-based web service selection approach to augment the current web service mechanisms. A trust model from our previous research, which offers strong protection against the adverse effect of unfair ratings from witnesses, is incorporated into an agent augmented service oriented virtual community. An experiment based on the virtual community system is conducted to study the effectiveness of the model in enabling trust agents to select highly trustworthy web services with minimal human supervision.

Credibility: How Agents Can Handle Unfair Third-Party Testimonies in Computational Trust Models

Usually, agents within multiagent systems represent different stakeholders that have their own distinct and sometimes conflicting interests and objectives. They would behave in such a way so as to achieve their own objectives, even at the cost of others. Therefore, there are risks in interacting with other agents. A number of computational trust models have been proposed to manage such risk. However, the performance of most computational trust models that rely on third-party recommendations as part of the mechanism to derive trust is easily deteriorated by the presence of unfair testimonies. There have been several attempts to combat the influence of unfair testimonies. Nevertheless, they are either not readily applicable since they require additional information which is not available in realistic settings, or ad hoc as they are tightly coupled with specific trust models. Against this background, a general credibility model is proposed in this paper. Empirical studies have shown that the proposed credibility model is more effective than related work in mitigating the adverse influence of unfair testimonies.

Trust-based collaborative filtering

• In order to identify similar users, similarity-based collaborative filtering techniques usually go through the whole user profiles database to calculate the similarities between the active user and all the other existing users. All the computations are carried out by a central server. The computation burden of the server increases quickly with the increase of the size of the profile database, leading to poor scalability. • Users tend to rate few items, the user profile database is usually sparse. Due to the sparsity, it is quite often the case that users do not co-rate the minimum number of items in common required to compute the similarity. In many cases, it is only possible to select similar users from a small portion of all users [1].

Fuzzy cognitive maps for dynamic grid service negotiation

The grid is moving from the scientific grid to a pervasive and economic/business grid. Service trading, in which service provider and service consumer negotiate for a mutually acceptable agreement on multi-issues such as service performance, access cost etc., is one of the most important components in building the Economic Grid. In view of Pervasive Grid, a new challenging issue is that participants on pervasive devices usually have limited computational capacity. And it is also desirable that a multi-issue negotiation agreement can be reached as quickly as possible since the wireless communication to exchange the offers is generally unreliable and power-consuming. Hence, an agile, automated, but lightweight multi-issue decision-making model is needed to facilitate service negotiation in Pervasive Grid. More over, existing methods for multi-issue negotiation only regard each issue as a separate issue, though in most of cases, there exist causal relationships between these negotiation issues. In this paper, a decision-making model based on Fuzzy Cognitive Map (FCM) theory is proposed for multi-issue negotiation which takes into account the causal relationships between the negotiation issues. In the proposed model, the causal relationships between the negotiation issues are well represented by FCMs. The service trading is modeled as a dynamic system with interdependent relationships among negotiation issues. The example and experimental results show that the proposed model is lightweight and promising to be employed in Pervasive Grid for multi-issue service negotiations.

Dynamic negotiations for grid services

A market-oriented grid introduces an economic or market-oriented perspective to the grid. Negotiation is a vital component that facilitates the market-oriented grid. Negotiating agents play an indispensable role within the market-oriented grid. The extremely dynamic nature of grid makes agent negotiation a new challenging research issue. In this paper, a new agent negotiation model is proposed to support the dynamic agent-mediated negotiation in a market-oriented grid environment.