Shelley Zhang - Academia.edu (original) (raw)

Papers by Shelley Zhang

IEEE Transactions on Computational Social Systems, 2020

Increasingly popular social networks have become fast-growing platforms for information sharing, ... more Increasingly popular social networks have become fast-growing platforms for information sharing, job searching, and product marketing. Information propagates rapidly in social network and may reach a very large population within a very short period of time. An excessive amount of information shared in social networks not only costs computational and communicational resources but also causes the information overload problem, which results in the delay and difficulty of making decisions and may lead to physical and psychological strain. We used computer technologies to attack this information overload problem. First, we developed automatic decision-making mechanisms to help each individual effectively share information. Second, we built a simulation test bed and proposed an evaluation matrix and then conducted an experimental evaluation of six different information-sharing strategies in terms of interest degrees, reachability, appreciation degrees, and communication cost. We also implemented two intelligent response mechanisms. The first one allows users to order information pieces according to the learned ratings of the information sources. The second mechanism dynamically adjusts the network structure based on machine-learning results. The simulation results show that such mechanisms would be very useful to motivate social-network users to adopt more selective information-sharing strategies.

BIG (resource-Bounded Information Gathering) is a n e x t generation information gathering agent ... more BIG (resource-Bounded Information Gathering) is a n e x t generation information gathering agent w h i c h i n tegrates several areas of Arti cial Intelligence research under a single umbrella. To date, reported work has presented the rationale, architecture, and implementation of the system. This has included planning, reasoning about resource trade-o s of di erent possible gathering and extraction approaches, information extraction from both structured as well as unstructured documents, and opportunistic re nement of the search process using the extracted information. In this paper, we present recent improvements made to BIG, which make i t a m o r e v ersatile and robust system. These include documentation classi cation to handle distraction, sophisticated information fusion techniques, and nally the logistics behind search precision versus coverage tradeo s. We also present e mpirical evaluations which show the performance improvement due to these extensions.

Lecture Notes in Computer Science, 2009

Conservative design is the ability of an individual agent to ensure predictability of its overall... more Conservative design is the ability of an individual agent to ensure predictability of its overall performance even if some of its actions and interactions may be inherently less predictable or even completely unpredictable. In this paper, we describe the importance of conservative design in cooperative multi-agent systems and briefly characterize the challenges that need to be addressed to achieve this goal.

Artificial Intelligence, 1999

The World Wide Web,has become,an invaluable information,resource but the explosion of available i... more The World Wide Web,has become,an invaluable information,resource but the explosion of available information,has made,Web search a time consuming,and complex,process. The large number of information sources and their different levels of accessibility, reliability and associated costs present a complex information gathering control problem. This paper describes the rationale, architecture, and implementation of a next generation information gathering system—a system that

Proceedings of the third annual conference on Autonomous Agents, 1999

Intelligent environments are an interesting development and research application problem for mult... more Intelligent environments are an interesting development and research application problem for multi-agent systems. The functional and spatial distribution of tasks naturally lends itself to a multi-agent model and the existence of shared resources creates interactions over which the agents must coordinate. In the UMASS Intelligent Home project we have designed and implemented a set of distributed autonomous home control agents and deployed them in a simulated home environment. Our focus is primarily on resource coordination, though this project has multiple goals and areas of exploration ranging from the intellectual evaluation of the application as a general MAS testbed to the practical evaluation of our agent building and simulation tools.

Virtual Organizations

Background o What is VO? o Why use MAS to study VO  Formation process  Operation phase-individu... more Background o What is VO? o Why use MAS to study VO  Formation process  Operation phase-individual decision making  A statistical model for predication  Simulation and experiments  Conclusion and Future work

ACM Transactions on Intelligent Systems and Technology, 2012

We present a novel ensemble architecture for learning problem-solving techniques from a very smal... more We present a novel ensemble architecture for learning problem-solving techniques from a very small number of expert solutions and demonstrate its effectiveness in a complex real-world domain. The key feature of our “Generalized Integrated Learning Architecture” (GILA) is a set of heterogeneous independent learning and reasoning (ILR) components, coordinated by a central meta-reasoning executive (MRE). The ILRs are weakly coupled in the sense that all coordination during learning and performance happens through the MRE. Each ILR learns independently from a small number of expert demonstrations of a complex task. During performance, each ILR proposes partial solutions to subproblems posed by the MRE, which are then selected from and pieced together by the MRE to produce a complete solution. The heterogeneity of the learner-reasoners allows both learning and problem solving to be more effective because their abilities and biases are complementary and synergistic. We describe the applic...

Artificial Intelligence, 2000

Proceedings of the 21st Innovative Applications of Artificial Intelligence Conference, Sep 4, 2009

In this paper we describe the application of a novel learning and problem solving architecture to... more In this paper we describe the application of a novel learning and problem solving architecture to the domain of airspace management, where multiple requests for the use of airspace need to be reconciled and managed automatically. The key feature of our “Generalized Integrated Learning Architecture”(GILA) is a set of integrated learning and reasoning (ILR) systems coordinated by a central meta-reasoning executive (MRE). Each ILR learns independently from the same training example and contributes to problem- ...

Autonomous Agents & Multiagent Systems/Agent Theories, Architectures, and Languages, 2009

In this paper we present our method and experimental results for handling virtual organization (V... more In this paper we present our method and experimental results for handling virtual organization (VO) task management operations. First, we present a combinatorial auction approach to the initial commitment decision problem, which determines how a team task (i.e. VO task) can be allocated to a team of agents forming a virtual organization, while taking into consideration that the agents may be of different nature and they have other (their own) tasks in addition to the VO tasks. Then we present our solution to the crisis management problem, which determines at run time what to do when an agent decides to abandon a previously committed task in order to pursue a newly arrived, better task. We have built a testbed for evaluation of the strategies and used a building construction domain problem to show the effectiveness of our approach.